#4242nd of 52 in Agent platforms
inkos
AI agent for writing novels, short stories, scripts and interactive fiction
- Stars
- 11k
- License
- AGPL-3.0
- Last commit
- Oct 2026
- Last release
- Aug 2026
- Language
- TypeScript
3,859 on 10 Apr 202610,954 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
InkOS is a Node.js CLI, TUI and local web Studio that drives LLMs through planning, writing, auditing and revising chapters of novels, short stories, scripts and branching interactive worlds. It keeps per-book state (characters, foreshadowing hooks, summaries) as schema-validated JSON with a SQLite FTS5 index, and commits chapter text and state atomically. Models connect through OpenAI Chat, OpenAI Responses or Anthropic Messages endpoints.
Who it is for: Fiction and web-novel writers who want LLM-assisted long-form drafting
Strengths
- Per-book state validated with Zod; chapter text and state are committed atomically
- Models can be routed per agent role, such as writer and auditor
- Same harness behind Studio, TUI, CLI and a JSON interact mode for external agents
- Standard SKILL.md skills; 19 built in, overridable by a project skill with the same ID
Weaknesses
- README is mainly in Chinese; English writing is enabled with --lang en
- Needs an external LLM API or a local endpoint such as Ollama or LM Studio
- AGPL-3.0 license restricts use in closed network services
- README describes the 2.0 branch as a development version verified with local builds
What it needs
- no GPU
- Needs Node.js 22.16+, LLM API provider (OpenAI-compatible or Anthropic)
- Models: OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, Gemini, Moonshot
Quick answers
Is inkos open source?
Yes. Its code is on GitHub under the AGPL-3.0 license.
Does inkos need a GPU?
No, it runs without one.
Also in Agent platforms
See all 52| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 94 out of 100 |
| 2 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 93 out of 100 |
| 3 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 93 out of 100 |
| #4 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |
| #5 | open-designDesign workspace that drives your coding agent to build prototypes, decks and video | 92 out of 100 |