Open-Source AI Frameworks
Guides to the open-source frameworks teams use to build AI applications — with practical implementation notes and where a production partner helps.
In this category
9router
9Router is an MIT-licensed Node.js/JavaScript gateway that proxies requests from AI coding tools (Claude Code, Cursor, Cline, Copilot) to 40+ LLM providers, imp…
A2A
A2A is an open protocol that lets AI agents built on different frameworks communicate and work together securely without exposing their internal logic or tools.…
a2a-python
The A2A Python SDK is an official library for building agentic applications that comply with the Agent2Agent (A2A) Protocol. It supports multiple transport prot…
abogen
Abogen converts ePub, PDF, and text files into audiobooks with synchronized captions using the Kokoro-82M text-to-speech model. It offers both a PyQt6 desktop G…
aci
ACI.dev is an open-source platform that connects AI agents to 600+ third-party tools and services (like Google Calendar, Slack, Vercel) through a unified interf…
Acontext
Acontext is an open-source memory layer for AI agents that automatically captures learnings from agent runs and stores them as plain Markdown skill files. Agent…
AdalFlow
AdalFlow is a Python library for building and auto-optimizing LLM applications (chatbots, RAG systems, agents) with a PyTorch-like API. It includes built-in pro…
adk-go
ADK Go is Google's open-source toolkit for building AI agents in Go, designed for cloud-native applications. It provides a modular, code-first framework that wo…
adk-python
ADK (Agent Development Kit) is Google's open-source Python framework for building, evaluating, and deploying AI agents using a code-first approach. It provides …
ag2
AG2 is an open-source Python framework for building multi-agent AI systems where agents collaborate to solve tasks using LLMs and tools. It evolved from AutoGen…
agency-agents-zh
A curated library of 266 plug-and-play AI agent role definitions (215 translated English roles + 50 original China-market roles) designed for integration into 1…
agent
Stakpak is an open-source DevOps agent written in Rust that runs continuously on your infrastructure to automate operational tasks. It uses AI models (via Anthr…
agent-lightning
Agent Lightning is a Python framework for training and optimizing AI agents using reinforcement learning and other algorithms. It integrates with existing agent…
Agent_Memory_Techniques
A collection of 30 runnable Jupyter notebooks teaching LLM agent memory techniques, from basic conversation buffers to advanced frameworks like MemGPT, Mem0, an…
agent-squad
Agent Squad is an open-source framework for orchestrating multiple AI agents in conversations, routing queries intelligently to specialized agents while maintai…
agent-starter-pack
Agent Starter Pack is a Python framework from Google Cloud that provides production-ready templates for building GenAI agents on Google Cloud. It bundles infras…
agentic-radar
Agentic Radar is a Python-based security scanner that analyzes LLM agentic workflows to identify vulnerabilities, visualize system architecture, and map detecte…
agentic-rag-for-dummies
Agentic RAG for Dummies is an educational and production-ready framework for building retrieval-augmented generation systems using LangGraph. It provides hierar…
agenticSeek
AgenticSeek is a fully local, privacy-focused AI agent framework written in Python that enables autonomous web browsing, code generation, and task planning with…
Agently
Agently is a Python framework for building AI agent applications with structured outputs, observable actions, and reusable workflows. It abstracts model provide…
agentops
AgentOps is a Python SDK that provides observability, monitoring, and debugging for AI agents. It tracks LLM costs, captures agent execution flows, and integrat…
agents-cli
agents-cli is a Google-backed CLI tool and skill suite that extends coding assistants (Claude, Antigravity, etc.) with commands to build, evaluate, and deploy A…
agentscope
AgentScope is a Python framework for building and deploying multi-agent systems with built-in observability, permission controls, and production-grade serving. …
AGiXT
AGiXT is a Python-based AI automation platform that orchestrates tasks across multiple AI providers (OpenAI, Anthropic, Google, local models) through a plugin s…
ai
TanStack AI is a TypeScript SDK that lets you build AI chat, tool-calling agents, and multimodal apps by switching between providers (OpenAI, Anthropic, Gemini,…
ai-berkshire
AI Berkshire is a Python-based investment research framework that combines Claude/Codex with value investing methodologies from four masters (Buffett, Munger, D…
ai-data-science-team
AI Data Science Team is a Python library providing pre-built AI agents for automating common data science tasks—loading, cleaning, visualization, and modeling—p…
ai-for-grant-writing
A curated collection of AI tools, prompts, and resources for improving grant applications using language models. The repository organizes services (ChatGPT, Gem…
aichat
AIChat is a unified CLI tool for interacting with 20+ LLM providers (OpenAI, Claude, Gemini, Ollama, etc.) through a single interface. It offers shell command g…
aici
AICI is a Microsoft Research framework that lets you write programs (as WebAssembly modules) to control and constrain LLM output in real time. Controllers can e…
aiconfig
AIConfig is an open-source Python/Node framework that separates AI prompts, model parameters, and settings from application code by storing them as JSON configs…
AionUi
AionUi is a free, open-source desktop application that provides a unified interface for coordinating multiple AI agents (Claude Code, Codex, etc.) on your local…
airllm
AirLLM is an open-source inference framework that runs very large language models (70B–671B parameters) on consumer-grade GPUs with limited VRAM by loading mode…
airweave
Airweave is an open-source retrieval layer that connects AI agents to enterprise data sources via 50+ integrations. It handles data synchronization, indexing, a…
Anthropic-Cybersecurity-Skills
A community-maintained library of 817 structured cybersecurity skills designed to equip AI agents (Claude, Copilot, Gemini, etc.) with expert-level security kno…
anything-llm
AnythingLLM is a self-hosted, all-in-one AI application that lets you chat with documents and run AI agents without external dependencies. It supports multiple …
APT
APT is a free, open-source Windows desktop application for local AI inference and batch media processing. It bundles offline models (ChatGPT, DeepSeek, Phi, Qwe…
AReaL
AReaL is an open-source reinforcement learning infrastructure designed to train AI agents at scale using asynchronous, distributed training. It bridges foundati…
argilla
Argilla is an open-source Python-based collaboration platform for building, annotating, and iterating on high-quality datasets for AI/ML projects. It supports t…
asl-ml-immersion
This is Google Cloud's official educational repository containing machine learning and generative AI notebooks, code samples, and reference architectures for ru…
AstrBot
AstrBot is an open-source Python-based AI agent platform that integrates with messaging apps (QQ, Telegram, WeChat, Slack, etc.) and LLMs to build conversationa…
astron-agent
Astron Agent is an enterprise-grade, open-source workflow platform for building multi-agent AI applications with built-in RPA automation, model management, and …
astron-rpa
AstronRPA is an open-source enterprise RPA desktop application that enables low-code/no-code automation of Windows applications and web pages through a visual d…
semantic-router
Semantic Router is a Python library that uses vector embeddings to make fast routing decisions for LLMs and agents without waiting for slow LLM generation. It c…
Auto-claude-code-research-in-sleep
ARIS is a lightweight, framework-agnostic Python toolkit for automating ML research workflows through cross-model review loops, idea generation, and experiment …
autoclip
AutoClip is a Python-based AI video processing system that automatically downloads videos from YouTube or Bilibili, analyzes them using LLMs to identify highlig…
AutoRAG
AutoRAG is an open-source Python framework that automates the process of building and optimizing Retrieval-Augmented Generation (RAG) pipelines for your specifi…
axolotl
Axolotl is an open-source Python framework for fine-tuning large language models (LLMs) with support for modern techniques like LoRA, quantization-aware trainin…
baml
BAML is a statically-typed programming language built for AI agents, combining TypeScript-like syntax with Rust-level type safety and runtime type persistence. …
bayesflow
BayesFlow is a Python library for amortized Bayesian inference that combines simulation-based modeling with deep learning. It supports multiple ML backends (PyT…
bedrock-chat
Bedrock Chat is an AWS-native chatbot platform built on Amazon Bedrock that supports multi-tenant chat, custom bots with knowledge bases (RAG), bot sharing, and…
BentoML
BentoML is a Python framework that turns machine learning models into production-ready APIs and serving systems with minimal code. It handles packaging, Docker …
Bert-VITS2
Bert-VITS2 is a Python-based text-to-speech (TTS) synthesis system combining VITS2 architecture with multilingual BERT embeddings for voice generation. The proj…
