Rust agents

Your own personal AI assistant. But with security by design. Support for numerous operating systems. Any platform.

OpenAI Dive is an unofficial async Rust library that allows you to interact with the OpenAI API.

A headless browser for AI agents that fetches modern web pages, runs JavaScript, manages sessions, and returns token-efficient Markdown.

Open-source bridge to use Kimi AI inside Cursor. Connect Kimi models to your AI coding workflow with fast setup, clean configuration, and reliable local tooling for code generation, refactoring, debugging, and agentic development.

The official Rust library for the Edgee AI Gateway

遵循harness原则，长时运行agent任务的框架，集成pi-rs

Open-Source Platform for Subagents and Agent Teams. Long-running, collaborative, proactive.

Agent Sessions is a desktop app for managing multiple AI agent sessions at once, written in Rust.

Open Source Agent Execution

Multi-agent (path finding) planning framework

EdgeCrab 🦀 A Super Powerful Personal Assistant inspired by NousHermes and OpenClaw — Rust-native, blazing-fast terminal UI, ReAct tool loop, multi-provider LLM support, ACP protocol, gateway adapters, and built-in security hardening.

Libra is evolving into an AI agent–native version control tools

the governed runtime for agent skill workflows, off the leash but on the record

High-performance capability authorization engine for AI agents. Cryptographically attenuated warrants, task-scoped authority, verifiable offline. Rust core.

Single CLI to monitor LLM provider usage across Codex, Claude, Gemini, Cursor, and Copilot: remaining quota, rate limits, and cost tracking in one place

The environment engine for agent worktrees - zero-config dep sync + port/DB/compose isolation

Agent and LLM API performance monitoring via network packet probe. Measures performance of OpenClaw, Claude, Codex, DeepAgents and more — deployed on the provider side, no SDK changes required.

AI agent relay station

Token-efficient navigation substrate for AI coding agents. Index code once and retrieve only the symbols you need.

Parallel, isolated dev environments for humans and AI coding agents. Real containers. Real databases. Zero collisions.

The first verifiably private cloud AI assistant. Runs in AWS Nitro Enclave with hardware attestation - nobody can access user data, not even the developer. Bridges WhatsApp, Telegram, Signal, email to SMS for dumbphone users.

Open-source AI agent runtime built in Rust. Define once, deploy isolated instances per tenant with built-in memory, encrypted vault, self-extending skills, cron, and multi-channel support.

OpenAI Codex CLI session log viewer for JSONL files in ~/.codex/sessions. Browse conversations, tool calls, tokens, collaboration chains, and live sessions on desktop and web.

Isolated Linux desktop workspaces for AI agents — a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work without touching your real desktop.

Fast local-first Rust CLI for codebase metrics, AST-compressed LLM context bundles, and built-in MCP server.

Falco-powered policy and visibility layer for AI coding agents

cli deep research tool using ollama (AI agent to reseach complexe query online)

Rust-based FAST local markdown search engine (with possible support for CJK)

Fast, interruptible verification browser for AI coding agents: 35 ms checks, pixel diffs, live human hand-off

A collection of software tools to aid myself (and optionally others) in improved agentic ai development

Git-backed long-term memory for AI coding agents

Self-evolving AI agent in Rust. Single binary, 10 LLM providers, 30+ tools, 17 platform adapters. Zero dependencies.

Interactive testing CLI for Tauri v2 apps : lets AI agents inspect, interact with, and debug Tauri applications in real-time

Open-source agent sandbox infrastructure for parallel coding agents: isolated workspaces, MCP/CLI control, observability, and atomic publication.

🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Gated DeltaNet + sparse attention, fine-grained MoE, native video/document understanding, long-horizon tool agents, quantization-aware training. Scales: Tiny (25M) to Large (1.3B).

Metrik 是一款桌面常驻工具，统一查看本机各个 AI 编程 Agent 的官方配额余量与 Token 消耗，支持 ChatGPT、Claude、GLM、Kimi 等主流 Agent。

OpenAI SDK

🦀 Open-source alternative to Claude Code, built from scratch in Rust. Agentic coding CLI — thinks, plans, and executes with any LLM. Compatible with Claude Code workflows.

OpenPawz is a native, offline-first desktop AI platform (Tauri v2 + Rust) that lets you run local models or connect to any compatible provider. It gives you private-by-default agents with hybrid memory, strong security guardrails, and extensibility through built-ins plus n8n community integrations

Reflex - The instant, code-aware local search engine.

Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.

Stealth headless browser engine in Rust — native BoringSSL TLS/JA4 fingerprint, real JS via deno_core, no Chromium, no CDP. Python + MCP bindings. A camoufox alternative.

A hypervisor and sandbox cloud for self-hosting AI agents and RL

Cognitive memory for AI agents. Pure Rust, <1ms recall, 2.7MB, zero cloud. Patent Pending.

AI-powered repository agent for GitHub, GitLab, Gitea, Azure DevOps. Issue triage, PR analysis, merge queue, notifications, dashboard, backup. Self-hosted, multi-provider.

Mnemosyne is a agentic memory and orchestration system designed to provide Claude Code with persistent semantic memory across sessions.

A tiny Rust gateway for running coding agents across model providers safely.

Cognitive memory for AI agents. Pure Rust, <1ms recall, 2.7MB, zero cloud. Patent Pending.

Govrix Scout — AI Agent Governance Diagnostic Tool (OSS)

The missing human checkpoint for AI coding agents. Give your AI agent a "pause & ask" button — review, correct, or enrich every step before it runs.

