Client loginBook a call
Build
Custom Software DevelopmentSystems built to your process
Web Application DevelopmentReact, Next.js, Rails, Django
Mobile App DevelopmentiOS, Android, React Native
App DevelopmentWeb and mobile apps, end to end
SaaS Product DevelopmentMulti-tenant from day one
MVP DevelopmentFirst release in 6–10 weeks
Enterprise SoftwareSSO, audit trails, scale
Connect & operate
API Development & IntegrationREST, GraphQL, webhooks
Cloud & DevOps EngineeringAWS, GCP, Azure, Terraform
QA & Software TestingAutomated suites, load, E2E
Legacy ModernizationStrangler-fig migrations
Cybersecurity EngineeringHardening and remediation
Data EngineeringPipelines, warehouses, reporting
Design & teams
UI/UX DesignInterfaces people finish tasks in
Prototyping & DiscoveryScope before you spend
Staff AugmentationSenior engineers on your team
Dedicated Dev TeamsA full pod, one contract
White-Label DevelopmentEngineering under your brand
Technology ArchitectureDecide once, correctly
Project ManagementDelivery you can audit
Start hereScope a build in one callBring a spec, a wireframe, or a paragraph. You leave with an architecture, a timeline, and a number.Book a scoping call
All software development services →How we price work →Talk to an engineer →
AI software
AI Application DevelopmentFull-stack AI products
AI Agent DevelopmentMulti-step autonomous agents
AI SaaS DevelopmentMulti-tenant AI products
Workflow AutomationReplace manual ops
Custom LLM AppsBranded internal assistants
LLM & data systems
Private LLM DevelopmentSelf-hosted Llama, Mistral, Qwen
RAG DevelopmentCited answers over your docs
MCP & WebMCPMake your systems agent-callable
Vector Database Setuppgvector, Pinecone, Qdrant
Document IntelligenceOCR and extraction pipelines
Vibe coding
AI-Assisted BuildsFast, with senior review
Rapid PrototypingClickable in days
Concept to CodeIdea to working software
Code Review & CleanupMake AI output shippable
Fractional AI TeamOngoing build capacity
Ready to ship?Put AI where the work isAgents, RAG, and private LLMs wired into the systems your team already uses — not a chatbot bolted to a homepage.Discuss an AI project
AI development services →AI readiness checklist →AI vs. traditional development →
Domain firstWe learn your workflow before we model itRegulated, operational, or high-volume — the constraints belong in the schema, not in a training doc.Talk about your domain
Selected workSoftware we own and operateMost agencies show screenshots. We run the products — the same stack, uptime, and on-call we hand to clients.View the portfolio
Plan smarterEstimate before you commitCost ranges, scope templates, and the questions we ask in discovery — free, no form.Open the cost calculator
Real conversationsTalk with a technical leadNo SDR, no discovery gauntlet. The person on the call is the one who scopes the build.Book a call
AI Frameworks · Narcooo

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 interfaces with persistent state management, character/world tracking, and multi-model support.

Talk to DEV.coDiscuss Implementation
Source: GitHub — github.com/Narcooo/inkos
7.8k
GitHub stars
1.5k
Forks
TypeScript
Primary language
AGPL-3.0
License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

FieldValue
RepositoryNarcooo/inkos
OwnerNarcooo
Primary languageTypeScript
LicenseAGPL-3.0 — OSI-approved
Stars7.8k
Forks1.5k
Open issues195
Latest releasev1.6.3 (2026-07-07)
Last updated2026-07-07
Sourcehttps://github.com/Narcooo/inkos

What inkos is

TypeScript agent framework with LLM integration (OpenAI, Anthropic, Gemini, Moonshot, etc.), SQLite memory, Markdown state projections, skill pluggability, and semantic compression for long-context handling. Exposes interact/compose/revise primitives and skill-based prompt packing.

Quickstart

Get the inkos source

Clone the repository and explore it locally.

terminalbash
git clone https://github.com/Narcooo/inkos.gitcd inkos# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

Long-form novel generation with persistent world state

Maintains character, plot, and world consistency across chapters via SQLite memory and Markdown projections; supports chapter planning, composition, review, and revision workflows.

Interactive fiction and branching narrative games

Dedicated Play mode with open-world contracts, variable/flag systems, relationship tracking, choice trees, and auto-generated images. Tracks world state and non-linear time progression.

Multi-format content production (shorts, scripts, covers, interactive drama)

Single workbench for short stories, play scripts, interactive games, and cover generation; reuses memory, skills, and context infrastructure across formats.

Implementation considerations

  • AGPL-3.0 license: any modifications, forks, or network-exposed deployments likely require source release and recipient licensing under AGPL. Consult legal before using in SaaS or commercial products.
  • Requires LLM provider setup (OpenAI, Anthropic, Google, Moonshot, etc.) and valid API keys; no built-in model included. Infrastructure costs and token usage dependent on workload size and chosen model.
  • Project is ~4 months old with 195 open issues and rapid iteration. Bug fixes and breaking changes may occur in minor releases; production readiness and long-term stability not formally guaranteed.
  • Studio web UI, TUI, and CLI all available but maturity/UX polish not detailed. CLI and programmatic API stability beyond documented examples unknown.
  • SQLite-backed state persists locally to `.inkos/` directory; no built-in cloud sync, multi-device access, or backup strategy documented. Manual migration/backup required for safety.