beta9
Beta9 is an open-source serverless GPU inference platform that lets you deploy, scale, and run AI workloads with minimal infrastructure overhead. It supports bo…
better-agents
Better Agents is a CLI tool and standards framework for building AI agents across multiple frameworks (Agno, Mastra, LangGraph, etc.). It provides project scaff…
bifrost
Bifrost is a Go-based AI gateway that unifies access to 1000+ models across 23+ providers (OpenAI, Anthropic, AWS, Google, etc.) through a single OpenAI-compati…
biniou
Biniou is a self-hosted web interface for 30+ generative AI models spanning text, image, audio, and video generation. It runs on commodity hardware (CPU-based, …
bisheng
BISHENG is an open-source LLM DevOps platform designed for enterprise AI applications, offering workflow orchestration, RAG, agent framework, model management, …
bitsandbytes
bitsandbytes is a Python library that makes large language models more memory-efficient through quantization techniques, enabling inference and training on cons…
botpress
Botpress is an open-source platform for building and deploying AI-powered chatbots and agents using LLMs like GPT-4. It provides a TypeScript SDK, CLI, and clou…
BrickGPT
BrickGPT is a fine-tuned language model that generates physically stable LEGO-like brick structures from text descriptions. It combines LLM reasoning with physi…
browser-harness
Browser Harness is a Python framework that connects large language models directly to Chrome via CDP (Chrome DevTools Protocol), enabling autonomous browser aut…
browser-use
Browser Use is a Python framework that enables AI agents to interact with websites by automating browser actions like clicking, typing, and form submission. It …
BrowserOS
BrowserOS is an open-source Chromium-based browser with built-in AI agent capabilities that can automate browser tasks via natural language. It supports both cl…
burr
Apache Burr is a Python framework for building stateful AI applications (chatbots, agents, simulations) using a state-machine model. It provides built-in monito…
casdoor
Casdoor is an open-source identity and access management (IAM) platform with a web UI, built to handle authentication (OAuth, OIDC, SAML, LDAP, WebAuthn) and us…
Causal-Forcing
Causal Forcing is a Python-based video generation framework that uses autoregressive diffusion distillation to enable real-time text-to-video and image-to-video…
caveman
Caveman is a prompt-engineering skill/plugin for Claude Code and 30+ other AI agents that reduces output tokens by ~65% by constraining agent responses to conci…
ccg-workflow
CCG is a workflow engine that orchestrates multiple AI models (Claude, Codex, Gemini) to automate software development tasks. Users describe what they want in p…
ChainForge
ChainForge is an open-source visual programming tool for testing and comparing LLM prompts across multiple models and parameter combinations. It enables rapid e…
chainlit
Chainlit is a Python framework for rapidly building conversational AI applications with a web UI, designed to work with LLMs like OpenAI and integrations such a…
chat-ui
Chat UI is an open-source TypeScript/SvelteKit application that provides a web interface for interacting with LLMs via OpenAI-compatible APIs. It powers Hugging…
ChatALL
ChatALL is a desktop application that lets you send prompts to multiple AI bots (ChatGPT, Claude, Gemini, etc.) simultaneously and compare their responses side-…
ChatGPT-Shortcut
ChatGPT-Shortcut is an open-source prompt management platform with 5000+ curated AI prompts for ChatGPT, Claude, and other AI tools. Users can search, copy, org…
ChatTTS
ChatTTS is a generative speech synthesis model optimized for dialogue and conversational AI applications. It supports English and Chinese with fine-grained cont…
Chinese-LLaMA-Alpaca
Chinese-LLaMA-Alpaca is an open-source project providing Chinese-optimized language models based on Meta's LLaMA, with extended vocabulary and instruction-tuned…
Chinese-LLaMA-Alpaca-2
Chinese-LLaMA-Alpaca-2 is an open-source project providing Chinese-optimized large language models (1.3B–13B parameters) based on Meta's Llama-2. It includes ba…
chronos-forecasting
Chronos is Amazon's open-source time series forecasting library providing pretrained transformer-based models (Chronos-2, Chronos-Bolt, and original Chronos) th…
ClawRouter
ClawRouter is an open-source LLM router that automatically selects and routes requests to the cheapest capable model from 55+ options (OpenAI, Anthropic, Google…
clearml
ClearML is an open-source MLOps platform that automates experiment tracking, model management, and orchestration for AI/ML workloads. It provides centralized tr…
clickclickclick
ClickClickClick is a Python framework that enables autonomous interaction with Android devices and desktop computers using various LLMs (local or remote). It br…
cocoindex
CocoIndex is an open-source incremental data indexing engine written in Rust with Python bindings, designed to keep AI agents and LLM applications supplied with…
code-review-graph
code-review-graph builds a persistent code intelligence graph using Tree-sitter to map your codebase structure and dependencies. It integrates with AI coding to…
CodeGen
CodeGen is an open-source family of language models (350M–16B parameters) trained by Salesforce for code generation and program synthesis. It offers multiple mo…
CodeMachine-CLI
CodeMachine is an open-source CLI tool that lets developers define AI coding workflows once and reuse them repeatedly. It orchestrates multiple AI agents (Claud…
CodeWhale
CodeWhale is an open-source terminal agent (TUI/CLI) written in Rust that lets you point a coding agent at a codebase and a language model, and it reads code, m…
codex-mobile
codex-mobile is a lightweight Node.js web bridge that exposes a Codex AI assistant UI in the browser, running on Linux, Windows, or Android (via Termux). It pro…
coffee
Coffee is an open-source IDE plugin that uses AI to generate and iteratively edit React components within your existing codebase. Developers mark sections with …
CogVideo
CogVideo is an open-source text-to-video and image-to-video generation system built on diffusion models. It includes CogVideoX (2024) and the earlier CogVideo (…
ComfyUI_frontend
ComfyUI_frontend is the official TypeScript-based web interface for ComfyUI, a node-based generative AI platform. It provides workflow visualization, node manag…
ComfyUI_Yvann-Nodes
ComfyUI_Yvann-Nodes is a Python package that adds audio-reactivity capabilities to ComfyUI, enabling users to generate AI-driven animations that synchronize wit…
composio
Composio is an open-source SDK (TypeScript and Python) that provides 1000+ pre-built tool integrations, authentication, and context management for building AI a…
context7
Context7 is an MCP server and CLI tool that injects up-to-date, version-specific library documentation and code examples directly into LLM prompts, eliminating …
contextgem
ContextGem is an open-source Python framework that automates structured data extraction from documents using LLMs, handling prompt generation, validation, and s…
CopilotKit
CopilotKit is an open-source SDK for building AI agent applications with generative UI across web (React, Angular, Vue), mobile (React Native), and chat platfor…
council
Council is an open-source Python platform for building and deploying LLM-powered applications with a unified interface across providers like OpenAI, Anthropic, …
CowAgent
CowAgent is an open-source AI agent framework written in Python that orchestrates task planning, tool execution, and multi-channel communication. It supports mu…
coze-loop
Coze Loop is an open-source AI agent development platform providing full-lifecycle management from prompt engineering and debugging through evaluation and post-…
coze-studio
Coze Studio is an open-source, visual AI agent development platform built in TypeScript and Go that enables teams to create, debug, and deploy AI agents through…
crewAI
CrewAI is an open-source Python framework for building multi-agent AI systems where autonomous agents collaborate to solve complex tasks. It provides both role-…
CushyStudio
CushyStudio is a TypeScript-based generative AI platform for creating images, videos, and 3D models through a visual interface and custom apps. It integrates Co…
daily_stock_analysis
An LLM-powered stock analysis system for multiple markets (A-shares, Hong Kong, US, Japan, Korea, Taiwan) that aggregates real-time market data, news, and gener…
datasets
Hugging Face Datasets is a Python library for downloading, processing, and managing AI datasets from the Hub or local files. It supports 100+ formats including …
Dayflow
Dayflow is a macOS productivity tool that automatically records screen activity and converts it into a structured work journal using AI analysis. It runs locall…
DB-GPT
DB-GPT is an open-source Python platform that connects to databases, files, and knowledge bases to enable AI-driven data analysis, SQL generation, and report cr…
Decepticon
Decepticon is an autonomous red team agent built on LLM and LangGraph that executes realistic attack chains (reconnaissance, exploitation, lateral movement) wit…
deep-searcher
