Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise. Learn more →
Top 23 Rust coding-agent Projects
-
herdr is the terminal multiplexer on my laptops. Unlike tmux, it knows which pane is an agent and whether that agent is working, blocked, done or idle:
-
AppSignal
AppSignal knows why the f*#k it crashed. Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
-
atlas
Source control for agents. Use multiple coding agents, track their changes and query them in one place (by pacifio)
-
Project mention: Capture why AI wrote each commit, stored in Git-notes | news.ycombinator.com | 2026-08-24
-
Surely the opposite question makes more sense: what's the value add of newer tools?
I will admit that I've used https://herdr.dev/ before because unlike tmux, it displays the status of running LLM agents.
-
-
foremerge
Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
Project mention: AI agents introduced several new layers to the development stack. You are probably missing this one. | dev.to | 2026-09-16We open-sourced the coordination layer we built and use: Foremerge (https://github.com/naw103/foremerge), Apache-2.0, one Rust binary, local-first, above Git rather than inside it. Setup is one paste into Claude Code, Codex, or Cursor. Stated plainly per the honesty its own docs demand: detection is deterministic but heuristic and can warn on compatible work, claims never lock anything, and there are no published benchmarks yet, so no performance claims. The layer matters regardless of whose implementation you run, including one you build yourself.
-
models
TUI and CLI for browsing models.dev, benchmarks, coding agents, and statuses for AI providers. (by reyamira)
Project mention: 10 CLI Tools Every Developer Should Use with AI Coding Agents | dev.to | 2026-04-04A terminal dashboard for comparing AI model providers. Models CLI lets you check pricing, context window sizes, and benchmark results for 2000+ models across 85+ providers without opening a browser.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
diri
The best way to work with coding agents. Run fifty in parallel, let them spawn each other, review everything in one place.
-
Project mention: Show HN: Seiso – A linter for project docs written by AI and read by agents | news.ycombinator.com | 2026-09-28
- judgment calls a tool can't make are written down with a reason
Each diagnostic says where the problem is and how to fix it, so an agent can usually repair it from the output alone. When a fix needs a decision, like which of two pages owns a fact, seiso names the decision instead of guessing. It doesn't try to detect "AI-sounding" prose, and it leaves formatting and spelling to other tools.
To try it: cargo install seiso (also on PyPI and npm), then seiso init and seiso check. Only stable rules run by default. The rest are behind --preview and can still give false positives.
It's early. I'd especially like to hear whether the doc kinds match how your docs are actually organized, and which rules get it wrong on your repo.
https://github.com/scarletkc/seiso
-
txcript
Pandoc for AI chats. Move ai chats across harnesses: Claude Code, Codex, OpenCode, Cursor, and more. Rust library, CLI, and WASM.
Project mention: You can read Claude Code's whole harness now. That's what every benchmark score throws away | dev.to | 2026-09-17The cleanest proof that the harness is doing real work: it's the only thing you can't carry to another agent. Someone is building exactly that portability layer. txcript is a Rust engine that translates a full session, tool history included, between Claude Code, Codex, OpenCode, Cursor and a dozen more agents. It launched on Hacker News as the open-source core of Skillsync, and its name is a tell: pandoc for AI chats.
-
Project mention: neovim VS runyte - a user suggested alternative | libhunt.com/r/neovim | 2026-09-01
Runyte is a fast terminal editor written in Rust. Common motion keybindings will feel familiar to users of both Vim and Helix. Terminal multiplexer, file manager, fuzzy search anything (files, buffers, terminals) and jump anywhere.
-
Project mention: I Let an AI Agent Supervisor Run Unattended for 19 Days. Here's What the Telemetry Says. | dev.to | 2026-04-16
Batty is supervised agent execution for software teams. It runs agents (Claude Code, Codex, Aider) inside tmux panes, tracks work on a markdown kanban board, gates merges behind a real test run, and surfaces escalations to a human via Discord. The supervisor itself is a Rust daemon. It's open source: github.com/battysh/batty.
