SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 Rust ai-tool Projects
-
cc-switch
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Project mention: DeepSeek makes the V4 Pro price discount permanent | news.ycombinator.com | 2026-05-22 -
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
computer-agent
Desktop app to control your computer with AI using your terminal, browser, mouse & keyboard
-
Project mention: Ask HN: How do you give AI agents real codebase context without burning tokens? | news.ycombinator.com | 2026-03-05
Working on a large Rust codebase. The token problem is real — Claude Code will happily spend $5 of context just trying to understand how two modules relate before writing a single line. And once context compaction kicks in, it's even worse — the agent loses the thread completely and starts grepping the same files again from scratch.
Approaches I've tried:
Feeding CLAUDE.md / architecture docs manually — helps, but gets stale fast. Cursor's built-in indexing — breaks on monorepos, and I don't love proprietary code going to their servers. Basic MCP server with grep — works for exact matches, useless for semantic queries.
Eventually built something more serious: a local Tree-sitter indexer that builds a knowledge graph of file relationships and exposes it via MCP so agents query semantically instead of grepping blind. One tool call instead of 15 grep iterations. Published it here: https://github.com/Muvon/octocode
But genuinely curious what others are doing before I go deeper on it.
Three specific questions:
1. How do you handle the "ripple effect" problem — knowing that changing one file semantically affects others that aren't obviously linked?
2. Do you trust closed-source indexing with proprietary code, or have you gone local-first?
3. Has anyone gotten GraphRAG-style relationship mapping to work in practice at scale, or is it still mostly hype?
-
hcom
Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Cursor CLI, OpenCode, Kilo, Pi, Kimi (by aannoo)
Project mention: CLI tool for live communication between agents in different TUIs and subagents | news.ycombinator.com | 2026-02-13 -
I have a custom Mac app that runs a workflow with plan/build/review/test/document subagents in Ralph loops, manages MCPs, etc. that I'm extremely happy with so far.
Beads was a bit of an inspiration for parts, as was Chainlink (https://github.com/dollspace-gay/chainlink).
-
slowql
Next-generation SQL static analyzer written in Rust. 282+ rules. Zero false positives. Security, performance, reliability, cost, compliance, quality. 14 SQL dialects. Offline. CI/CD ready.
Project mention: SlowQL – stop bad SQL before it reaches production | news.ycombinator.com | 2026-03-09- Quality (30 rules): naming, deprecated syntax, style
171 rules total. 873 tests. Zero telemetry. Your SQL never leaves your machine.
pip install slowql && slowql
I spent serious time on the terminal experience — health score gauge, severity heat map, keyboard navigation. It sounds like a detail but it drives actual adoption.
GitHub: https://github.com/makroumi/slowql
-
Project mention: Is Claude Code 5x Cheaper Than Cursor? I Ran 12 Experiments to Find Out | dev.to | 2026-03-31
Use "token-reducing" libraries like RTK. The premise is that a lot of CLI binaries that the AI coding agents call generate noisy output that is bad for LLMs. It creates a proxy to optimize the tokens. Consider looking for more, since this is a class of tooling. In the CLI, there is tokf. There are also prompt compressors like Microsoft's LLMLingua.
-
forgemax
Code Mode inspired local sandboxed MCP Gateway - collapses N servers x M tools into 2 tools (~1,000 tokens)
-
skillfile
One-stop shop for AI skills and agents. Search 110K+ community skills, install and track them declaratively, and deploy across all major AI coding tools (Claude Code, Codex, Cursor, Antigravity and more)
Project mention: Skillfile, the declarative skill manager, now auto-discovers skills in repos | news.ycombinator.com | 2026-03-19 -
Project mention: Show HN: Give your AI agent a brain that understands your codebase | news.ycombinator.com | 2026-05-16
-
scryer
Model-driven development for coding agents. Plan changes in a shared responsibility model mapped to your code; your agent reads, modifies, and implements it through a built-in MCP server.
Bringing model-driven development to coding agents with a desktop tool called Scryer: https://github.com/aklos/scryer
It's still pretty experimental, but I think now that AI can feasibly generate code from intent/specs it's worth doing... especially with how much vibe coding is both a blessing and a curse.
Basically, what if we took those markdown specs everyone likes using and systematized them into a model graph then represented that as a wiki? And what if we surfaced a planned change to a codebase as a diff of the definition of that model? You can then properly keep track of what gets implemented and how, because you're no longer reading an essay from the agent as a plan, you see a complete diff of everything it plans to do.
I've been using it myself for work, but it'd be nice to get some feedback from other people's perspectives.
-
fossil-mcp
The code quality toolkit for the agentic AI era. Find dead code, clones, and scaffolding across 15 languages. MCP server + CLI.