DeepSearcher is an open-source Python framework that combines large language models (OpenAI, DeepSeek, Claude, etc.) with vector databases (Milvus, Zilliz) to p…
DeepAnalyze
DeepAnalyze is an open-source agentic LLM system for autonomous data science that automates the full pipeline from data preparation through analysis, modeling, …
DeepAudit
DeepAudit is an open-source Python-based multi-agent system for automated code vulnerability detection and auditing. It uses LLMs (supporting Ollama private dep…
deeplake
Deep Lake is an open-source AI data platform that acts as a database and vector store for large-scale machine learning and LLM applications. It stores multimoda…
deepreasoning
DeepReasoning is a Rust-based inference API that chains DeepSeek R1's reasoning traces with Anthropic Claude for combined problem-solving and code generation. I…
DeepResearch
Tongyi DeepResearch is an open-source agentic LLM with 30.5B parameters (3.3B active) designed for autonomous web research and information-seeking tasks. It com…
DeepSeek-Reasonix
DeepSeek-Reasonix is a terminal-based AI coding agent written in Go, designed to work natively with DeepSeek's API and optimized for token efficiency through pr…
deer-flow
DeerFlow is an open-source agentic framework from ByteDance that orchestrates AI agents with sandboxes, memory, and extensible skills to handle long-running res…
designing-multiagent-systems
A comprehensive educational repository and accompanying book on building multi-agent systems from first principles. Includes PicoAgents, a fully implemented fra…
dify
Dify is an open-source platform for building and deploying AI applications with visual workflows, RAG pipelines, and agent capabilities. It supports hundreds of…
DocsGPT
DocsGPT is an open-source AI platform for building private agents and assistants with document analysis, multi-model support, and enterprise search capabilities…
dynamiq
Dynamiq is an open-source orchestration framework for building AI agents and LLM applications with support for RAG, multi-agent workflows, and integration with …
E2B
E2B is an open-source platform that lets you run AI-generated code safely in isolated cloud sandboxes. It provides Python and JavaScript SDKs for developers to …
EasyR1
EasyR1 is an open-source reinforcement learning framework for training vision-language and language models efficiently at scale. It supports multiple RL algorit…
EBT
Energy-Based Transformers (EBT) is a PyTorch research implementation enabling generalized reasoning and scalable learning across modalities (NLP, images, video)…
ECC
ECC is a performance optimization framework for AI coding agents (Claude, Cursor, Codex, etc.) that bundles skills, memory management, security scanning, and cr…
edict
Edict is a Python-based multi-agent orchestration system inspired by ancient imperial governance structures, featuring 12 specialized AI agents, a real-time Kan…
Edit-Banana
Edit-Banana is a Python framework that converts static diagrams (PNG, JPG, etc.) into editable DrawIO XML format. It uses SAM 3 for element segmentation, multim…
embabel-agent
Embabel is a JVM-based agent framework written in Kotlin that lets you build AI agents by mixing LLM interactions with your own code and domain models. It uses …
EmbedAnything
EmbedAnything is a Rust-based embedding pipeline for generating vector embeddings from text, images, audio, and PDFs. It supports multiple embedding backends (C…
emdash
Emdash is an open-source desktop application that orchestrates multiple AI coding agents in parallel, isolating each task in its own Git worktree for independen…
END-TO-END-GENERATIVE-AI-PROJECTS
A curated collection of 18+ end-to-end generative AI projects demonstrating LLM applications including RAG systems, chatbots, document processing, and fine-tuni…
envd
envd is a CLI tool that simplifies creation of containerized development environments for AI/ML workloads by replacing complex Dockerfiles and shell scripts wit…
epub2tts
epub2tts is a Python tool that converts EPUB or text files into audiobooks using multiple text-to-speech engines (Coqui TTS, OpenAI, Microsoft Edge, Kokoro). It…
EverOS
EverOS is a Python library that provides a portable memory layer for AI agents, storing conversations and knowledge as readable Markdown files with SQLite and L…
fastapi_mcp
FastAPI-MCP is a Python library that automatically exposes your FastAPI API endpoints as Model Context Protocol (MCP) tools, enabling AI assistants like Claude …
fastrtc
FastRTC is a Python library for building real-time audio/video applications with WebRTC and WebSocket support. It simplifies integrating voice assistants, speec…
firecrawl
Firecrawl is an open-source web scraping and data extraction API that converts websites into clean markdown or structured JSON. It handles JavaScript-heavy site…
FlagEmbedding
FlagEmbedding is an open-source Python toolkit for building retrieval and retrieval-augmented generation (RAG) systems using embedding models and rerankers. It …
Flowise
Flowise is a visual, low-code platform for building AI agents and workflows without writing code. It integrates with LLMs like OpenAI and supports RAG, multi-ag…
flyte
Flyte is an open-source workflow orchestration platform for machine learning and data pipelines, written in Go with Python SDK support. It enables teams to defi…
forge-film
Forge is an open-source Python orchestration engine that compiles film stories into scene dependency graphs and schedules parallel video generation across multi…
Foundation-Models-Framework-Lab
Foundation Lab is a native iOS and macOS workbench for building, testing, and deploying applications using Apple's Foundation Models framework. It provides an i…
fragments
Fragments is an open-source Next.js template that enables building AI-generated applications similar to Claude Artifacts or Vercel v0. It integrates with the E2…
FunClip
FunClip is an open-source video transcription and clipping tool built on Alibaba's FunASR, with a local Gradio UI for subtitle generation and LLM-assisted intel…
gateway
Portkey Gateway is an open-source API routing layer that unifies access to 1,600+ language models, vision models, and AI services through a single standardized …
Gemini-API
Gemini-API is a reverse-engineered Python wrapper for Google's Gemini web interface, offering asynchronous access to text generation, image/video/audio creation…
genai-processors
GenAI Processors is a lightweight Python library for building modular, asynchronous AI pipelines that work with Google's Gemini API and other generative models.…
generative-ai
A Google Cloud–maintained repository of sample code, Jupyter notebooks, and reference implementations demonstrating how to build generative AI applications usin…
generative_ai_project
A structured, Apache 2.0-licensed template repository for building scalable generative AI applications. Provides modular organization (agents, memory, retrieval…
generative-ai-use-cases
AWS GenU is a TypeScript application providing pre-built generative AI use cases (chat, RAG, summarization, image generation, agents) integrated with AWS Bedroc…
generative-ai-with-javascript
Microsoft's JavaScript-based generative AI course teaches developers how to build AI-powered applications through hands-on lessons, video tutorials, and a compa…
Generative-Media-Skills
A collection of 41 CLI-driven workflow recipes and agent skills for AI-powered image, video, and audio generation. Designed as composable tools for Claude Code,…
generative-ai
A comprehensive learning repository and resource hub for generative AI, covering roadmaps, practical projects, use cases, and interview preparation. It includes…
GenieX
GenieX is Qualcomm's runtime for running large language models and vision models locally on Snapdragon devices (Windows ARM64, Android, Linux ARM64) without clo…
giskard-oss
Giskard is an open-source Python library for testing and evaluating AI agents and LLM-based systems. It provides tools for creating evals (tests that validate n…
git-mcp
GitMCP is a free, open-source MCP server that connects AI assistants (Claude, Cursor, Copilot) to GitHub repositories, enabling them to access current documenta…
gitleaks
Gitleaks is a Go-based CLI tool that scans git repositories, directories, and stdin for hardcoded secrets like passwords, API keys, and tokens using regex-based…
GLM-4.5
GLM-4.5 is a 355B-parameter foundation model series (with compact 106B Air variant) designed for agentic AI applications, featuring hybrid reasoning modes for c…
gollm
gollm is a Go library that provides a unified interface to interact with multiple LLM providers (OpenAI, Anthropic, Groq, Ollama, etc.) with built-in support fo…
gorilla
Gorilla is an open-source project that fine-tunes large language models to accurately invoke APIs and call functions from natural language instructions. It incl…
GPTCache
GPTCache is a semantic caching layer for LLM queries that reduces API costs and latency by storing and retrieving similar responses from a local cache instead o…
gptme
gptme is an open-source AI agent that runs in your terminal, equipped with tools to write code, execute shell commands, and browse the web. It works with multip…
gpustack
GPUStack is an open-source GPU cluster manager that orchestrates inference engines (vLLM, SGLang, TensorRT-LLM) across multi-cloud and on-premises GPU clusters.…
