herdr

This new GUI looks awesome, however it's not clear how to do the agent integration? With the TUI I installed the skill via `npx skills add https://github.com/herdrdev/herdr --skill herdr` and the agent knew what I was talking about when I said herdr, now I have to tell the agent 'Read `herdr-app --skill` and ...' - seems like extra steps?

Nope. I think you are confused since Herdr was free software and licensed under AGPL 3.0 [0] before it was VC funded. One (emacs) gets millions in donations via the FSF and the other get little to no money or donations for being "free software" from the start despite both of them being "free software". [0] https://github.com/herdrdev/herdr/blob/a57b97285c3308fbdcc16...

I run a similar setup, just with different models. I also use herdr, which lets me have the same project worked on side by side by different models, each in its own git worktree. https://github.com/earendil-works/pi https://github.com/herdrdev/herdr

pi-cowboy is an agent orchestrator for Pi(https://pi.dev) and Herdr(https://github.com/herdrdev/herdr). Break large jobs into focused subtasks, hand them off to background agents running in parallel, and consolidate the results when they finish. Each agent runs in an isolated copy-on-write Git work-tree, minimising disk overhead. pi-cowboy can orchestrate foreign harnesses too, including Claude Code, Codex, OpenCode and more. Feature highlights: - Foreign harnesses: pi-cowboy agents can run in Claude Code, Codex, OpenCode, Pig and Pi-Bolt, as well as Pi. This gives you great flexibility in choosing how to spend your tokens. Running out of Codex usage? Switch your pi-cowboy harness to OpenCode, select one of its free models, and let it handle the rest. Pig and Pi-Bolt are pi variants that are more efficient, with a lower memory footpr

How does this compare to something like herdr which does all of this? https://github.com/herdrdev/herdr

Sadly it does not. There are both a discussion about support for non-git vcs (https://github.com/ogulcancelik/herdr/discussions/522) and about jj specifically. Hopefully any of those get some traction

I've been working on my own private harness for the past 8 months, and I've been collecting ideas from such repos I've stumbled upon. pi-tmux is one such example (seems to be archived now) which inspired me to use tmux as communication layer and provide visibility of subagents of multiple models in their native harnesses [1]. There's also herdr, which is not 0-stars, but is super interesting but lesser known project [2]. This also has interesting substrates to allow agent coordination. None of these are harnesses per se, but they're pointing towards clear gaps in existing harnesses. For example, we've known for a while now that compounding knowledge of different class of models achieves better performance. Why is there no harness where this is a native functionality? And there's no harness where subagents are first class citizens both in

I'm currently using herde[1] to handle/supervise multiple agents (with some patches I need to try to upstream) along with Nono[2] for sandboxing. This sandboxing approach avoids use of a microVM, which lets me use tooling I already have installed inside the sandbox. The downside is getting all the policies correct as it seems every project needs some new type of access, though Nono does try to make policy writing easy. I've been considering switching my approach to using a microVM through microsandbox[3]. The pro of this approach is you can essentially skip the policies and rely on the security of the VM boundary. The negative is that now you've lost all your installed tools, so you need to either provision at runtime or build something (like an image) beforehand to match your dev environment. I still don't know which is less maintenance.