SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 Rust ai-agent Projects
-
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
For solo development there are already plenty of good tools: Agent Deck, AoE, Vibe Kanban, CCManager, and others. Most of them support different agents. Agent Deck and AoE can run sessions in Docker. Agent Deck can work with your own sessions on other remote servers.
-
OpenFang is an operating system for autonomous agents. Not a framework. Not a wrapper. An actual OS, written from scratch in Rust by RightNow AI. 137,728 lines of code across 14 crates. Compiles to a single 32MB binary with zero external dependencies. This is not something someone cobbled together over a weekend.
-
-
aichat
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.
-
If you don't want to do that, don't use a VM. I like nono:
https://github.com/always-further/nono
-
forkd
Fork() for AI agent microVMs. Spawn 100 children in ~100ms from a warm parent; BRANCH a live VM in ~150ms. KVM-isolated, snapshot CoW.
-
Project mention: Show HN: Smol machines – subsecond coldstart, portable virtual machines | news.ycombinator.com | 2026-04-17
Could it be made even faster using some of the ideas from https://github.com/zerobootdev/zeroboot ?
-
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
-
boxlite
The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud.
Project mention: Show HN: I made a local proxy for AI tool calls to keep my API keys safe | news.ycombinator.com | 2026-05-05it would be cool if we can integrate it with the local micro-VM https://github.com/boxlite-ai/boxlite
-
webclaw
Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.
GitHub repo
-
Install actionbook CLI from https://github.com/actionbook/actionbook run `actionbook setup`, and pick extension mode for browser connection.
-
Project mention: Pi (Rust): High-performance AI coding agent CLI written in Rust | news.ycombinator.com | 2026-07-06
-
weave
Entity-level git merge driver. Resolves false conflicts git invents when independent agents edit the same file. ~95% reduction vs. line-based merge. (by Ataraxy-Labs)
Project mention: Weave: Merging based on language structure and not lines | news.ycombinator.com | 2026-06-13This tool does not work. I wanted it to work. I wanted to automate merges with AI supervision. No dice. Silent corruption that wouldn't go away no matter how many issues I filed. Unacceptable. Had to disable it. https://github.com/Ataraxy-Labs/weave/issues?q=is%3Aissue%20...
-
Project mention: Show HN: Ask your LLM traces what went wrong (vLLora) | news.ycombinator.com | 2026-01-26
Hi HN,
We built Lucy, a trace-debugging tool inside vLLora (our open-source LLM observability stack).
The problem: Debugging AI agents is painful. A single failure often hides inside a trace with 200+ spans—tool calls, retries, partial outputs, and silent failures. Even with tracing, finding the actual root cause (e.g. a tool schema mismatch or a contradictory system prompt) usually means manually scanning logs for 20+ minutes.
What Lucy does: Lucy lets you query your traces using natural language. You can ask things like “Why did this agent loop?” or “Which step was slow?” and it inspects the span tree to surface likely causes. For example, it can flag:
- Tool schema mismatches (e.g. hallucinated or invalid arguments)
- Prompt contradictions (e.g. system instruction conflicts with user intent)
- Silent failures (e.g. context truncation or max-token exits)
It’s early and still in beta.
We’d love to hear how you’re debugging agent failures today—logs, replay, evals, custom scripts, or something else.
Link to Repo: https://github.com/vllora/vllora
-
Project mention: Weave – A language aware merge algorithm based on entities | news.ycombinator.com | 2026-03-03
How do you get blob file writes fast?
I built lix [0] which stores AST’s instead of blobs.
Direct AST writing works for apps that are “ast aware”. And I can confirm, it works great.
But, the all software just writes bytes atm.
The binary -> parse -> diff is too slow.
The parse and diff step need to get out of the hot path. That semi defeats the idea of a VCS that stores ASTs though.
[0] https://github.com/opral/lix
-
AutoAgents
A multi-agent framework written in Rust that enables you to build, deploy, and coordinate multiple intelligent agents (by liquidos-ai)
Project mention: Show HN: Running AI agents across environments needs a proper solution | news.ycombinator.com | 2026-03-24 -
horizon
GPU-accelerated terminal board that puts all your sessions on an infinite canvas (by peters)
Project mention: Your Terminal Is Burning Battery Like It's Mining Bitcoin | news.ycombinator.com | 2026-04-29I've always found tabs to be pretty limiting, though I have a ton of them in Firefox and Konsole since that's what's - been - available. They're marginal improvement over multiple windows. Then Horizon[0] came on the scene a few weeks ago and I fell in love with that infinite canvas. Started tweaking it like crazy, but now I'm working on a full port that natively supports Xpra[1], so I can have all my apps on an infinite canvas with views grouped exactly as I prefer. And that's the future IMO.
