Rust agents

A native Rust multi-agent operating system and swarm workspace — GPUI desktop chamber, headless gluon daemon, git-worktree isolation and an automatic merge gate.

All Kind of MODEL IN ONE APP. Workspace for Claude Code & Codex — multi-model parallel sessions, Telegram remote control, scheduled cron tasks with push notifications, usage analytics, permission modes. CLI + native macOS desktop app.

A semantic, transactional, replayable MCP control plane that lets autonomous AI agents operate Dwarf Fortress as a long-lived civilization. Safe-Rust phase-0B scaffold: MVCC world state, witnessed semantic plans, evidence-backed effects, deterministic replay.

open-source pentest management built to be operated by an AI agent

Abandoned, unsupported research archive for a local-first, model-agnostic LLM agent harness exploring orchestration, code retrieval, off-agent verification, deterministic replay, sandboxing, context management, and model routing. MIT.

Remote Desktop Control for AI agents: screenshot, mouse, keyboard and window control of another machine over Tailscale, exposed as MCP tools. Built with Rust

croit AIplane — one plane for all your AI. Self-hosted AI infrastructure connecting applications and users with models, agents, tools and enterprise data: an OpenAI-compatible LLM gateway, server-side agent execution, MCP, RAG, memory, sandbox, identity, RBAC and quotas. Routes across vLLM, SGLang, Ollama and hosted APIs.

A state-based autonomous agent framework. Crafting digital entities with non-linear cognitive memory and self-evolving emotions. (Work in Progress)

A minimalistic async Rust implementation of the Model Context Protocol (MCP).

Give your AI Agent understanding of your codebase. A Rust CLI that turns your entire project into a single, optimized context file for Cursor, Antigravity, and Claude.

QilbeeDB is a cloud-agnostic, high-performance graph database built for autonomous AI agents, real-time memory, and enterprise automation.

A state-based autonomous agent framework. Crafting digital entities with non-linear cognitive memory and self-evolving emotions. (Work in Progress)

Protect .env secrets from AI coding agents. CLI (Rust) + VS Code extension. AES-256-GCM vault, OS keychain, Touch ID, smart sandbox values. Agents see fakes — you see the real ones.

Self-hosted API gateway for Claude Code on Amazon Bedrock — unlock extended thinking, web search & tool use with team budgets, OIDC SSO, and an admin portal

The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.

A step-by-step guide to building a Codex-style agent runtime,like codex

An external memory for LLMs: a bi-temporal knowledge graph with hybrid (keyword + vector) retrieval and a self-improving reflection loop. Benchmarked to beat flat vector RAG on corrections and time-versioned queries.

Discord Rich Presence for Codex CLI, Codex VS Code Extension, and Codex App.

Real-time guardrail runtime for AI agents.

muxel is a GPUI-native multiplexer for coding agents

Agentic coding scheduler, a Rust agent harness that runs background coding agents autonomously

A cooperative gate for the shell commands AI agents run. Previews, backups, policy, audit. Claude Code + Cursor. A windshield, not a sandbox.

ShellX — desktop AI workspace for Grok Build, Claude Code, Codex, and Antigravity across Windows, macOS, WSL, and SSH. Includes a private agent browser and secure local Vault for credentials.

A state-based autonomous agent framework. Crafting digital entities with non-linear cognitive memory and self-evolving emotions. (Work in Progress)

A systems language designed so an AI agent can safely write and run backend code: proven no GC/races/overflow, GBNF-constrained generation, structured diagnostics, OS-process sandboxing.

Dure — every coding agent, one workspace across desktop and mobile.

Semantic code search and RAG system written in Rust with tree-sitter chunking, MCP server for IDE integration, prompt injection detection, and secret redaction

Open-source Prompt Firewall — deflect up to 95% of redundant LLM traffic before it leaves your infrastructure. Documents: https://isartor-ai.github.io/Isartor/index.html

Unified API for LLM providers and simple agent library in JS, Rust, and Go

AI gateway built in Rust with advanced routing, caching, and monitoring capabilities.

m1nd is a local-first context runtime for coding agents: an evidence-bound, continuously verified model of your code, memory, and change.

An AI chat proxy with universal tool access, protocol conversion, load balancing, key isolation, prompt enhancement, centralized MCP hub, and built-in WebSearch & WebFetch — more than an AI assistant for chat, translation, mind maps, flowcharts, and search.

