DEV.co
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.

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.

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.

Work with a software development agency

Need help beyond evaluating inkos? DEV.co is a software development agency offering software development services and web development for teams of every size. Our software developers and web developers build custom software, web applications, APIs, and ai frameworks integrations — and maintain them long-term.

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.