graphrag
GraphRAG is a Microsoft open-source Python system that combines knowledge graphs with large language models to improve reasoning over private, unstructured text…
guardrails
Guardrails is a Python framework for adding safety checks to LLM applications through input/output validation and structured data generation. It provides pre-bu…
h2o-llmstudio
H2O LLM Studio is a no-code GUI and Python framework for fine-tuning large language models without coding experience. It supports modern techniques like LoRA, 8…
hallucination-leaderboard
The Hallucination Leaderboard is an open-source benchmarking tool that ranks LLM performance on factual accuracy when summarizing documents, using Vectara's HHE…
hamilton
Apache Hamilton is a Python library for building portable, modular data transformation DAGs that run anywhere Python executes—notebooks, scripts, Airflow, FastA…
Hands-On-Large-Language-Models
Official code repository for the O'Reilly book "Hands-On Large Language Models" by Jay Alammar and Maarten Grootendorst. Contains 12 Jupyter notebooks covering …
harness-sdk
Strands Agents is an open-source Python and TypeScript SDK for building and running AI agents with any LLM provider (OpenAI, Anthropic, Bedrock, Gemini, etc.). …
headroom
Headroom is a Python/TypeScript compression layer that reduces LLM token consumption by 60–95% on structured data and 15–20% on code by intelligently compressin…
heretic
Heretic is a Python tool that automatically removes safety alignment restrictions from language models using abliteration techniques, without requiring manual t…
hermes-agent
Hermes Agent is a Python-based AI agent framework from Nous Research that runs locally or in the cloud with built-in memory, skill learning, and multi-platform …
hermes-desktop
Hermes Desktop is a TypeScript-based native desktop application that provides a graphical interface for installing, configuring, and interacting with Hermes Age…
hexstrike-ai
HexStrike AI is an MCP server that connects large language models (Claude, GPT, Copilot) to 150+ cybersecurity tools for automated penetration testing, vulnerab…
honcho
Honcho is a memory infrastructure platform for AI agents that persists conversations, events, and context over time. It extracts reasoning from interactions to …
Horizon
Horizon is a Python-based AI-powered news aggregation tool that autonomously fetches, summarizes, and ranks news from multiple sources, delivering daily briefin…
html-anything
html-anything is a local-first HTML editor that uses AI agents (Claude, Cursor, Gemini, etc.) to generate HTML documents in multiple formats—decks, posters, rep…
Huatuo-Llama-Med-Chinese
BenTsao (formerly HuaTuo) is an open-source Chinese medical large language model built by instruction-tuning LLaMA, Alpaca, Bloom, and Huozi base models with me…
IncarnaMind
IncarnaMind is a Python application that lets you chat with your PDF and TXT documents using multiple LLMs—OpenAI GPT, Anthropic Claude, Llama2, or local open-s…
inference
Xinference is an open-source Python library for deploying and serving large language models, speech recognition, and multimodal AI models through a unified API.…
Infographic
Infographic is an open-source TypeScript framework that generates and renders data visualizations from declarative syntax, with AI-friendly design for streaming…
inkos
InkOS is a TypeScript-based AI agent system for story creation supporting novels, scripts, interactive games, and IP content. It offers Studio, TUI, and CLI int…
Integuru
Integuru is an AI agent that reverse-engineers internal APIs from platforms without public API documentation by analyzing browser network traffic. It generates …
InternVL
InternVL is an open-source multimodal vision-language model family designed to match or approach GPT-4o performance. It supports image classification, semantic …
intro_dgm
intro_dgm is an educational GitHub repository containing Jupyter notebook implementations of major deep generative modeling techniques (VAEs, GANs, diffusion mo…
Janus
Janus is a unified multimodal AI model from DeepSeek that handles both image understanding and text-to-image generation in a single architecture. Available in m…
jcode
jcode is a CLI-based AI coding agent harness written in Rust, designed for multi-session workflows with Claude, OpenAI, and other LLM providers. It emphasizes p…
JeecgBoot
JeecgBoot is an open-source AI-driven low-code platform built on Java (Spring Boot 4) that combines low-code (code generation) and zero-code (visual configurati…
JoyVASA
JoyVASA is a Python-based diffusion model for generating animated talking heads and animal faces driven by audio input. It decouples facial appearance from moti…
json_repair
json_repair is a Python library that fixes malformed JSON from LLMs, APIs, logs, and user input by repairing syntax errors like missing quotes, commas, and brac…
julep
Julep is a Python framework for building durable, composable AI agents as dataflows that can crash, resume, and retry safely. It provides a decorator-based auth…
khoj
Khoj is a self-hosted AI assistant that lets you chat with local or cloud LLMs and search your documents. It integrates with Obsidian, Emacs, browser, desktop, …
klavis
Klavis is an open-source Model Context Protocol (MCP) integration platform that connects AI agents to 100+ prebuilt tools and services at scale. It offers three…
koog
Koog is a JetBrains-backed Kotlin framework for building AI agents that run on the JVM and cross-platform targets (Android, iOS, browser). It provides fault tol…
krita-ai-diffusion
Krita AI Diffusion is a Krita plugin enabling AI-powered inpainting, outpainting, and image generation directly within the editor. Users can refine existing art…
kusion
Kusion is a declarative platform orchestrator written in Go that helps platform engineers and app developers collaborate by abstracting infrastructure complexit…
LangBot
LangBot is an open-source Python platform for rapidly building and deploying AI-powered instant messaging bots across Discord, Slack, Telegram, WeChat, and 7+ o…
langchain
LangChain is a Python framework for building AI agent applications and LLM-powered systems. It provides standardized interfaces to chain together models, data s…
Langchain-Chatchat
Langchain-Chatchat is an open-source Python application for building local RAG (Retrieval-Augmented Generation) and Agent systems using LLMs like ChatGLM, Qwen,…
langchain_dart
LangChain.dart is an unofficial Dart port of the popular Python LangChain framework, enabling developers to build LLM-powered applications in Dart and Flutter. …
langchain-kr
langchain-kr is a Korean-language tutorial repository covering LangChain fundamentals, practical examples, and integrations with OpenAI, HuggingFace, and local …
langchain4j
LangChain4j is an open-source Java library that simplifies building applications powered by large language models (LLMs). It provides unified APIs to work with …
langextract
LangExtract is a Google-authored Python library that extracts structured information from unstructured documents using LLMs, with precise source grounding (char…
langflow
Langflow is an open-source platform for building and deploying AI workflows and multi-agent systems through a visual interface. It supports major LLMs, vector d…
langgraph
LangGraph is a Python framework for building stateful, long-running AI agents with built-in support for durability, human oversight, and persistent memory. It h…
langgraphjs
LangGraph JS is a TypeScript framework for building stateful agents that can persist through failures, support human oversight, and manage long-term memory. It …
langwatch
LangWatch is an open-core platform for testing, evaluating, and monitoring LLM-powered agents. It provides end-to-end agent simulations, evaluation workflows, o…
LanPaint
LanPaint is a training-free inpainting extension for ComfyUI that works with any Stable Diffusion model. It uses an iterative "think mode" to improve inpainting…
LaVague
LaVague is an open-source Python framework for building AI-powered web agents that can automate multi-step browser tasks. It uses a World Model to interpret obj…
LEANN
LEANN is a Python-based vector database designed for on-device RAG (Retrieval-Augmented Generation) that achieves 97% storage reduction through graph-based reco…
lemonade
Lemonade is a local AI server that runs LLMs and multi-modal models directly on user GPUs and NPUs, offering private inference without cloud dependency. It expo…
letta
Letta is an open-source Python platform for building stateful AI agents with persistent memory that can learn and improve over time. It supports local execution…
LightRAG
LightRAG is a Python-based retrieval-augmented generation (RAG) framework that combines vector retrieval with knowledge graph indexing for faster, more accurate…
Liquid
Liquid is an open-source multimodal AI model that handles text, image understanding, and image generation in a single unified architecture. Built on an autoregr…
litgpt
LitGPT is a Python framework providing 20+ pre-built large language models with recipes for pretraining, fine-tuning, and deploying at scale. It emphasizes mini…
llama-cookbook
Llama Cookbook is Meta's official guide for building applications with Llama models, providing Jupyter notebooks and code examples for inference, fine-tuning, a…
