This is actually useful.
@minchoi392K followers
126,632 views
35 Comments
Comments from the original post on X (Twitter)

@minchoi
GitHub repo:
47 likes

@dagmfreseid
Wait isn’t there gitingest already?
3 likes

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

@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

@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

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

@minchoi
Nice
1 like

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

@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

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

@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
This is useful 👍🔥 Thanks for sharing
1 like

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

@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

@Void1_IA
¿Y el contexto operacional? Permisos, decisiones históricas, por qué un componente está aislado. Eso no emerge del código.

@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.

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

@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.

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