Token usage tracker for Claude Code and Codex CLI — Rust daemon, 7ms reports, JSONL-parsing

A better grep for AI agents. Structural search, call graphs, impact analysis, semantic compression. 87% fewer tokens. 16 languages. Built in Rust.

Lightweight AI agent runtime targeting Raspberry Pi Zero 2W and low-end VPS. File-based memory, MCP tool support, Telegram integration — all in a single binary.

This Cloudflare Workers tool automatically adds AI-generated summaries to articles in your Miniflux RSS reader.

A stop-loss for Claude Code: detects loops, compaction danger, failed tools, and token waste before the next request.

Open-source local-first AI desktop copilot with an expressive blob companion, voice and text commands, browser automation, app control, and community-driven capabilities.

Harness Engineering control plane for agent-first software delivery. Orchestrate Claude Code, Codex, OpenCode, and shell-native agents via declarative workflows.

Superzent - an agent-first workspace built on Zed

Perfetto trace analysis via MCP — PerfettoSQL queries plus dedicated Chrome tools for scroll jank, page loads, and main-thread hotspots

Command-line client for the Harmont CI platform

Mission control for a fleet of AI coding agents (Claude Code, Codex, Antigravity, OpenCode, Cursor, Aider) across many repos — desktop app + Rust TUI, tmux-backed, with durable fleet mail and policy-based agent supervision.

Cross-platform Rust daemon that prevents disk-full incidents for AI coding workloads using predictive pressure control, safe artifact cleanup, and multi-volume ballast pools.

Cross-platform Rust computer-use MCP server for macOS and Windows: AX/UIA, screenshots, OCR, pointer and keyboard input, clipboard, stdio, and HTTP.

Local-first desktop command center for Claude Code, Codex, OpenCode, and other coding agents—parallel tasks, worktrees, dev services, port forwards, diffs, and review.

Behavior sharing for AI agents in teams — the topos CLI + self-hostable plane keep every agent's skills current

The AI agent-native systems programming language: Meaning in. Verified machine code out. All target OS, memory managed through Ownership & fully interoperable with existing ecosystems & object-oriented AI Agents with payment capability.

The review app for code your agent writes. Native Rust/GPUI desktop app with real Git workflows.

Git-free file snapshots and rewind — put a directory back the way it was, without a repository and without touching your version control.

Native calendar for Google Calendar, iCloud and any CalDAV server. Born on Omarchy Linux, runs on any Linux and on macOS, with a CLI your agent can use. Tauri, Rust, Svelte.

super over-engineered rust gtk shell with an ai that can shut down your computer

ja is a small CLI / TUI app that allows you to work with AI tools

🤖 AI-powered CLI for file reorganization. Runs fully locally — no data leaves your machine.

Rust SDK for the WhatsApp Business API — bulk messaging, batching, and multi-tenant support.

Agent OS in Rust — one binary, 37 agents, 26 LLM providers, 37 channels (Telegram/Discord/Slack...), MCP server, A2A protocol, 120+ API endpoints, web dashboard

LLM proxy with built-in DLP and regulatory compliance. Redacts secrets before they reach the API. EU AI Act, GDPR, HDS/PCI DSS ready. Multi-provider failover, live TUI, virtual keys, fan-out. 6 MB, zero deps. Rust.

Meerkat - A modular, high-performance agent harness built in Rust.

Rust-based rewrite of Optopsy: An options backtesting engine exposed via Model Context Protocol (MCP)

AI-native static site generator — MCP server, Claude Code integration, sub-second Rust builds

Stop rebuilding your agentic setup every time. Define it in YAML, run it with one command, and share it like a recipe 📜

🛡️ The security firewall for AI agent tools & MCP servers (Claude 5, GPT-5.6, Gemini 3.8, Antigravity, Cursor, Codex, Hermes). Catch command injection, secret theft & toxic flows in <50ms. 100% offline Rust SAST + 1-click auto-fix + SARIF.

Code intelligence engine for AI coding agents. Structural graph queries plus semantic search, exposed via CLI and MCP.

Lightweight, self-hosted Sentry alternative. Rust + SQLite, ~10 MB RAM. Sentry-SDK compatible ingest, fast SvelteKit dashboard, MCP-ready for AI agents.

Stable line-addressed file editing for Claude Code, Codex, ... using content-hashed anchors instead of fragile string replacement.