Fluent is a self-improving software factory. It autonomously turns your team's vision, ideas, bug reports, user feedback, production logs, and agent traces into working software.

A self-evolving AI coding agent for long-running, complex software engineering.

A fast codebase indexer and knowledge wiki for AI agents.

🧠 A native graph-based memory system for autonomous AI agents, featuring bio-inspired sleep-based memory consolidation and powered by KIP & AndaDB.

One contract for execution governance across every stack, every team, and every AI agent.

A secure and efficient gateway for interacting with OpenAI's API, featuring load balancing, user request handling without individual API keys, and global access control.

Rust client for t3.chat access Claude Fable-5, GPT-5.6, Gemini 3.5, Grok 4.3, DeepSeek V4 & 50+ frontier AI models from your terminal. TLS impersonation, credit tracking, usage billing.

3-level security toolkit for AI agents: regex patterns, heuristic rules, ML classification. Claude Code hooks, git pre-commit, CI/CD scanner.

Planr turns product intent into a durable task graph that Codex, Claude Code, Cursor, MCP clients, and humans can share without losing ownership or evidence.

Run linux commands with natural language. Eg.: "show my graphic card" instead "lspci | grep VGA"

A unified web extraction and stateful automation engine for AI. Replaces heavy testing frameworks with token-optimized browser control, deep research, and HITL.

🔗🤖 Build multi-tenant AI agents that execute secure blockchain operations across Solana and EVM networks

A Rust library designed to facilitate the conversion of various document formats into markdown text.

Multi-repo semantic code search MCP server in Rust — hybrid vector + BM25 retrieval, tree-sitter AST chunking, fully offline. For OpenCode, Claude Code, Cursor, and any MCP client.

A terminal interface for Nanocodex

Full-configuration CLI for Codex Micro and Work Louder Input: profiles, layers, keymaps, actions, provider handoff, verified apply, and rollback.

Rust executable for Refact Agent, it lives inside your IDE and keeps AST and VecDB indexes up to date, offers agentic tools for an AI model to call. Yes, it works as a LSP server from IDE point of view.

rizzler: stop crying over Git merge conflicts and let AI handle the drama

Rust runtime with TS/Python bindings for Claude Skills with progressive disclosure of skill metadata, full content and scripts/resources. Any agent can now own skills. Currently support Seatbelt and experimentally, WASM, sandboxing

The first SSH client built for AI agents. Let Claude Code, Codex, and other CLI agents manage your servers through MCP skills. Beautiful UI, native performance.

AI gateway and observability server written in Rust. Designed to help optimize multi-agent workflows.

Live view of your AI agents at work.

[EXPERIMENTAL] Eidetica-Native AI Agent framework

A self-hosted AI agent daemon built in Rust. Runs on your machine, talks through Telegram, Discord, Slack, Email and Matrix. Fully local with Ollama or powered by any of 12 cloud providers. Execute commands, capture media, schedule tasks, browse the web , all from a chat message.

semantic search for your local files find by meaning, not keywords. 120+ file types, OCR, MCP server for AI agents. 100% private.

Claude's missing better half — a companion tool for Claude Code usage.

Ares is an autonomous security operations platform where LLM-driven red and blue team agents operate against each other on live infrastructure, enabling realistic evaluation of attack and defense.

Universal memory runtime for AI agents

Agentic runtime in Rust — persistent, supervised agents. Self-hosted, local-first, zero telemetry. Apache 2.0.

Self-extending autonomous agent in one Rust binary. One-line install, any provider (OpenAI-compatible, Anthropic, xAI) or fully local via llama.cpp, live /evolve self-modification, MCP, messaging gateway, built-in bench

Shinkai allows you to create AI agents without touching code. Define tasks, schedule actions, and let Shinkai write custom code for you. Native crypto support included.

Mobile control plane for AI agents. Rust + GPUI + QUIC. Available on iOS/Android

An editor for teams of local coding agents (Claude Code, Codex, and friends)

🌿 StoryMoss (草苔) — AI导演式小说创作系统。Tauri+Rust驱动的桌面写作软件，集成知识图谱、伏笔追踪、StyleDNA风格引擎、协同编辑、7阶段全自动创作工作流。让AI成为你的创作搭档，越写越懂你。

Terminal pixel-art office for AI coding agents — watch your Claude Code sessions type, walk, and nap in a coworking lounge. Half-block rendering, A* pathfinding, per-tool monitor glow. Pure Rust, runs over SSH.

Libra is evolving into an AI agent–native version control tools

The code quality toolkit for the agentic AI era. Find dead code, clones, and scaffolding across 15 languages. MCP server + CLI.

A GPUI based diff viewer and Codex orchestrator for vibe engineering

Agentic IDE with custom harness

Lightweight, secure Linux sandboxes for untrusted processes. Runs in the browser and on the server.

Fast search engine on object storage, with full text search, vectors, and SQL, natively on Parquet.

A rust implementation of ELIZA - a natural language processing program developed by Joseph Weizenbaum in 1966.

AI Agent Kernel for Edge/IoT — 5-layer Rust runtime with 6 LLM providers

TUI dashboard for managing AI coding agents (Claude Code, OpenCode, Codex CLI, Gemini CLI) in tmux

Secure on device personal agents

A self-hosted AI companion web app with anime-style Live2D and VRM characters. Talk with your companion via text or voice — they respond with expressive facial animations, lip-synced speech, and per-sentence emotional reactions.

A high-performance Rust implementation of the Hermes-Agent orchestration loop for LLM-driven tool execution.

The living armor an AI agent inhabits: eternal devouring, eternal evolution, eternal amplification.