Skip navigation
This is actually useful.
0:00 / 6:18

This is actually useful.

Min Choi

@minchoi392K followers

Visit on X
1,117 likesDownloadOriginal post

126,632 views

This is actually useful. LangChain just released OpenWiki. It's an open-source agent that creates a wiki for your codebase, connects it to your coding agent, and keeps it updated as your repo changes. Your AI coding agent gets long-term repo context without stuffing everything into CLAUDE.md. Here's how to setup. Save this.

35 Comments

Comments from the original post on X (Twitter)

  • Min Choi's profile picture

    @minchoi

    GitHub repo:

    47 likes

  • Dagmfre Seid's profile picture

    @dagmfreseid

    Wait isn’t there gitingest already?

    3 likes

  • Brian Kennedy's profile picture

    @dans_la_cuisine

    Surprised it’s not called LangWiki. Feels off brand for them, not sure why…

    3 likes

  • Antony Fuentes's profile picture

    @antonyfuentesa

    Cool stuff. This is a limitation in today’s agents. I would love something similar but for learnings, workflows, user common preferences, etc … say my agent once spent 5 cycles attempting something until it “learned” what was blocking it and succeeded at the task, then the wiki grabs it as a learning so next time the cycle is faster. I know this can be done with Karpathy’s wiki approach (I’m already doing it). However just kinda weird why coding agents like @cursor_ai @claudeai and codex dont do it out of the box.

    3 likes

  • Dr. Tali Režun's profile picture

    @talirezun

    Been solving this manually for close to two years now, back when context windows were tiny and models were nowhere near this capable. My approach: Before any code gets written, I build a foundational documentation set. Architecture file, project blueprint, UI/UX scenarios, features definition. All markdown, all written before an agent touches anything. During the actual build, I feed the relevant files into context as needed instead of dumping everything at once. I maintain running memory through AGENTSmd and CLAUDEmd, plus a separate memorymd file. And once I hit around 80% of the context window, I write a handoff file, basically a compressed briefing that lets a fresh agent session pick up exactly where the last one left off without burning tokens re-deriving everything. It works, but it's genuinely a lot of manual upkeep. That's exactly why I'm glad something like OpenWiki exists now, it automates a big chunk of what I've been doing by hand for codebases specifically. One more piece I've added recently: I run this whole memory layer through The Curator, an app with an MCP server built in, so agents can read and write to a persistent knowledge graph instead of me managing every file manually. Feels like one more piece of the same mosaic everyone's converging on. Agents need an actual memory layer, not just a bigger prompt.

    3 likes

  • dhang's profile picture

    @DarayuthH

    been looking for something exactly like this the CLAUDE.md approach was getting messy fast

    2 likes

  • Min Choi's profile picture

    @minchoi

    Nice

    1 like

  • Ben Charoenwong's profile picture

    @BenCharoenwong

    Is this line a complement to, or substitute of, graphify? Anyone tried using both?

    2 likes

  • Haichao's profile picture

    @haichao3606

    Is it possible to let the coding agent update openWiki? So it can always stay up to date, no need for another model api, and coding agent might have clearer context on what is the change and what worth remember.

    2 likes

  • John's profile picture

    @johnmccoyx

    the real bottleneck was never context, it was nobody wanting to babysit a wiki. this just automates the babysitting

    2 likes

  • Skillselion's profile picture

    @Skillselion

    the auto-updating part is the whole point. a hand-written codebase wiki rots the second someone refactors, and a stale wiki is worse than none - the agent trusts it and confidently builds on context that's no longer true. keeping it in sync is the hard problem, not generating it.

    1 like

  • 08Tech | AI News's profile picture

    @_08tech

    This is useful 👍🔥 Thanks for sharing

    1 like

  • Storm Wrath's profile picture

    @antiPlacid

    Careful... Medusa flagging 13x Critical concerns incl Security issue detected: agentic-supply-chain-tool-compromise

    1 like

  • Burke Holland's profile picture

    @burkeholland

    I love to see this as a standard. Ideally though, this would be baked into harnesses not requiring a 3rd party CLI / subscription.

    1 like

  • Void IA's profile picture

    @Void1_IA

    ¿Y el contexto operacional? Permisos, decisiones históricas, por qué un componente está aislado. Eso no emerge del código.

  • Rian Arz's profile picture

    @rianarz

    LangChain's OpenWiki is a smart move for agent memory. We've seen similar context wins in Supabase + vector stores for our couple app — the agent can now reference past decisions without re-summarizing the whole repo every run. Curious how it handles merge conflicts in the wiki.

  • Behnam Ebrahimi's profile picture

    @BehnamEbrahimi

    the keeping-it-updated part is where this lives or dies. if the wiki drifts from the actual repo state, it's worse than no context because the agent trusts stale info. wonder how it handles merge conflicts and rebases

  • Neural Times's profile picture

    @Neural_Times

    so now we just get a wiki instead of the usual waitlist spam? guess ai is finally reading documentation too

  • Manoj Subramanyam's profile picture

    @unscriptedmanoj

    I solved it using a default CONTEXT.MD file for each folder like a init file and rules file or folder at root level that takes care inter-relationships. I ask agent to update relevant context files after every valid change.

  • 红孩儿Redman's profile picture

    @redman_talk

    Wait, so no more bloated CLAUDE.md? Finally. This actually solves a real problem. Saving this one.