-
Project mention: Open-agent-view: One dashboard for all your coding agents | news.ycombinator.com | 2026-08-27
-
Project mention: Show HN: Terminal-native prompt composer for power users running many agents | news.ycombinator.com | 2026-09-03
-
agent-box
Sandboxed containers for AI coding agents with disposable Git/Jujutsu workspaces (by 0xferrous)
Project mention: A way to exclude sensitive files issue still open for OpenAI Codex | news.ycombinator.com | 2026-06-28I've contributed to https://github.com/0xferrous/agent-box which allows you to bind-mount git repositories into containers that agents operate in. Your usual .gitignore can then be used to ignore files to be bind-mounted, which preventa agents from accessing them at all.
I've also created https://github.com/nothingnesses/agent-images which allows you to use Nix to reproducibly spin up OCI containers containing agents and use these with agents-box.
I use both at the moment to work on some personal projects with agents, where I set up multiple separate git worktrees for the agents to work in and that prevents them from trampling over each other's work.
-
agent-console
A local terminal control plane for Codex, Claude Code, and pi sessions—discover, monitor, resume, and work beside persistent workspace shells. (by buhuipao)
Project mention: Show HN: Agent Console – A Local Dashboard for Codex and Claude Code | news.ycombinator.com | 2026-07-27 -
Project mention: Show HN: Perspica – A semantic diff for reviewing code | news.ycombinator.com | 2026-09-30
-
agent-hop
Runtime for coding-agent harnesses. Run Claude Code, Codex, OpenCode, Pi, and Grok in one terminal; hop live between them; search or resume any local session.
Project mention: Show HN: Agent-hop – a Rust TUI that hops a live Claude Code chat into Codex | news.ycombinator.com | 2026-08-26 -
Project mention: Show HN: Riftri – copy-on-write Git worktrees for running agents in parallel | news.ycombinator.com | 2026-09-23
check more here including the benchmarks and numbers - https://github.com/assistant-ui/riftri
-
repopilot
Local, deterministic review of Git changes: weakened tests and CI gates, security boundaries, blast radius. CLI, GitHub Action, MCP server, and coding-agent plugins.
Project mention: 358 pull requests that changed tests: agents rarely weakened them. They bent the code instead. | dev.to | 2026-10-04Repo: https://github.com/MykytaStel/repopilot
-
Project mention: Show HN: Lunar, a coding harness extensible via Lua | news.ycombinator.com | 2026-08-21
-
-
lucidos
Software that builds and runs the apps and automations you describe. Your machine, your data, your accounts. MIT licensed.
Project mention: Show HN: Lucidos, a local AI OS that keeps the apps you describe running | news.ycombinator.com | 2026-08-05 -
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
NOTE:
The open source projects on this list are ordered by number of github stars.
The number of mentions indicates repo mentiontions in the last 12 Months or
since we started tracking (Dec 2020).
Rust coding-agents discussion
Rust coding-agents related posts
-
You can read Claude Code's whole harness now. That's what every benchmark score throws away
-
AI agents introduced several new layers to the development stack. You are probably missing this one.
-
Agent orchestrators and agent coordinators are not the same layer
-
31 hard questions about coordinating parallel coding agents, answered
-
Foremerge: Catch conflicts between AI coding agents before they code
-
Capture why AI wrote each commit, stored in Git-notes
-
Reachpad – make applications you can share instantly
-
A note from our sponsor - AppSignal
www.appsignal.com | 9 Oct 2026
Index
What are some of the best open-source coding-agent projects in Rust? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | herdr | 42,938 |
| 2 | atlas | 9,508 |
| 3 | git-ai | 2,814 |
| 4 | herdr | 2,164 |
| 5 | codanna | 755 |
| 6 | foremerge | 521 |
| 7 | models | 513 |
| 8 | diri | 424 |
| 9 | seiso | 179 |
| 10 | txcript | 153 |
| 11 | runyte | 104 |
| 12 | batty | 57 |
| 13 | open-agent-view | 44 |
| 14 | proqi | 42 |
| 15 | agent-box | 37 |
| 16 | agent-console | 34 |
| 17 | perspica | 33 |
| 18 | agent-hop | 32 |
| 19 | riftri | 23 |
| 20 | repopilot | 23 |
| 21 | lunar | 13 |
| 22 | tauri-plugin-ui-inspector | 8 |
| 23 | lucidos | 8 |
Sponsored
AppSignal knows why the f*#k it crashed.
Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
www.appsignal.com