llama_index
LlamaIndex is an open-source Python framework for building applications that augment large language models with private data through retrieval-augmented generat…
LlamaFactory
LlamaFactory is an open-source Python framework for fine-tuning 100+ large language models and vision-language models using methods like LoRA, QLoRA, and full-p…
llm-action
llm-action is a Chinese-language educational repository (24.7k stars) covering large language model engineering: training techniques (LoRA, QLoRA, RLHF), infere…
llm-app
Pathway llm-app is an open-source framework for building production-ready RAG (Retrieval-Augmented Generation) and enterprise search applications. It includes D…
llm-apps-java-spring-ai
A collection of sample Spring AI applications demonstrating how to build Java-based generative AI systems using LLMs, embeddings, and RAG patterns. Covers chatb…
llm-beginner
llm-beginner is a structured six-task tutorial for learning LLM fundamentals and agent development, progressing from Transformer basics through mini-GPT impleme…
llm-engineer-toolkit
llm-engineer-toolkit is a curated repository cataloging 120+ open-source libraries for large language model development, organized by function (training, infere…
llm-foundry
LLM Foundry is an open-source training and deployment toolkit for large language models, built and maintained by Databricks (formerly MosaicML). It provides end…
llm-guard
LLM Guard is an open-source Python toolkit that provides input and output scanning for large language models to detect and prevent security issues like prompt i…
llm-ui
llm-ui is a React component library designed to render and format output from large language models. It handles common LLM output challenges like broken markdow…
llmfit
llmfit is a Rust-based terminal tool that detects your hardware and recommends which LLM models will run well on it. It scores models across quality, speed, fit…
LLMUnity
LLMUnity is a C# package that integrates Large Language Models directly into the Unity game engine, enabling developers to create AI-driven NPCs and characters …
llmware
llmware is a Python framework for building enterprise RAG (retrieval-augmented generation) pipelines optimized for small, specialized models running locally or …
LLPhant
LLPhant is a PHP framework that simplifies building generative AI applications with support for multiple LLM providers (OpenAI, Anthropic, Mistral, Ollama, etc.…
LMCache
LMCache is an open-source KV cache management layer for LLM inference that stores and reuses cached key-value data across requests to reduce computation and imp…
lmdeploy
LMDeploy is an open-source toolkit for compressing, deploying, and serving large language models with optimized inference engines. It achieves significant perfo…
lmnr
Laminar is an open-source observability platform designed to monitor and debug AI agents. It provides tracing, performance signals, evaluation tools, and dashbo…
LMOps
LMOps is a Microsoft research initiative providing open-source techniques for building AI products with large language models, covering prompt optimization, lon…
lms
LM Studio CLI is a command-line interface for managing and interacting with LM Studio, a desktop application for running large language models locally. It provi…
LobsterAI
LobsterAI is an open-source desktop AI agent built by NetEase Youdao that automates office workflows—data analysis, document generation, web research, video cre…
LocalAI
LocalAI is an open-source AI engine that runs language models, vision, audio, and image generation tasks locally on any hardware without requiring a GPU. It use…
lollms-webui
LoLLMs WebUI is a Python-based web interface for running and managing multiple large language models and multimodal AI systems locally. It supports various mode…
loop-engineering
Loop Engineering is a JavaScript toolkit and methodology for designing systems that orchestrate AI coding agents (Claude, Grok, Codex) rather than manually prom…
lorax
LoRAX is an Apache 2.0–licensed inference server that serves thousands of fine-tuned LoRA adapters on a single GPU by dynamically loading task-specific weights …
LTX-Desktop
LTX Desktop is an open-source desktop application for generating, editing, and refining videos using LTX generative AI models. It supports local GPU-based gener…
ludwig
Ludwig is a Python-based, declarative deep learning framework that enables training and fine-tuning of LLMs, multimodal models, and tabular AI systems via YAML …
Maestro
Maestro is a TypeScript-based desktop orchestration tool for coordinating multiple AI coding agents (Claude Code, OpenAI Codex, OpenCode, etc.) in parallel. It …
MaiBot
MaiBot is a Python-based LLM agent designed for conversational interaction, emphasizing natural dialogue over task efficiency. It includes plugin extensibility …
marvin
Marvin is a Python framework for building AI workflows with structured outputs and agentic control flow. It provides task-centric abstractions for delegating wo…
mattergen
MatterGen is a Python-based generative model developed by Microsoft for designing inorganic materials across the periodic table. It uses diffusion-based generat…
MaxKB
MaxKB is an open-source Python platform for building enterprise agents with built-in RAG pipelines, workflow orchestration, and MCP tool support. It integrates …
mcp-agent
mcp-agent is a Python framework for building AI agents that connect language models to external tools via the Model Context Protocol. It provides pre-built patt…
mcp-context-forge
ContextForge is an open-source AI gateway and registry (Apache 2.0) that unifies MCP, REST, and gRPC APIs behind a single endpoint with centralized governance, …
mcp-toolbox
MCP Toolbox for Databases is an open-source Model Context Protocol server that bridges AI agents and applications to enterprise databases. It provides prebuilt …
mcp-ui
mcp-ui is a TypeScript/multi-language SDK that implements the Model Context Protocol (MCP) Apps standard to enable interactive web UIs for AI tools. It provides…
md
WeChat Markdown Editor is a browser-based tool that converts Markdown to WeChat-formatted articles. It supports custom themes, AI assistance, multiple image hos…
MedicalGPT
MedicalGPT is a Python framework for training domain-specific large language models in healthcare using a multi-stage pipeline (pretraining, supervised fine-tun…
meetily
Meetily is a self-hosted, open-source AI meeting assistant built in Rust that runs entirely on your local machine. It captures, transcribes, and summarizes meet…
mellea
Mellea is a Python library that converts typed Python functions into structured LLM calls, replacing brittle prompts with type-safe, testable generative workflo…
mem0
Mem0 is a Python/JavaScript memory layer for AI agents and assistants that stores and retrieves user context across conversations. It uses multi-signal retrieva…
MemOS
MemOS is a memory operating system for LLMs and AI agents that provides persistent, multi-modal memory storage with hybrid retrieval, token savings (35.24%), an…
mempalace
MemPalace is a local-first AI memory system that stores conversation history verbatim and retrieves it using semantic search, achieving 96.6% recall without API…
memvid
Memvid is a serverless, single-file memory system for AI agents that replaces complex RAG pipelines with embedded vector search, full-text indexing, and tempora…
mergekit
mergekit is a Python toolkit for combining multiple pre-trained language models (like Llama and Mistral) into a single model without retraining. It uses memory-…
metaflow
Metaflow is an ML workflow framework from Netflix that helps data scientists and engineers move projects from local notebooks to production at scale. It provide…
MetaGPT
MetaGPT is an open-source multi-agent framework that assigns LLM roles (product managers, architects, engineers) to collaboratively generate software from natur…
MindSearch
MindSearch is an open-source LLM-based multi-agent web search framework that mimics human search behavior, similar to Perplexity.ai Pro. It orchestrates paralle…
MiniOneRec
MiniOneRec is an open-source framework for building generative recommendation systems using large language models. It combines semantic item tokenization (SID),…
mission-control
Mission Control is a self-hosted dashboard for managing AI agent fleets, dispatching tasks, and tracking costs across multi-agent workflows. It runs on SQLite w…
ml-engineering
An actively maintained open-source knowledge repository documenting practical methodologies, tools, and runnable scripts for training and operating large langua…
mlc-llm
MLC LLM is an open-source deployment engine that compiles and runs large language models across diverse platforms—from GPUs (NVIDIA, AMD, Apple, Intel) to brows…
mlflow
MLflow is a comprehensive open-source platform for managing the full lifecycle of AI and ML projects, from experiment tracking to production deployment. It prov…
mlx-vlm
MLX-VLM is a Python package for running and fine-tuning vision-language models (VLMs) locally on Apple Silicon Macs using the MLX framework. It supports inferen…
MNN
MNN is a lightweight, high-performance inference engine developed by Alibaba for deploying deep learning models on mobile devices, embedded systems, and edge ha…
mockserver-monorepo