A modular framework for building complete AI solutions. It's mostly a Rust framework with a subset of it ported to Deno.

Minimalist voice-to-text app. Hold hotkey, speak, auto-paste. Cloud transcription via OpenAI/Groq.

Actor-based DAG workflow execution engine for low-code applications and Agentic AI

Multi-tool AI agent harness — 22 skills, self-evolving engine, unified memory, autonomous spec-to-PR pipeline. Works with Claude Code, Codex, Cursor, OpenCode, and Cline.

🔍 AI-powered code auditor using Rust & Ollama. Features agentic tool-calling architecture where LLM autonomously explores, reads, and analyzes codebases. Detects security vulnerabilities, bugs, and performance issues. Generates detailed Markdown reports with actionable insights.

A general-purpose, multi-provider AI agent engine. Tools, orchestration, persistent memory, and application integration through terminal, headless, and ACP interfaces.

Local repo-intelligence index + MCP server: semantic search, symbol/graph navigation, impact-surface preflight, git + GitHub papertrail, and a source-anchored memory graph.

Zero-trust security gateway between AI agents and MCP servers: scoped capabilities, redaction, rate and cost limits, and verifiable session logs.

Streaming reasoning layer for AI. Incremental rules engine with vector search, graph traversal, and explainable derivation traces.

A cross-platform chatbot framework written in Rust, featuring a flexible dynamic plugin system.

An unofficial Rust SDK for the OpenAI Responses API.

Type-aware, secret-safe clipboard history for Claude via MCP. Rust binary, macOS + Linux. Ships as .mcpb.

Browser-native vector database built in Rust and compiled to WebAssembly for client-side embedding storage and semantic search.

DoWhiz - Oliver, a trusted AI operator for work and life. 🧸

A CLI context hub for agentic work. Used by the Speakeasy engineering team

Ship product, not plumbing. Open source framework for AI-first SaaS — identity, OAuth, API auth, webhooks, notifications, and agents in one stack.

Open Source Code Review Agent for Context-Aware Large Repositories

Agentic Ops Framework

Type-safe, async Rust SDK for the Agent2Agent (A2A) protocol, built to the final v1.0.0 spec — JSON-RPC, REST, WebSocket & gRPC for building interoperable AI agents

Semantic code intelligence for AI agents — compile repositories into navigable concept graphs with impact analysis, coupling detection, and prophecy.

跨平台桌面语音输入工具 / Cross-platform voice input app with real-time HUD, ASR, LLM correction, and text injection

Air-gapped AI coding agent in one Rust binary + Q56, a hidden-test benchmark for local coding models: 16 configs, 36 full runs, no LLM judge. Runs entirely on your own hardware through Ollama or LM Studio. No cloud brain. No API key. No telemetry.

High-performance Holographic Memory System (HMS) for Node.js, powered by Rust. This library implements Vector Symbolic Architectures (VSA) using Binary Spatter Code (BSC) to enable semantic search, analogical reasoning, and associative memory at scale.

A wizard style software project idea launcher. Use at project launch (sprint 0) with the /sprint-loops protocol (https://github.com/crussella0129/sprint-loops)

Self-hosted, OpenAI-compatible LLM gateway that turns any backend into an agent. Point an OpenAI SDK at it and the model runs tools mid-completion. From web search, code sandbox, document rendering, RAG, MCP connectors all behind a built-in chat UI. Multi-backend routing with health checks + failover, OIDC + RBAC, per-user tokens.

Open-source operating environment for autonomous AI agents, with cross-platform machine control, oversight, and multi-host federation.

🔐 本地加密密钥管理 CLI——AES-256-GCM 纯本地存储，AI 只能拿到别名注入，永远看不到明文。

小白也能上手的 Claude Code / Codex 上游配置切换桌面应用 | A cross-platform, site-driven desktop app for switching Claude Code & Codex providers

A systems language designed so an AI agent can safely write and run backend code: proven no GC/races/overflow, GBNF-constrained generation, structured diagnostics, OS-process sandboxing.

Elegant web interface for agentive development.

AI agents should not make irreversible changes. TraceFold escrows the inverse before an effect lands, or refuses it, and issues receipts anyone can verify offline.

RAM efficient terminal agent harness for coding, cybersecurity, and automation.

AI-powered code guardian — static analysis that watches your entire codebase

Multi-repo agentic orchestration that learns from every run

High-performance local AI inference engine.