langchain-aiDeveloper tools
openwiki
A CLI that uses agents to generate and continuously maintain Markdown wikis for codebases or personal knowledge, with a local graph visualizer.
- Backend
- Full stack
- Data
- Content creation
- Code quality
- Productivity
- CLI
- Web
- Windows
- macOS
- Linux
- Browser
- Runs locally

- Popularity
- 16.9k Stars
- GitHub stars
- Recent activity
- 10/1/2026
- Updated in the last 30 days
- License
- MIT
- Permissive
Why it matters
We look beyond stars: what problem it solves, whether it creates real utility, and what makes its approach worth noticing.
Problem
Addresses the common pain point where codebase and personal knowledge bases lack automatically maintained documentation, leading to stale docs.
Practical value
Offers a practical CLI, multi-model support, CI/CD auto-updates, and a local graph visualizer, making it highly useful for development and knowledge management.
Innovation / differentiation
Combines LLM agents with open knowledge format outputs, multi-source connectors, and interactive graphs, providing solid differentiation.
Leverage potential
Integrates directly into workflows via CI tools like GitHub Actions, maintaining up-to-date documentation with minimal manual intervention.
Why now
Arrives as the AI agent toolchain matures rapidly, coinciding with growing developer demand for automated project memory maintenance.
Community activity
In the last 90 days there were 243 new issues and 641 pull requests; the bounded issue/PR samples include 74 issue authors and 64 PR contributors, with 26 releases.
Maintainer responsiveness
The 91-issue window sample had a 81% close rate, and the 89-pull-request sample had a 30% merge rate. Maintainer-response observations covered 45% of that issue sample, with a 0% response rate and median first response of not enough data.
Key highlights
- Generate and update version-controlled Markdown wikis for codebases
- Provide separate code-wiki and personal-knowledge modes
- Connect sources including local Git, Notion, Gmail, and web search
Quick start
How it is installed, how hard it is, and where to start.
Where it runs
Runs locally
Difficulty
Medium — some setup needed
- 01Install
openwikiglobally with npm or pnpm, then runopenwiki --initinside a repository. - 02Choose a model access method on first run and configure code-mode or personal-mode data sources and credentials as needed.
- 03Review the generated Markdown under
openwiki/, browse it withopenwiki visualize, and add the documented CI update job when continuous maintenance is needed.
Best for
- Developers who want to try it on their machine
More about it
OpenWiki lets a documentation agent read a repository or configured knowledge sources and write a user-owned Markdown wiki that it can maintain on later runs. Code mode turns repository structure, runtime flows, and Mermaid diagrams into version-controlled documentation, while personal mode can ingest sources such as local Git repositories, Notion, Gmail, and web search. A loopback-only visualizer provides graph-based browsing. Generation requires access to a supported model, but the project does not require a single provider or API-key-only authentication path.
Sources
Each field shows its status and source — expand to review.
14 · Expand
Sources
Each field shows its status and source — expand to review.
capability tags
Verifiedcontent_creation, code_quality, productivity
Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026
editor note
Verified{"en":"A good fit when you want agent-generated documentation to remain ordinary Markdown instead of living in a proprietary knowledge store. Generated pages still deserve code-review-style spot checks, and connectors such as Gmail or Notion should use least-privilege credentials.","zh":"适合把“Agent 生成文档”落到普通 Markdown 文件,而不是锁在专有知识库里。要注意生成结果仍需代码评审式抽查,连接 Gmail/Notion 等来源时也要按最小权限配置凭据。"}
Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026
how to use
Verified{"steps":[{"en":"Install `openwiki` globally with npm or pnpm, then run `openwiki --init` inside a repository.","zh":"使用 npm 或 pnpm 全局安装 `openwiki`,在代码库中运行 `openwiki --init`。"},{"en":"Choose a model access method on first run and configure code-mode or personal-mode data sources and credentials as needed.","zh":"首次运行选择模型访问方式,并根据需要配置代码模式或个人模式的数据源与凭据。"},{"en":"Review the generated Markdown under `openwiki/`, browse it with `openwiki visualize`, and add the documented CI update job when continuous maintenance is needed.","zh":"生成后检查 `openwiki/` 中的 Markdown,再用 `openwiki visualize` 在本地关系图中浏览;需要持续维护时接入 CI 更新任务。"}],"installAt":"local","difficulty":"medium"}
Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026
intro
Verified{"en":"OpenWiki lets a documentation agent read a repository or configured knowledge sources and write a user-owned Markdown wiki that it can maintain on later runs. Code mode turns repository structure, runtime flows, and Mermaid diagrams into version-controlled documentation, while personal mode can ingest sources such as local Git repositories, Notion, Gmail, and web search. A loopback-only visualizer provides graph-based browsing. Generation requires access to a supported model, but the project does not require a single provider or API-key-only authentication path.","zh":"OpenWiki 会让文档 Agent 读取代码库或配置的数据源,把结果写成用户自己持有的 Markdown Wiki,并在后续更新时继续维护。代码模式适合把仓库结构、运行流程和 Mermaid 图沉淀为可版本控制的文档;个人模式则能接入本地 Git、Notion、Gmail、Web Search 等来源。它还带有仅绑定 127.0.0.1 的可视化服务,用关系图浏览 Wiki。生成内容需要可用的模型访问方式,但不强制只能使用单一模型厂商或 API Key。"}
Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026
Latest release
Verifiedv0.6.1
Source: GitHub API · latest_release=v0.6.1 · 10/1/2026
License
VerifiedMIT
Source: GitHub API · license.spdx_id=MIT · 10/1/2026
needs api key
VerifiedNo
Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026
One-liner
Verified{"en":"A CLI that uses agents to generate and continuously maintain Markdown wikis for codebases or personal knowledge, with a local graph visualizer.","zh":"用 Agent 为代码库或个人资料生成并持续更新 Markdown Wiki 的 CLI,并提供本地关系图可视化。"}
Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026
Platforms
Verifiedwindows, macos, linux, browser
Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026
Category hint
Inferred from materialsai-apps
Source: Project README · hint=ai-apps · 8/13/2026
product forms
Verifiedcli, web
Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026
role tags
Verifiedbackend, fullstack, data
Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026
supports local
VerifiedYes
Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026
supports self host
VerifiedNo
Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026
Related projects
Other verified projects matched by category, capabilities, and intended roles.
spec-kit
An open-source CLI toolkit for Spec-Driven Development that guides AI coding agents through structured specification, planning, and code generation steps.
Flare
A graph-first IDE for agentic coding featuring a live codebase map, integrated terminal, and MCP task collaboration.
mcp-dashboards
An MCP server that renders interactive charts, dashboards, and KPI widgets directly inside AI chat clients.
claude-code
An agentic coding tool for the terminal that understands codebases, handles routine development tasks, explains code, and works with Git workflows.
codex
OpenAI’s coding agent that runs locally, with terminal, IDE, and desktop-app entry points.
CLI-Anything
A toolkit for generating and managing agent-callable CLIs for existing software, with CLI-Hub, generation workflows, and skill/plugin integrations.
