@yibie: LangChain open-sourced OpenWiki—a CLI built for agents that automatically writes and maintains docs for your codebase. Not for you to write docs by hand, but for agents to write, maintain, and reference. OpenWiki: LangChain open…
Summary
LangChain has open-sourced OpenWiki, a CLI tool designed for AI agents that automatically generates and continuously maintains documentation for codebases, supporting multiple models and continuous integration.
View Cached Full Text
Cached at: 07/02/26, 12:22 PM
LangChain open-sourced OpenWiki—a CLI specifically for agents, which automatically writes and maintains documentation for your codebase. It’s not about writing docs manually; it’s about agents writing, agents maintaining, and agents referencing.
OpenWiki: LangChain’s open-source self-maintaining documentation system for agents
LangChain released a new project yesterday, with 477 stars and MIT license. OpenWiki is a CLI designed specifically for agents—it automatically generates and continuously updates documentation for your codebase.
Install: npm install -g openwiki
How to use: openwiki --init to configure model and API key → openwiki generates documentation into the openwiki/ directory → then automatically appends prompts to AGENTS.md / CLAUDE.md to instruct the coding agent to reference this wiki.
Key design: • Supports GLM 5.2, Kimi K2.6, Sonnet 5, etc., with a default list of pre-configured models • Supports OpenRouter, Fireworks, Baseten, OpenAI, Anthropic • GitHub Action integration—automatically opens a PR every day to update documentation • Incremental updates if the documentation directory exists; creates from scratch if it doesn’t.
It echoes all the themes we translated today: • Karpathy’s LLM Knowledge Base (same concept, but now as an automated tool) • EXM7777’s Agent OS principle “keep memory in files” • Memory Update Loop from the 20 Loop patterns
This tool advances the concept of “letting AI remember your codebase” to a single npm install step. LangChain says it is built specifically for agents—not a wiki for humans. 477 stars show that this is exactly a pain point.
Original article: https://github.com/langchain-ai/openwiki…
#OpenWiki #LangChain #AgentDocumentation
langchain-ai/openwiki
Source: https://github.com/langchain-ai/openwiki
OpenWiki
OpenWiki is a CLI that writes and maintains documentation for your codebase, built specifically for agents.
OpenWiki
Install
npm install -g openwiki
Quick Start
Initialize OpenWiki, configure your model and API key, then generate documentation
openwiki --init
Then to ensure your documentation stays up-to-date, add the GitHub action to your repository to automatically open a PR once a day with documentation updates: openwiki-update.yml
Copy the contents of that file into .github/workflows/openwiki-update.yml in your repository.
Usage
Start the interactive CLI:
openwiki
Start OpenWiki with an initial request:
openwiki "Please generate documentation for this repository"
Run a single command and exit:
openwiki -p "Summarize what you can do"
Initialize OpenWiki:
openwiki --init
Update existing documentation:
openwiki --update
Show help:
openwiki --help
openwiki creates initial documentation in openwiki/ when no wiki exists. If openwiki/ already exists, it refreshes that documentation from repository changes. By default, the CLI stays open after each run so you can send follow-up messages. Use -p or --print for a one-shot non-interactive run that prints the final assistant output.
openwiki will automatically append prompting to your AGENTS.md and/or CLAUDE.md files to instruct your coding agent to reference it when searching for context. If the file does not already exist in your repository, OpenWiki will create it for you.
On the first interactive run, OpenWiki will have you configure your inference provider, API key, and LLM. You will also be able to set a LangSmith API key to trace your OpenWiki runs to a LangSmith tracing project named “openwiki” (optional).
These configuration options and secrets will be saved to ~/.openwiki/.env on your local machine.
Customizing
OpenWiki supports OpenRouter, Fireworks, Baseten, OpenAI and Anthropic out of the box. By default, there are a few models pre-defined (GLM 5.2, Kimi K2.6, Sonnet 5, etc) but for each inference provider, OpenWiki will allow you to specify your own custom model ID.
If there’s an inference provider or model you’d like to see added, please open a PR!
Similar Articles
OpenWiki: CLI that writes and maintains agent documentation for your codebase
OpenWiki is a CLI tool from LangChain that automatically generates and maintains documentation for your codebase, designed for AI agents. It supports multiple inference providers and can be integrated with GitHub Actions for daily updates.
@GitHub_Daily: AI for long-running complex tasks: as context grows, models tend to 'forget' and output quality drops sharply. The LangChain team has open-sourced a tutorial: Deep Agents from Scratch, which deconstructs core design patterns of mainstream agents from scratch, explained thoroughly...
The LangChain team has open-sourced the tutorial 'Deep Agents from Scratch', which deconstructs the core design patterns of mainstream agents from scratch, covering task planning, context offloading to a file system, and sub-agent isolation. It includes 5 progressive notebooks, allowing you to build a complete deep research agent hands-on.
@BraceSproul: https://x.com/BraceSproul/status/2072375136368660515
OpenWiki is an open source agent and CLI that automatically generates and maintains documentation for codebases, helping coding agents understand repo structure and logic.
@DashHuang: https://x.com/DashHuang/status/2057323152758480955
This article explores why GitHub is a better foundation for knowledge collaboration than traditional documentation systems in the AI agent era, due to its advantages such as open collaboration, AI model familiarity, local full context, and structured raw data.
@mylifcc: Recently while working on Agent memory and personal knowledge systems, I discovered this project obsidian-wiki, so fitting! It brings Andrej Karpathy's LLM Wiki pattern to Obsidian: enabling AI Agents to autonomously inges…
This tweet introduces the obsidian-wiki project, which implements Andrej Karpathy's LLM Wiki pattern on Obsidian, allowing AI Agents to autonomously ingest multi-source knowledge and organize it into a wikilink-interconnected markdown knowledge base. It supports Delta incremental updates and source attribution (provenance), and has built-in features like query, audit, graph export, etc. Currently at 2k stars.