MockServer is a Java-based HTTP(S) mock server and traffic proxy for development and testing. It auto-detects and handles HTTP/1.1, HTTP/2, gRPC, WebSockets, TC…
Mooncake
Mooncake is an open-source LLM serving platform designed for efficient distributed inference through a KVCache-centric disaggregated architecture. It enables mu…
morphic
Morphic is an open-source AI-powered search engine that combines traditional web search with generative AI to produce cited, streaming answers with rich UI comp…
mostlyai
MostlyAI is a Python SDK for generating high-fidelity synthetic tabular and language data locally or via remote endpoints. It offers differential privacy, quali…
ms-swift
ms-swift is an open-source fine-tuning and deployment framework for 600+ large language models and 300+ multimodal models. It provides training (pre-training, S…
Multi-Agent-Medical-Assistant
Multi-Agent Medical Assistant is an open-source Python chatbot that combines large language models, computer vision, retrieval-augmented generation (RAG), and w…
nano-vllm
Nano-vLLM is a lightweight Python implementation of an LLM inference engine built from scratch in ~1,200 lines of code. It offers performance comparable to vLLM…
nanobot
Nanobot is a lightweight, MIT-licensed open-source AI agent framework written in Python that lets you build personal AI assistants with web UI, multi-channel ch…
NarratoAI
NarratoAI is a Python-based open-source tool for automating video narration and editing using LLMs. It generates scripts, adds voiceovers, creates subtitles, an…
nexent
Nexent is a zero-code platform for building production-grade AI agents using natural language prompts. It provides unified tooling for skills, memory, orchestra…
note-gen
NoteGen is an open-source, cross-platform Markdown note-taking app that lets you quickly capture raw information (text, voice, screenshots, files) and then use …
oh-my-pi
oh-my-pi is an open-source AI coding agent for the terminal that integrates with IDEs and supports 40+ LLM providers. It offers features like hash-anchored edit…
ollama
Ollama is an open-source application that lets you run large language models locally on your machine without relying on cloud APIs. It supports models like Llam…
omlx
oMLX is a macOS-native LLM inference server optimized for Apple Silicon, featuring continuous batching and a two-tier KV cache (RAM + SSD) to manage context eff…
omnigent
Omnigent is an open-source Python meta-harness that provides a unified orchestration layer for multiple AI agent frameworks (Claude Code, Codex, Cursor, Pi, cus…
OmniLottie
OmniLottie is a multimodal generative model that creates Lottie vector animations (JSON format) from text, images, or video inputs. It combines Vision-Language …
opcode
opcode is a desktop GUI application built with Tauri that manages Claude Code sessions, custom AI agents, and usage analytics. It provides a visual interface fo…
open-design
Open Design is an open-source desktop application that combines AI-powered design generation with local-first execution. It supports multiple coding agents (Cla…
Open-Generative-AI
Open-Generative-AI is a free, self-hosted web studio for generating AI images and videos using 200+ models (Flux, Midjourney, Kling, Sora, Veo) without content …
open-llms
open-llms is a curated list of large language models licensed for commercial use, including Apache 2.0, MIT, and OpenRAIL-M models. It catalogs model parameters…
open-multi-agent
Open Multi-Agent is a TypeScript framework that automatically breaks down high-level goals into parallel task workflows (DAGs) and executes them across Claude, …
open-swe
Open SWE is an open-source framework for building internal coding agents that automate software tasks like writing code, running tests, and opening PRs. It runs…
openagent
OpenAgent is an open-source self-hosted AI assistant platform built in Go that combines large language models, retrieval-augmented generation (RAG), and autonom…
openagi
OpenAGI is an open-source Python framework for building autonomous multi-agent systems that can decompose tasks, coordinate worker agents, and execute actions v…
openai-agents-python
OpenAI Agents SDK is a Python framework for building multi-agent workflows that delegate tasks between LLM-powered agents. It supports 100+ LLMs, includes sandb…
opencompass
OpenCompass is an open-source LLM evaluation platform supporting 100+ datasets and a wide range of models (Llama, Mistral, GPT-4, Claude, Qwen, etc.). It provid…
OpenEMMA
OpenEMMA is an open-source Python implementation of Waymo's end-to-end autonomous driving model that uses vision language models (VLMs) and camera inputs to pre…
openfang
OpenFang is an open-source Agent Operating System written in Rust that runs autonomous agents on schedules without requiring user prompts. It compiles to a sing…
openlit
OpenLIT is an open-source observability platform for AI/LLM applications, providing OpenTelemetry-native monitoring, GPU tracking, prompt management, and evalua…
OpenLLM
OpenLLM is a Python framework that lets you run open-source language models (Llama, Qwen, Mistral, etc.) as OpenAI-compatible API endpoints locally or in the cl…
openmed
OpenMed is a Python-based healthcare AI framework for clinical named-entity recognition (NER) and PII de-identification that runs entirely on-device without clo…
OpenMemory
OpenMemory is a self-hosted cognitive memory engine for LLM applications that stores and recalls user context across conversations using multi-sector memory (ep…
opensquilla
OpenSquilla is a token-efficient Python AI agent framework that routes queries to the cheapest capable model while maintaining persistent memory, web search, an…
openui
OpenUI is a TypeScript framework for building generative UIs by streaming structured output from LLMs. It combines a compact language (OpenUI Lang), React/Vue/S…
openvino
OpenVINO is an open-source toolkit for optimizing and deploying AI inference across edge and cloud devices. It supports models from PyTorch, TensorFlow, ONNX, a…
opik
Opik is an open-source observability and evaluation platform for LLM applications, RAG systems, and agentic workflows. It provides tracing, automated evaluation…
Orpheus-TTS
Orpheus TTS is an open-source speech synthesis system built on Llama-3b that generates natural-sounding speech with zero-shot voice cloning and emotion control.…
osmedeus
Osmedeus is a Go-based orchestration engine for security testing that automates complex reconnaissance and vulnerability scanning workflows through declarative …
Overture
Overture is an open-source MCP server that visualizes AI coding agent execution plans as interactive flowcharts before code generation begins. It runs locally a…
PaddleNLP
PaddleNLP is a Python-based NLP and LLM library built on the PaddlePaddle framework, offering tools for training, compression, and inference of language models …
paddler
Paddler is an open-source LLM/VLM load balancer and serving platform built in Rust for self-hosted inference at scale. It uses llama.cpp as its inference engine…
PageIndex
PageIndex is a reasoning-based document retrieval system that organizes PDFs into hierarchical tree structures and uses LLM reasoning instead of vector similari…
PandaWiki
PandaWiki is an open-source AI-driven knowledge base system that helps teams quickly build product docs, technical docs, FAQs, and blogs with AI-assisted creati…
parlant
Parlant is a Python framework for building customer-facing AI agents with strict behavioral control through context engineering. It dynamically filters instruct…
peft
PEFT is a Python library from Hugging Face that enables efficient fine-tuning of large language models and diffusion models by updating only a small fraction of…
PentestGPT
PentestGPT is an open-source Python framework that automates penetration testing using large language models. It can autonomously identify vulnerabilities, run …
pezzo
Pezzo is an open-source LLMOps platform built in TypeScript that helps teams manage prompts, monitor LLM operations, and collaborate on AI deployments. It offer…
plandex
Plandex is an open-source, terminal-based AI coding agent that plans and executes large, multi-file coding tasks. It manages context efficiently, maintains a sa…
plano
Plano is an AI-native proxy and data plane built in Rust that centralizes agent orchestration, LLM routing, observability, and safety guardrails for agentic app…
poml
POML is a markup language (like HTML for prompts) that helps developers structure and manage prompts for large language models. It includes a VS Code extension,…
ponytail
Ponytail is a JavaScript plugin that guides AI agents toward minimal, necessity-driven code generation by enforcing a seven-rung decision ladder before writing …
potpie
Potpie is a Python-based CLI tool that builds a knowledge graph from your codebase, git history, and connected development tools (GitHub, Linear, Jira, Confluen…
PowerInfer
PowerInfer is a high-speed LLM inference engine for consumer-grade GPUs that uses activation locality (hot/cold neuron separation) to run large language models …
PPTAgent
PPTAgent is an open-source agentic framework for automated PowerPoint generation using LLMs. It supports both template-based and freeform visual design, integra…
presentation-ai
