Show HN: AutoLearn Skills for self-improving agents

(autolearn.dev)

27 points | by toobulkeh 19 hours ago

5 comments

  • toobulkeh 19 hours ago
    I vibe coded this at a hackathon a few weeks ago. The solution isn’t stable yet, but it’s similar to Claude Skills with the benefit of only needing an MCP client.

    I open sourced it too.

    It has a bit to go—like automatically monitoring reasoning traces and security—but I thought this would be easier to use than trying to maintain your own skills.md collection if the server handled more of it for you.

    I’d be curious if anyone thinks I should keep working on it. I’d love someone to collaborate with on it!

  • stpedgwdgfhgdd 15 hours ago
    I sometimes have to decide between running Claude Code headless with a prompt or let CC generate an application based on the prompt. (coining: Codification Threshold tradeoff)

    The tradeoff is that the prompt is non-deterministic, but also more flexible. It can handle unknown situations. The generated code executes much faster and reliable for known situations.

    If auto-learn would reduce the non-deterministic nature, i.e. chance of failing, that would speed up software development.

  • snowfield 13 hours ago
    This is a very interesting concept. I have a few questions though.

    Even if the agent has mcp tools avaible, you can't guarantee that it would necessarily use them right? I imagine that you'd have a lot of new tools that do nearly the same things.

    Also how does this scale? If the agent has like 300 tools.

    • toobulkeh 7 hours ago
      I don’t know (yet) but some ideas might be: 1. A skill that searches skills 2. MCP that returns only relevant skills based on context 3. Separate concerns through sub agents that each have their own autolearn server
  • drdeca 17 hours ago
    How does it determine whether the code it has for the skill, failed? (In order to determine that it needs to improve the code for that skill, I mean)
    • toobulkeh 16 hours ago
      Definitely needs some work here. That isn’t done (yet). Great feature request! I think it would be some kind of testing logic or feedback loop. Or both!
  • personjerry 17 hours ago
    I don't understand, it'd be nice to see even a single example of the application