What does it do?
firstmate is an agent distro: a portable directory of instructions, skills, tooling, policies, and state conventions that turns a general-purpose agent into a specialized one. [1] You talk to one agent, the first mate, which spawns autonomous agents in visible sessions, gives each a clean git worktree so parallel work on one repository does not collide, supervises them, and returns finished pull requests, approved local merges, or investigation reports. [2a][2b] For example, asking it to fix a flaky login test and add dark mode makes it clone the project, spawn two isolated workers, and report a pull request ready for review. [3]
Activity, over time
Daily observations from the public event archive.
Attention
Daily stars & forks
Star accumulation
Cumulative stars
Pull requests
Daily opens & merges
Conversations
Daily issues & comments
Community
Daily accounts & reviews
Releases
Daily releases
Trending history
Daily top 10 · last 90 days · UTC
Latest stargazers
The last 10 distinct accounts we observed this year.
Most active participants
PR, issue, comment & review events in the past year.
Packages
README badges
Embed a badge in your README or website.
Mentions
Ask HN: Agent swarm, orchestra, sequential, what's your workflow? Hi, Something I've read here and there is people using LLMs for multi-agent orchestration, and I cannot fully understand the idea behind it. So for those of you who do, do you not review code anymore, as you're undoubtedly the bottleneck in this setup? How does this not end up in a chinese whisper game, especially considering how much LLMs infer, guess, and find edge cases and whatnot everywhere? I have two co worker, one is closer to my workflow, plans a lot, build one at a time, almost a duet with our company's LLM. Another one will take the conf room and voice mode over with his orchestrator, define all kind of things and full send it. One is a system engineer the other a web dev, but you get the idea. I have looked at various attempt from people on github to implement these things, eg kunchenguid/firstmate; herdr itself; claude multi agent process. It has never worked out on my end, is it because of the complexity of the work or am I incompetent at delegating? I understand the importance of mastering LLMs in this brave new world but to me it seems complicated to handle more than one at a time, especially if the problem is complex and requires reading/back and forth with it. I'd appreciate resources of any kind to look deeper into it, or reading some of your work flows, good people of HN. Cheers :)
@fabienpenso Try kunchenguid/firstmate @kunchenguid
私もイマココで、このやり方を支援してくれる kunchenguid/firstmate って仕組みを愛用してます。メインエージェントだけがラップトップで動いてて、他のエージェントはすべて自宅サーバーで動かしてるので、ラップトップ閉じられない問題もなくてとてもよいです。
@tibo_maker solved this a few months ago with firstmate kunchenguid/firstmate you are not alone. we got this pain because we were juggling the sessions ourselves everyone who used firstmate knows how good it feels when it’s the agent doing the context switch, not you
Day 89 of building in public REA let me completely clone a Mac app that I liked - fucking crazy sruff morluto/rea And running it via firstmate to manage the orchestration - kunchenguid/firstmate t.co
@shan3v herdr + kunchenguid/firstmate has been working pretty well