Rust agents

Build and manage AI agents within git repositories using a Rust-based, dependency-free framework that version-controls agent identity, rules, and tools.

A high-performance, developer-centric agentic runtime built in Rust.

Manage project.md files using a single CLI tool to track tasks and coordinate work between humans and AI agents without databases or external services.

A typed language for AI agents — author in Nebula, ship as Python. Rust compiler + JSON toolchain.

Private, local-first AI workspace for macOS, Windows & Linux. Bring your own model (Claude/GPT/Gemini) or run fully offline with Ollama. Consented file/shell/web tools, chart & table artifacts, and focused apps like Personal Finance. No cloud account, no telemetry.

Tiny local coding CLI

Nexus: Autonomous AI agent platform combining OpenClaw's channel breadth with Hermes Agent's learning loop — plus graph memory, DID identity, privacy-as-config, and zero-API-key demo mode. Rust + Go.Please contribute to unlock the next era of agentic AI.

🔍 Enable real-time exploration of GitHub repositories with this high-performance Model Context Protocol (MCP) server built in Rust.

Ultra-fast codebase cartography for LLMs

Deterministic code intelligence engine — compiler-grade symbol, call-graph, and CFG extraction from LLVM IR, Java bytecode, and tree-sitter. SQLiteGraph-backed graph store for grounded LLM coding workflows.

Rust CLI that merges files/dirs into one XML or text output for fast LLM context or general aggregation, with filters, optional tree, and clipboard support.

CLI tool to verify OpenAI-compatible model deployments — check tool-call and reasoning support

🌐 Build high-performance web sensing and browser automation tools with ReasonKit Web, a Rust-native implementation for efficient solutions.

Локальный модуль машинного зрения для LLM-агентов на чистом Rust: метрический 3D scene-graph каждый кадр, MCP-сервер, $0/CPU/приватно

Let AI coding agents (Claude, Codex, Pi) see and control your Bevy game - remote input injection, screenshots, and frame-synced feedback over a simple JSON-lines TCP protocol.

ai built in os mainly on rust with some hint of c c++ assembly

An agentic development environment for Julia: AI agents drive a keyboard-driven TUI + REPL to read, run, and surface code — and coordinate across sessions and machines.

A private AI assistant that lives in your terminal. Fully on-device, no account, no telemetry.

Desktop AI assistant overlay with DeepSeek-optimized reasoning, long-term memory, skill/equipment self-evolution, Chrome CDP browser automation, and task tracking. Built in Rust with wry WebView.

MCP server for Bareos backup system. Query your backups via your favorite AI assistant

Menu-bar app: PDFs, Office & images → clean Markdown on your Mac. Offline, local, no API keys.

Personal autonomous AI agent runtime in Rust. Multi-channel (Telegram, terminal, HTTP), background task handling, persistent memory, tool orchestration.

An event-sourced runtime for AI agents that survives kill -9, written in Rust.

Детерминированная агентная архитектура: спецификации, ADR, roadmap и скелет реализации (Rust + TypeScript bootstrap)

AI desktop guide that shows you where to click — it observes, never clicks. Free tier (no sign-up), BYOK or local Ollama, source-available.

A personal assistant that runs on your own machine, does real work on it, and writes itself new abilities when the ones it has are not enough.

A Rust agent SDK, harness, and coding agent — safe by construction (non-bypassable authorization → approval → guarded IO).

The official Rust library for the Steel API

A statically typed language and compiler for AI agents. Write once, verify statically, compile to a portable Agent IR.

A local-first AI coding workspace with approvals, diffs, quotas, and optional model delegation.

adversarial security scanning and testing for MCP servers and agentic tool surfaces.

官方 DeepSeek Harness（dsh）原生桌面壳：Tauri 2 把官方 WebUI 变成原生桌面窗口，保留会话/工作区/插件/技能。内置 SenseVoice 离线语音输入、插件市场、视觉模型配置；锚定模式解决 DeepSeek 思考模式问题

Run models that do not fit in your RAM. Keeps the always-read weights resident, streams the routed experts from disk.

Lightweight, SID-aligned, TMF-compliant BSS for terminal-first operation. LLM-native. eSIM-first.