Presentation-AI is an open-source, MIT-licensed Next.js application that generates professional slide decks using AI. It supports multiple text models (OpenAI, …
preswald
Preswald is a Python-based tool that packages interactive data apps into single HTML files that run entirely in the browser using WebAssembly. It bundles Python…
product-manager-prompts
A curated collection of 96 copy-paste AI prompts for product managers, organized by workflow (execution, workshops, market research, storytelling). Designed to …
prompt-master
Prompt Master is a Claude skill that optimizes prompts for any AI tool by extracting intent, asking clarifying questions, and applying tool-specific frameworks …
promptflow
Prompt Flow is a Microsoft-backed Python framework for building, testing, and deploying LLM applications through a visual/code-based flow system. It handles the…
promptfoo
Promptfoo is an open-source CLI and library for testing, evaluating, and security-testing LLM applications. It lets you compare prompt performance across multip…
prompty
Prompty is a markdown-based format and toolkit for writing, managing, and executing LLM prompts across Python, TypeScript, and VS Code. It abstracts away provid…
ps-fuzz
ps-fuzz is an open-source Python tool that tests and hardens generative AI application system prompts against LLM-based attacks such as jailbreaks, prompt injec…
pydantic-ai
Pydantic AI is a Python agent framework built by the Pydantic team that enables rapid development of production-grade LLM applications. It provides type-safe ag…
PyRIT
PyRIT is an open-source Python framework from Microsoft designed to help security teams identify and test risks in generative AI systems. It provides tools and …
pyspur
PySpur is a visual IDE for building and debugging AI agents with drag-and-drop workflow creation, human-in-the-loop approvals, and multi-LLM provider support. I…
QOwnNotes
QOwnNotes is an open-source plain-text note and todo-list manager written in C++ that integrates with Nextcloud and ownCloud for syncing and collaboration. It s…
Qwen
Qwen is Alibaba Cloud's open-source large language model series, available in sizes from 1.8B to 72B parameters, with both base and chat-aligned variants. Model…
rag-time
RAG Time is a Microsoft-authored educational repository containing a 5-week video course series, sample code, and guides on Retrieval-Augmented Generation (RAG)…
RagaAI-Catalyst
RagaAI Catalyst is a Python SDK for monitoring, debugging, and evaluating AI agent systems and LLM applications. It provides tracing, multi-agentic system debug…
ragas
Ragas is a Python framework for evaluating and optimizing Large Language Model applications through objective metrics, automated test generation, and production…
ray
Ray is an open-source distributed computing framework for scaling Python and AI workloads from a laptop to a cluster. It provides core runtime abstractions (tas…
RD-Agent
RD-Agent is a Microsoft open-source Python framework that automates data-driven R&D workflows using AI agents. It targets machine learning engineering tasks, da…
read-frog
Read Frog is an open-source browser extension that uses AI models (OpenAI, DeepSeek, etc.) to provide immersive translation and language learning features direc…
reader
Reader is a free API service that converts any URL into LLM-friendly markdown output, handling web pages, PDFs, and Office documents. It also provides web searc…
REINVENT4
REINVENT4 is an AI-powered Python tool for generating and optimizing small molecules in drug discovery. It uses reinforcement learning and transfer learning to …
remove-ai-watermarks
Remove-AI-Watermarks is a Python CLI and library that strips visible and invisible AI watermarks (SynthID, Gemini sparkle, C2PA metadata) from AI-generated imag…
RemoveWindowsAI
RemoveWindowsAI is a PowerShell script that disables and removes Microsoft's AI features (Copilot, Recall, AI Actions) from Windows 11. It modifies registry key…
repomix
Repomix is a CLI and web tool that packages your entire codebase into a single AI-friendly file (XML, Markdown, or plain text) for feeding to LLMs like Claude o…
rig
Rig is a Rust library for building LLM-powered applications with support for 20+ model providers and 10+ vector stores under a unified interface. It enables age…
rivet
Rivet is an open-source visual IDE and TypeScript library for building complex AI agent workflows and prompt chains. It supports multiple LLM providers (OpenAI,…
rowboat
Rowboat is an open-source desktop AI assistant that builds a persistent knowledge graph from your work (email, meetings, Slack) and provides built-in surfaces—e…
RQ-VAE-Recommender
RQ-VAE-Recommender is a PyTorch implementation of a generative retrieval model for recommendation systems that uses semantic IDs. It tokenizes items into learne…
rtk
RTK is a CLI proxy written in Rust that intercepts and compresses command output before it reaches LLM context windows, reducing token consumption by 60-90% on …
RWKV-Runner
RWKV-Runner is a lightweight TypeScript desktop application (8MB) that automates RWKV model management and provides an OpenAI API-compatible interface. It enabl…
Scrapegraph-ai
ScrapeGraphAI is a Python library that uses large language models (LLMs) to automate web scraping and data extraction from websites and documents. Users define …
seatunnel
Apache SeaTunnel is a distributed data integration platform that moves large volumes of data between diverse sources using batch, real-time, and CDC modes. It s…
self-llm
Self-LLM is a Chinese-language educational repository providing comprehensive tutorials for deploying, fine-tuning, and using 50+ open-source large language mod…
semantic-kernel
Semantic Kernel is a Microsoft-maintained, open-source SDK for building AI agents and multi-agent systems that work with any LLM. It provides tools for orchestr…
semantic-router
vLLM Semantic Router is a Go-based intelligent routing system that directs requests to the optimal AI model in multi-model deployments. It reduces token waste, …
semantica
Semantica is a Python framework that adds accountability and explainability to AI agents by building structured knowledge graphs, decision records, and audit tr…
serve
Jina Serve is a Python framework for building and deploying AI services using gRPC, HTTP, and WebSockets. It provides built-in support for containerization, Kub…
serverless-chat-langchainjs
This is an Azure sample project demonstrating a serverless chatbot using LangChain.js with Retrieval-Augmented Generation (RAG). It combines Azure Functions, St…
sglang
SGLang is an open-source, high-performance serving framework for large language models and multimodal models. It delivers low-latency, high-throughput inference…
shadcn-chatbot-kit
shadcn-chatbot-kit is a TypeScript component library for building customizable AI chatbots using shadcn/ui. It provides pre-built, copy-paste components for cha…
shell_gpt
ShellGPT is a command-line tool that integrates LLMs (OpenAI GPT-4 by default, or open-source models via Ollama) to generate shell commands, code snippets, and …
SillyTavern
SillyTavern is a locally-installed web interface for interacting with multiple LLM APIs (OpenAI, Claude, Mistral, Horde, NovelAI, etc.), image generation engine…
skyvern
Skyvern is an AI-powered browser automation framework that uses LLMs and computer vision to automate web workflows without brittle selectors. It provides both a…
spacy-layout
spacy-layout is a Python plugin that converts PDFs, Word documents, and similar files into structured, analyzable text using spaCy's NLP capabilities. It extrac…
SparkVSR
SparkVSR is a research framework for interactive video super-resolution that lets users control output quality by manually editing sparse keyframes, which the s…
sparrow
Sparrow is an open-source platform for extracting structured data from documents using local machine learning models and vision LLMs. It processes invoices, for…
Speech
NVIDIA NeMo Speech is an Apache-2.0 licensed Python framework for building speech AI models including ASR, TTS, and speech LLMs. It is actively maintained with …
Stable-Diffusion
This is a curated GitHub repository and educational resource hub (not a packaged tool) created by Dr. Furkan Gözükara, containing tutorials, guides, and links f…
star-vector
StarVector is a multimodal vision-language model that converts images and text into Scalable Vector Graphics (SVG) code. It treats vectorization as a code gener…
SuperAGI
SuperAGI is a Python-based open-source framework for building, deploying, and managing autonomous AI agents. It provides a GUI, toolkit marketplace, vector data…
superduper
Superduper is an open-source Python framework that integrates AI models and agents directly into databases. It allows developers to build custom AI applications…
surogate
Surogate is a C++/CUDA-based training framework optimized for high-speed LLM fine-tuning and pre-training using low-precision formats (FP8, FP4) and CPU offload…
SWE-agent
SWE-agent is an LLM-based agent that autonomously fixes GitHub issues, finds security vulnerabilities, or solves coding challenges by controlling tools and file…
synthetic-data-generator
SDG is a Python framework for generating high-quality synthetic tabular data using statistical models (CTGAN, GaussianCopula) and LLM-based approaches. It suppo…