When to avoid it — and what to weigh

  • Permissive commercial SaaS licensing required — AGPL-3.0 requires derivative works and networked modifications to release source and license recipients under AGPL. Using in a commercial service (SaaS, hosted) requires careful legal review or relicensing.
  • Minimal downstream customization or proprietary enhancements — AGPL copyleft obligations extend to modifications and network-accessed services. Fork-and-enhance models may trigger source-release requirements unless you run entirely behind your own walls (non-networked).
  • Mature, battle-tested production systems with guaranteed support — Project is ~4 months old (created 2026-03, latest release 2026-07) with rapid iteration (195 open issues). Production stability, SLA, and vendor support are unknown; 7,800 stars suggest adoption but not enterprise-grade maturity signals.
  • Language/locale independence — README, docs, and UI are primarily Chinese with English fallback. Configuration, examples, and community discussion likely centered on Chinese novel/IP writing conventions; English support is described as 'now supported' but may lag in feature completeness.

License & commercial use

AGPL-3.0 (GNU Affero General Public License v3.0). Copyleft license requiring source disclosure and recipient AGPL licensing for modifications and network-accessed derivatives. Non-network, private internal use may have more permissive interpretation, but SaaS, hosting, API services, and commercial deployment require careful legal review.

Commercial use is not clearly permitted under AGPL-3.0 without compliance obligations. Running as-is for internal story creation on isolated infrastructure may be acceptable, but offering services (SaaS, APIs, hosted platform) or building proprietary derivatives almost certainly triggers source-release requirements. Relicensing, proprietary fork with legal review, or negotiated commercial agreement recommended before commercial deployment. Consult legal counsel before committing to commercial product plans.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

SignalAssessment
MaintenanceActive
DocumentationAdequate
License clarityNeeds review
Deployment complexityLow
DEV.co fitPossible
Assessment confidenceMedium
Security considerations

User-provided API keys stored in project-local `.inkos/secrets.json` (unencrypted, presumably). LLM requests made directly to external providers; network isolation and data residency not addressed. No audit logging, encryption at rest, or secrets management integration documented. Skill system loads Markdown files locally; no signature/provenance verification described. Studio runs locally by default but network exposure/auth model unclear if deployed remotely. Threat model for story content leakage to LLM providers not discussed.

Alternatives to consider

Anthropic Claude (Claude API, model fine-tuning)

Closed-source commercial offering with permissive terms for many use cases, native long-context handling, and managed infrastructure. Lacks the specialized story/world-state management and multi-format support of InkOS, but simpler licensing and support model.

OpenAI GPT API + custom orchestration layer

Flexible LLM backbone with commercial licensing and enterprise support. Requires building own story state, memory, skill system, and UI; more engineering effort but full control over architecture and licensing.

Open-source narrative/game engines (Twine, Ink, Unity Netcode, etc.)

Specialized tools for interactive fiction, branching narratives, and game development with mature ecosystems. Lack native LLM agents but avoid licensing constraints; suitable if LLM integration is optional or custom.

Software development agency

Build on inkos with DEV.co software developers

Review AGPL-3.0 licensing, test with your LLM provider, and run `npm i -g @actalk/inkos` to start. Consult legal before commercial deployment.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

BrowserOSEverOSWorldX

Related on DEV.co

Explore the category and the services that help you build with it.

AI FrameworksAI Development ServicesAI development and LLM integrationContent and creative toolsCustom software engineeringTalk to DEV.co

inkos FAQ

Can I use InkOS in a commercial product or SaaS?
AGPL-3.0 requires careful review. If you offer services to end users, modifications or network exposure likely triggers source-release and AGPL licensing to recipients. Consult legal counsel; relicensing or commercial agreement may be necessary.
What LLM providers are supported?
OpenAI, Anthropic, Google Gemini, Moonshot (Kimi), MiniMax, 智谱, ByteDance 百炼, and OpenAI-compatible custom endpoints. Multi-model routing available. No bundled model; external API key required.
Is the web UI (Studio) production-ready?
Studio is available and actively developed, but project is ~4 months old with 195 open issues. Stability, performance, and feature completeness not formally guaranteed. Treat as beta for high-stakes production.
How is story state persisted?
SQLite database in `.inkos/` directory (local project folder). No cloud sync or multi-device sync built-in. Backups and migrations are manual. Suitable for local/desktop use; cloud deployment requires additional infrastructure.

Custom software development, end to end

DEV.co has shipped ai frameworks software across regulated and high-growth industries. Our software development services and AI development services cover the work that follows a decision to adopt inkos.

Ready to integrate InkOS?

Review AGPL-3.0 licensing, test with your LLM provider, and run `npm i -g @actalk/inkos` to start. Consult legal before commercial deployment.

Talk to DEV.coSchedule a Consultation