Aios — Artificially Intelligent Operating System. An AI-native operating environment where no component both decides and executes.

A safety layer for AI agents; it decides what your agent is allowed to do - and proves it.

Native Rust whole-codebase analysis for AI agents.

Capable coding agents on local Ollama models — including the small ones. Task-based model routing, tolerant tool-call parsing, and an auditable permission system.

Z3-powered reasoning for AI agents. MCP server + CLI for scheduling, logic, config, and safety.

A local, user-controlled safety boundary for AI-powered automation.

A personal assistant that runs on your own machine, does real work on it, and writes itself new abilities when the ones it has are not enough.

Understand a local media file (image/video/audio) from the command line — transcript + structured description as one JSON envelope, via an agentic CLI backend (agy/claude/codex).

A fast Rust tool for harvesting source files as Markdown and copying them to your clipboard.

Autonomous terminal coding agent - Rust, ratatui TUI, OpenAI-compatible providers

Context broker for AI coding agents (CLI + MCP). Queries codebases via progressive disclosure instead of feeding entire files into context — reducing token waste and context rot. AST-aware retrieval, surgical editing with syntax guard, semantic search. Inspired by Recursive Language Models research (MIT/Stanford, 2025). Built in Rust.

Declarative test-case management: git-native case files, agent execution, human review gate

A zbus-style message bus that keeps external integrations out of the OpenHuman kernel's dependency graph.

Stateless Model Context Protocol (MCP) server for Fastly Compute — an edge-native, WebAssembly reference implementation of the 2026-07-28 spec.

A local CLI for logging predictions before the outcome and checking whether your "80% sure" comes true 80% of the time.

Codex CLI is the best agent harness, but it’s locked to OpenAI. Pyxis won’t be.

Ardur — open-source personal AI agent. Lives in your terminal and across your messaging channels. Multi-provider LLM access, tool use, memory, plugins, with cap-token security, receipt-chain transparency, and cost-tuple awareness built in.

FastRMCP: The high-level, ergonomic, and production-focused framework for building Model Context Protocol (MCP) servers in Rust. Inspired by FastMCP and FastAPI.

Long-term memory for AI agents. MCP server with local embeddings, heat-based recall, and hierarchical clustering on embedded SurrealDB.

A programming language designed for AI agents

Rust powered, self hosting team of agents each with its email, shared organization and agent memory, shared tools and skills. GrokBot or Buzz idea but with decentralized email access, BYOK and regular OAuth social login.

Lossless, on-device token-cost reduction for Claude Code and LLM coding agents. Free plugin: compresses tool-result output, dedups context, compacts the system prompt — stacks on Anthropic prompt caching. Rust hot path, Python fallback, fail-open. PolyForm Noncommercial.

Voice-first AI assistant in Rust. Wake word, full-duplex speech with barge-in, hybrid local/cloud inference. Currently the voice loop: openWakeWord to Silero VAD to Whisper to streaming Claude to Piper TTS.

Natural language → optimized AI context window. Tell it what to build, get exactly the files an LLM needs, trimmed to fit, in seconds.

Self-hosted AI agent harness in Rust, built for long tasks: a virtual session keeps work coherent across context compaction & restarts. Telegram/Discord, durable queues, fail-closed permissions, Codex/OpenRouter routing, a JSONL receipt for every step. 6 deps, no async runtime, Windows-first.

An agentic OBD-II scanner that never makes anything up. Bring your own model, read every module on the bus, and click any number to see the raw bytes behind it.

A real GTO solver, packaged as an LLM agent skill. Heads-up NLHE CFR+ with precomputed flop/turn tables and on-demand subgame solvers, accessed through a single `poker` CLI.

Run local LLMs on limited VRAM safely. Dynamic model sharing and OpenAI API drop-in replacement.

A typed language for LLM agent systems on BEAM: effect-row tracking, auditable tool effects, typed actors, and OTP supervision, queryable by agents over MCP.

The coding agent built for local models. One native binary for your terminal that finds the model your local server has loaded, and tells you whether that model can actually drive tools.

An opinionated loop based automations written in rust

One key press, one action, one card. A lightweight Windows 11 tray assistant behind the Copilot key that looks at your screen and helps, with cloud or local (Ollama) models.