Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

  • Hacker News
  • I was immediately hoping for some local-AI setups that do real work, on limited resources. Unfortunately it looks like this is still waiting on more people to share.
  • As always with smallish tools/services like these whipped up with an LLM, I find there's more value in seeing the "source code", i.e. the prompt itself.

    Turns out it's quite useful in this instance, and I just made a small couple of tweaks to get a summary of my own workflow.

    FWIW, this is what I modified it to:

    Help me share how I work with AI with my teammates.

    Use our existing conversations and relevant local tools within my permissions to discover my agents, harnesses, skills, connections and working practices. Keep secrets, raw configuration and private project details out of the draft. Explain how my tools work together and develop a concrete workflow where the evidence supports it, rather than listing installed software. Draft from what you know without a questionnaire; ask one short question only if an essential gap prevents a useful draft. If local inspection is unavailable, use our conversation without claiming otherwise. Save a private draft, show me the exact preview, and wait for my explicit approval before publishing.

  • It'd be useful to see "approx monthly cost" or something similar. I love seeing other people's setups, but the first post I clicked on describes at least $400/mo in subscription plans.
  • It’s called Autobot, it’s designed to get as close as I could reasonably get to a real world Iron Man Jarvis.

    WHAT IT DOES

    OSS/MIT Harness that helps agentic tasks run for up to 4 days using without performance degradation. Designed to work really well in native, conversational voice mode. Does a good job with knowledge work, managing computer use “leases” in a way that avoids conflicts across sub agents.. or deploying an entire AWS infrastructure pattern from zero and launching 100 different VM images.

    HOW IT DOES IT

    Uses a canonical event ledger, heartbeat (for persistence by low cost orchestration), extends foundation memory to encrypted disk storage, and manages its own scheduling system (easier to switch to another platform).

    Installs as a project, so very easily. Zero config. No special app, access needed.

    Accompanying repos have the skills to disable approvals inherent to the foundation models (use with caution, not advised - separate repo under parent).

    BENCHMARKS

    Currently top of AssistantBench Leaderboard; and, benchmarked at the top of OS World 2.0, the hardest knowledge work computer use benchmark I could find, using a model that is one generation behind. All benchmarks in repos with cryptographic seals.

    Entirely free, nothing to sell - it’s been a game changer for me, so I’m just putting it out there.

    Hoping to find others also working on pushing this particular dimension of harnesses forward.

    CHECK IT OUT

    https://github.com/demeyer1/Autobot/graphs/traffic

  • Well, not a dev here, so my primitive setup is to have an alias in my .bashrc that launches firefox with the prompt added to the Google AI mode, so all I have to do is Super+T (terminal), type 'ai' followed by my query. For laughs, this also allows to bake in response styles:

      query="$*"
      base="Respond like Dr. House, do not hold back the profanities; "
    
    I also have an even shorter alias for '?' using fabric that answers right in the same terminal, that I learned from Mischa Vandenburg:

      echo "$*" | fabric --model gemini-2.5-flash --pattern ask_ai
    
    that one I use my own API key so it costs some small amount per use.
  • 20 year industry vet here. Yeah, no thank you. In the age of AI, developer productivity and job security will involve your proprietary workflow. It no longer makes sense to share your knowledge with the world.

    I'd highly advise people don't do this.

  • My local setup: I begrudgingly open `claude` on a terminal, hate it for 8 hours, then turn off my computer and forget it exists. Rinse and repeat
  • This feels self-selective to how some people work, because it requires using MCP to contribute.

    I'm a reasonably heavy AI user, and have some custom skills/MCP servers I'd share, but there is no way in hell I'm connecting to some arbitrary MCP server and connecting my Github account to it. Noppppeeeee.

Explore Birbla archives