opencrow — Self - Claude Code that gets smarter the more you use it
by•
Run claude — it gets smarter the more you use it. opencrow adds cross-session recall and background learning to the Claude Code CLI. No extra API key.
Replies
Best
Maker
📌
Hey Product Hunt 👋
I built opencrow to scratch my own itch. I use Claude Code every day, and the same thing kept bugging me: every session starts from zero. It doesn't remember how I like things done, and I'd keep re-explaining the same context or re-solving the same little tasks.
Claude Code actually ships the building blocks to fix this — hooks, skills, memory, MCP — but nothing wires them together into something that learns from how you use it. So I built that layer.
opencrow is a thin wrapper. You run opencrow instead of claude, and the foreground is your exact same interactive session — nothing intercepted, nothing re-rendered. What changes is around it:
- Each turn, it pulls relevant work from your past sessions into context (and you can full-text search your own history).
- When the session ends, a background pass indexes the conversation, remembers your preferences, and turns recurring tasks into reusable skills — written into your global ~/.claude/skills/, so any claude session benefits.
Two things I cared about a lot:
- No extra API key. It drives the claude you're already logged into, so it stays on your subscription.
- Everything is inspectable and reversible (opencrow memory / opencrow skills, archive-not-delete). Auto-generated stuff you can't undo is scary to rely on.
It's MIT, and macOS (arm64) is the primary target right now. Other platforms may work but are less tested — feedback there especially welcome.
I'd love to hear: what's your current setup for making Claude Code remember things across sessions? And what kinds of skills would you want it to learn for your workflow?
Report
Does the background learning actually persist across completely separate projects, or does the memory stay scoped to whatever folder you launched Claude from?
Report
Maker
@alparsland64069 It persists globally. We can add project-scoped learning as a feature if there's demand for it.
Report
the no-extra-api-key approach is genuinely clever, lets claude code just keep getting sharper across sessions without you babysitting config or juggling credentials. clean execution.
Report
Maker
@ratkca43150 Thank you! Exactly. Since Claude Code runs in the background, I can efficiently keep the knowledge-learning feedback loop going.
Report
ran it for a few sessions and the cross-session recall actually stuck, like it remembered my preferences without me retyping them. really handy when you jump between projects
Report
Maker
@betlhasdem6t4n Thanks, that's exactly what it's built for! The recall index and your learned preferences live in one global store, so they carry across every project without you retyping anything — jumping between repos is where it pays off most. If you ever find cross-project facts bleeding together in a way you don't want, that's on our radar too: we can add optional project-scoped learning down the line. Glad it's sticking for you.
Report
opencrow hooked me when I closed the session and reopened it a day later, my project context was already there in claude. wild time saver
Report
Maker
@eslemdasuywptd Love hearing that! Picking up right where you left off a day later is exactly the point — when the session ends, opencrow indexes it in the background, so the next session starts with your context already recalled instead of you rebuilding it from scratch. Thanks for giving it a spin, and glad it's saving you time!
Replies
Does the background learning actually persist across completely separate projects, or does the memory stay scoped to whatever folder you launched Claude from?
@alparsland64069 It persists globally. We can add project-scoped learning as a feature if there's demand for it.
the no-extra-api-key approach is genuinely clever, lets claude code just keep getting sharper across sessions without you babysitting config or juggling credentials. clean execution.
@ratkca43150 Thank you! Exactly. Since Claude Code runs in the background, I can efficiently keep the knowledge-learning feedback loop going.
ran it for a few sessions and the cross-session recall actually stuck, like it remembered my preferences without me retyping them. really handy when you jump between projects
@betlhasdem6t4n Thanks, that's exactly what it's built for! The recall index and your learned preferences live in one global store, so they carry across every project without you retyping anything — jumping between repos is where it pays off most. If you ever find cross-project facts bleeding together in a way you don't want, that's on our radar too: we can add optional project-scoped learning down the line. Glad it's sticking for you.
opencrow hooked me when I closed the session and reopened it a day later, my project context was already there in claude. wild time saver
@eslemdasuywptd Love hearing that! Picking up right where you left off a day later is exactly the point — when the session ends, opencrow indexes it in the background, so the next session starts with your context already recalled instead of you rebuilding it from scratch. Thanks for giving it a spin, and glad it's saving you time!