[0] https://github.com/peters/horizon
-
macro
Macro is a unified interface for email, messages, tasks, calls, agents, pull requests, docs, crm — linked together with shared AI memory. (by macro-inc)
Project mention: Show HN: Macro – unified system for email, chat, tasks, docs, agents (AGPL/Rust) | news.ycombinator.com | 2026-06-15 -
graphbit
GraphBit is the world’s first enterprise-grade Agentic AI framework, built on a Rust core with a Python wrapper for unmatched speed, security, and scalability. It enables reliable multi-agent workflows with minimal CPU and memory usage, making it production-ready for real-world enterprise environments.
Project mention: GraphBit's Internal Execution Flow Architecture: Overview and Key Components | dev.to | 2025-11-10Github: https://github.com/InfinitiBit/graphbit
-
Project mention: Show HN: Instant GraphRAG over any Postgres database | news.ycombinator.com | 2026-07-07
Hi HN, I’m building Polygres.
TLDR: Polygres turns Postgres into a full graph-rag database for agents by combining relational data, graph traversal, vector search, hybrid search, and ranking over the same source-of-truth data.
Insert via sql, query as a graph, and vice versa.
PgVector already exists, but we added the missing component which was PgGraph (OSS). You can check that out here: https://github.com/Evokoa/pgGraph
Currently many companies and teams have to sync together multiple databases (eg postgres + qdrant + neo4j) and I believe much of this should just stay inside the Postgres world, with a single query to retrieve. The magic of connected data, reranking, etc, should be hidden away.
For this launch, we built a public Wikipedia demo as a retrieval test surface. Enter a query and Polygres runs semantic search, text search, candidate merging, and reranking over indexed Wikipedia pages.
-
sandboxed.sh
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets, and OKX read-only security checks.
Project mention: Show HN: Open Agent, My attempt at a managed environment for AI coding agents | news.ycombinator.com | 2026-01-23 -
agnix
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plugin for all major IDEs included, with autofixes.
Project mention: Show HN: Agnix – lint your AI agent configs (Claude.md, skills, MCP, hooks) | news.ycombinator.com | 2026-02-11
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 ai-agents discussion
Rust ai-agents related posts
-
How to Connect an AI Agent to Your Data Warehouse
-
What Is a Semantic Layer? A Practical Guide for Data Engineers
-
Why Your AI Agents Need a Semantic Layer
-
Show HN: Termaxa – I found my AI-agent gate had silently stopped gating Cursor
-
agent-workspace-linux Is Not Computer Use: Verify the Workspace Boundary First
-
Persistent memory for Claude Code that survives context compaction
-
Git tells you what changed. Causari tells you why.
-
A note from our sponsor - SaaSHub
www.saashub.com | 16 Jul 2026
Index
What are some of the best open-source ai-agent projects in Rust? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | chroma | 28,750 |
| 2 | vibe-kanban | 27,344 |
| 3 | openfang | 17,997 |
| 4 | cocoindex | 10,697 |
| 5 | aichat | 10,246 |
| 6 | nono | 3,018 |
| 7 | forkd | 2,718 |
| 8 | zeroboot | 2,403 |
| 9 | herdr | 2,164 |
| 10 | boxlite | 2,151 |
| 11 | webclaw | 1,706 |
| 12 | actionbook | 1,573 |
| 13 | pi_agent_rust | 1,297 |
| 14 | weave | 1,221 |
| 15 | vllora | 810 |
| 16 | lix | 717 |
| 17 | AutoAgents | 712 |
| 18 | horizon | 665 |
| 19 | macro | 576 |
| 20 | graphbit | 568 |
| 21 | pgGraph | 531 |
| 22 | sandboxed.sh | 467 |
| 23 | agnix | 336 |
Sponsored
SaaSHub - Software Alternatives and Reviews
SaaSHub helps you find the best software and product alternatives
www.saashub.com