system_prompts_leaks
A GitHub repository documenting extracted system prompts from major AI services (Claude, ChatGPT, Gemini, Grok, and others). Content is released under CC0 (publ…
TaxHacker
TaxHacker is a self-hosted AI accounting app that extracts transaction data from receipts, invoices, and PDFs using LLMs (OpenAI, Gemini, Ollama, etc.). It auto…
text-embeddings-inference
Text Embeddings Inference (TEI) is a Rust-based inference server optimized for deploying text embedding and sequence classification models with high throughput …
Text-To-Video-AI
Text-To-Video-AI is an open-source Python framework that generates videos from text prompts by orchestrating multiple AI services—LLMs for script generation, te…
TF-ICON
TF-ICON is a Python-based research implementation for seamlessly compositing objects from one visual style into images of another style using Stable Diffusion, …
TimeCraft
TimeCraft is a Microsoft Research diffusion-based framework for generating synthetic time series data across diverse domains (energy, finance, healthcare, trans…
tiny-llm
tiny-llm is an open-source educational course that teaches LLM inference optimization and serving on Apple Silicon using Python and MLX. It covers building core…
toon
TOON is a compact, human-readable data format optimized for LLM input that encodes JSON data using CSV-style tables for arrays and YAML-like indentation for obj…
Toonflow-app
Toonflow is an open-source Electron desktop application that automates AI-driven short-form video production from text input (novels, scripts). It orchestrates …
TradingAgents
TradingAgents is an open-source Python framework that uses multiple LLM-powered agents (analysts, researchers, traders, risk managers) to collaboratively evalua…
trae-agent
Trae Agent is an open-source, LLM-powered CLI tool built by ByteDance for automating software engineering tasks through natural language instructions. It suppor…
trafilatura
Trafilatura is a Python tool for discovering, downloading, and extracting text and metadata from web pages. It handles crawling, HTML parsing, and outputs struc…
transformer-explainer
Transformer Explainer is an interactive web-based visualization tool that runs GPT-2 in the browser, allowing users to understand how Transformer models work by…
transformers
Transformers is a comprehensive Python framework for building, training, and deploying state-of-the-art machine learning models across text, vision, audio, and …
TrendRadar
TrendRadar is a Python-based AI-driven trend monitoring system that aggregates news and trending topics from multiple platforms via RSS, applies keyword filteri…
trulens
TruLens is a Python framework for evaluating and tracking LLM applications and AI agents in production. It provides instrumentation, feedback functions, and a U…
TTS-WebUI
TTS-WebUI is a unified web interface built with Gradio and React that aggregates 20+ text-to-speech, audio generation, and audio processing models (Bark, Tortoi…
txtai
txtai is an open-source Python framework that combines vector search, LLM integration, and workflow orchestration into a single tool. It enables developers to b…
TypeChat
TypeChat is a Microsoft library for building natural language interfaces by replacing prompt engineering with schema engineering. You define types representing …
UFO
UFO is a Python-based desktop automation framework by Microsoft that evolved into UFO³, supporting both single-device Windows automation (UFO²) and multi-device…
UltraRAG
UltraRAG is a Python-based framework for building retrieval-augmented generation (RAG) pipelines using a low-code YAML configuration approach. It standardizes R…
ultravox
Ultravox is an open-source multimodal LLM that processes audio and text directly without requiring a separate speech-recognition step, enabling faster real-time…
unilm
UniLM is a Microsoft research repository containing large-scale pre-trained foundation models spanning language, vision, speech, and multimodal tasks across 100…
unity-mcp
Unity MCP is an MIT-licensed bridge that connects AI assistants (Claude, ChatGPT, Cursor, etc.) to the Unity Editor via the Model Context Protocol. It exposes 4…
UnrealGenAISupport
UnrealGenAISupport is a free MIT-licensed Unreal Engine 5 plugin that integrates 200+ LLM and generative AI models (OpenAI, Claude, Gemini, DeepSeek, etc.) into…
unsloth
Unsloth Studio is a web UI and Python library for training and running open-source language models locally on consumer hardware. It supports inference, fine-tun…
unstructured
Unstructured is an open-source ETL library that converts complex documents (PDFs, Word, HTML, images) into structured data suitable for LLM pipelines. It provid…
Vane
Vane is a privacy-focused AI answering engine that runs locally on your own hardware, combining web search with support for local and cloud LLMs (Ollama, OpenAI…
VAR
VAR is an open-source visual generation model that uses autoregressive "next-scale prediction" instead of diffusion. It generates images by predicting progressi…
Vibe-Trading
Vibe-Trading is a Python-based AI agent framework for algorithmic trading that combines LLM capabilities with multi-agent orchestration, backtesting, and quanti…
ViewComfy
ViewComfy is an open-source TypeScript tool that converts ComfyUI workflows into deployable web applications with drag-and-drop form configuration. It supports …
vllm
vLLM is an open-source Python library for running and serving large language models efficiently. It handles inference workloads with optimized memory management…
vllm-ascend
vLLM Ascend is a community-maintained plugin that enables running large language models on Huawei's Ascend NPU hardware using the vLLM inference framework. It s…
voltagent
VoltAgent is a TypeScript-based platform for building AI agents with tools, memory, and workflows. The open-source framework lets teams create multi-agent syste…
openui
OpenUI is an open-source tool that generates UI components from natural language descriptions, with live rendering and the ability to convert output to React, S…
web-llm
WebLLM is a TypeScript-based engine that runs large language models directly in web browsers using WebGPU acceleration, with no server required. It provides Ope…
web-llm-chat
WebLLM Chat is a browser-based AI chat application that runs large language models natively using WebGPU, eliminating server dependencies and keeping all data l…
WebAI2API
WebAI2API converts web-based AI services (LMArena, Gemini, ChatGPT, DeepSeek, etc.) into OpenAI-compatible API endpoints. It uses browser automation via Camoufo…
WeClone
WeClone is a Python-based tool that fine-tunes open-source LLMs (like Qwen) using your chat history to create a digital avatar that mimics your communication st…
whichllm
whichllm is a CLI tool that automatically detects your hardware and recommends the best local LLM to run on it, ranked by real benchmark scores rather than just…
WilmerAI
WilmerAI is a Python-based semantic prompt router and workflow engine that sits between applications and multiple LLM APIs, enabling context-aware routing and c…
WorldGen
WorldGen is a Python library that generates 3D scenes from text prompts or images in seconds, supporting both Gaussian splatting and mesh output formats. It ena…
WorldSeed
WorldSeed is a Python-based multi-agent simulation engine where AI agents interact within a declaratively defined world, producing emergent behaviors. It enable…
WorldX
WorldX is a TypeScript-based open-source framework for generating AI-driven virtual worlds from a single text prompt. It combines procedural map/character gener…
XianyuAutoAgent
XianyuAutoAgent is a Python-based AI customer service automation system built for Alibaba's Xianyu (闲鱼) marketplace platform. It provides 24/7 automated custome…
xtuner
XTuner is an open-source training framework optimized for fine-tuning and pre-training ultra-large mixture-of-experts (MoE) models, with support for multimodal …
xTuring
xTuring is a Python library for fine-tuning and running open-source language models locally or in private environments. It simplifies the process of preparing d…
xyne
Xyne is an open-source AI search and answer engine that connects to your work apps (Google Workspace, Slack, Atlassian) to securely index and search across frag…
YTPro
YTPro is a YouTube client built in JavaScript for Android that adds features like background playback, video downloading, ad blocking, and Google Gemini integra…
zenml
ZenML is an open-source MLOps platform that orchestrates ML pipelines and AI agents across different infrastructure backends. It provides workflow orchestration…
zep
Zep is an Apache-2.0 licensed repository containing examples, integrations, and tools for building agent memory with Zep Cloud, a managed platform for temporal …
A software development agency for open-source projects
DEV.co is a software development agency offering custom software development services and web development for companies adopting open-source ai frameworks. Our software developers and web developers evaluate, implement, integrate, customize, and maintain open-source software in production — so your team ships faster with less risk.
Building with open-source ai frameworks?
DEV.co helps companies evaluate, customize, integrate, and deploy open-source software with senior software developers.