Project mention: Fossil MCP – Dead code detection for vibe-coded projects | news.ycombinator.com | 2026-02-10 -
mcpls
Universal MCP to LSP bridge - expose Language Server Protocol capabilities as MCP tools for AI agents
Project mention: Language Server Protocol (LSP) for AI Coding Agents | news.ycombinator.com | 2026-01-04 -
Agent-Span
The Web Access Gateway for AI Agents — 52 channels, 92 MCP tools, 9 SDKs, self-healing backends, async Rust
-
rewindos
A private, open-source alternative to Windows Recall — for Linux. Captures your screen, OCRs it, and makes everything you've seen instantly searchable. 100% local, no cloud.
Project mention: RewindOS – Searchable screen history for Linux local | news.ycombinator.com | 2026-06-16 -
codeprism
An experimental, 100% AI-generated, high-performance code intelligence server providing AI assistants with a graph-based understanding of codebases.
-
primer
Build real software step-by-step with Claude, Codex, OpenCode, Gemini, Cursor, and other agents (by armgabrielyan)
Project mention: Show HN: Primer – build software with AI agents one milestone at a time | news.ycombinator.com | 2026-03-23 -
HashMeterAi
The honest, local-first usage meter for AI coding tools. With full privacy and with no server or reading your chats.
Project mention: Show HN: HashMeterAi – Private AI Token Real Usage Meter for All Models | news.ycombinator.com | 2026-06-15 -
mnemoria
Persistent, git-friendly memory storage for AI agents — hybrid semantic + full-text search, append-only binary format, zero-copy reads
Project mention: Show HN: Oc-mnemoria – Persistent memory for AI coding agents | news.ycombinator.com | 2026-03-02 -
lumen
Real-time LLM token and cost monitor with TLS-intercepting proxy or HTTP relay; cross-platform with macOS status bar app and browser dashboard (by DataGrout)
Project mention: Show HN: Lumen–free Real-time LLM token and cost monitor | news.ycombinator.com | 2026-06-11 -
baseline
Enforce architectural decisions AI coding tools keep ignoring — bans, ratchets, and design system rules in a single Rust binary (by stewartjarod)
Project mention: Show HN: Baseline – enforce team decisions ESLint can't express | news.ycombinator.com | 2026-02-22 -
callimachus
One local, searchable index of your AI coding-agent history Claude Code, Codex, Cursor, Gemini & more. Keyword + semantic search, MCP server, CLI & VS Code extension.
Project mention: Show HN: Callimachus – Local search across your AI coding-agent history | news.ycombinator.com | 2026-06-20 -
vigilo
Audit trail and cost tracker for AI coding agents. See exactly what Claude Code and Cursor read, wrote, and executed - locally, in real time. (by Idan3011)
Project mention: Show HN: Vigilo – Local audit trail and cost tracker for AI coding agents | news.ycombinator.com | 2026-02-24
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-tools discussion
Rust ai-tools related posts
-
Kimi K3, Qwen 3.8, and Anthropic's (Potential) Unravelling
-
Where every major LLM stands politically
-
Show HN: HashMeterAi – Private AI Token Real Usage Meter for All Models
-
We rebuilt our auth back end in under an hour using a DSL/compiler approach
-
Is Claude Code 5x Cheaper Than Cursor? I Ran 12 Experiments to Find Out
-
Skillfile, the declarative skill manager, now auto-discovers skills in repos
-
Skillfile, the declarative skill manager, now auto-discovers skills in repos
-
A note from our sponsor - SaaSHub
www.saashub.com | 20 Jul 2026
Index
What are some of the best open-source ai-tool projects in Rust? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | cc-switch | 117,566 |
| 2 | computer-agent | 670 |
| 3 | octocode | 433 |
| 4 | hcom | 392 |
| 5 | chainlink | 350 |
| 6 | slowql | 217 |
| 7 | tokf | 191 |
| 8 | forgemax | 149 |
| 9 | skillfile | 137 |
| 10 | bitloops | 112 |
| 11 | scryer | 78 |
| 12 | fossil-mcp | 63 |
| 13 | mcpls | 49 |
| 14 | Agent-Span | 43 |
| 15 | rewindos | 40 |
| 16 | codeprism | 31 |
| 17 | primer | 15 |
| 18 | HashMeterAi | 14 |
| 19 | mnemoria | 13 |
| 20 | lumen | 11 |
| 21 | baseline | 10 |
| 22 | callimachus | 5 |
| 23 | vigilo | 4 |
Sponsored
SaaSHub - Software Alternatives and Reviews
SaaSHub helps you find the best software and product alternatives
www.saashub.com