Rust agents

CodeGraph MCP - Give persistent learning to your coding agent for a codebase across teams & token saving superpower to the coding agent

Tasks for planning - enhanced with Hiveminds for multi-model reviews, Swarms for long running autonomous tasks. Nurse to keep things running!

MCP server for the Linux desktop 🐧🤖

The data layer for AI with Vector, Graph and Vector-Math built into one single rust engine

Open re-implementation of Claude Code's built-in Dynamic Workflow: a script-driven runner for agent-authored JavaScript workflows — agent(), parallel(), pipeline(), token budgets, git-worktree isolation, deterministic resume — plus pandacode, a pluggable executor for codex, claude, and domestic LLMs. Auto offline HTML execution-graph reports.

Fast, offline code search and code intelligence for LLM agents.

Cross-platform AI companion port of OpenClicky for Windows, Linux, and macOS.

A Rust framework for building LLM applications with support for 8+ LLM providers, agents, RAG, BM25/hybrid search, LangGraph workflows, and multiple vector/document storage backends.

chew through any source into clean datasets! a fast ingestion, RAG & fine-tuning toolkit

muxel is a GPUI-native multiplexer for coding agents

a human-like, self-evolving, self-cleaned AI memory system for LLM

A lightweight, portable executable for invoking LLM with multi-API support - eliminating installation requirements while maintaining operational efficiency. 轻量级大语言模型api调用工具，无需安装，仅一个~10M可执行文件，支持自定义多种模型（OpenAI、Claude、Gemini、DeepSeek等，以及第三方提供的api）和prompt。

WMB-100K — The first 100,000-turn benchmark for AI memory systems

🤖 Your Agents' personal email 📧

Local-first AI agent mesh in Rust. Hard budget enforcement, adaptive model routing, and end-to-end OpenTDF encryption. Built for individuals and small teams.

Deterministic context database for AI agents. Same query → same context, every time.

Local-first CLI to read, compare, and hand off sessions across Claude Code, Codex, Gemini, and Cursor agents. Checkpoints, cross-agent messaging, zero npm deps.

A four-layer Retrieval-Augmented Generation (RAG) engine in Rust with SMT-based logic verification and knowledge graph support.

Compress logs for LLM analysis — Rust-powered, Python API. 40-60% token savings.

Bones for your agents — composable async agentic AI framework for Rust

MCP server in Rust for AI agent persistent memory: branch-aware session handoffs, local ONNX embeddings, SQLite-backed semantic search.

Bamboo — a local-first AI agent harness & runtime in Rust. Persistent memory, 22 built-in tools, skills, MCP, sub-agents, workflows & schedules behind one HTTP + WebSocket API. Embed it as a crate, or run it as a server.

Not a framework. A file format for agent-to-agent handoffs — provenance, parallel safety, and human visibility by design. Model-agnostic. Framework-agnostic. Open spec, MPL-2.0.

Rusty inference library using various backends including llama.cpp

Deterministic authorization + tamper-evident audit for AI agents, humans, and workloads — one principal type, safety invariants machine-checked by an SMT solver (cvc5), every decision independently verifiable offline. Pure Rust.

Framework-agnostic, local-first memory lifecycle for AI agents: Rust CLI, SQLite/FTS recall, forgetting, audit, consolidation, DOX/Revolve adapters, and TUI.

Shepherd is an end-to-end AI Software Engineering platform that supervises the complete software delivery lifecycle—not just code generation, but planning, execution, testing, regression, governance, deployment, and continuous knowledge growth.｜Shepherd 将 AI 的一次性交付，转化为组织的长期软件工程资产。

A universal git-native AI agent framework — written in Rust. Single binary. Zero dependencies. 383 models. Blazing fast.

Production-grade LLM client - Rust, Python, TypeScript. 100+ providers, 11,000+ models.

macOS desktop connector for OpenClaw: securely bridge remote agents to your local machine via SSH tunnel and local browser CDP.

Skill-first AI coding agent in Rust — injects only the context your task needs. No prompt bloat. Single binary, no runtime.

融合数据平台

The only AI stack nestled on a biodiverse agentic kernel framework

Token Oriented Object Notation (TOON) for Linked Data

🌱 Guided Indexing Kernel [Experimental]

Agent-agnostic context, tracking, and cost analytics for AI-assisted development. Curated docs · Session tracking · Cost analytics · Team knowledge — all git-native

An AI-powered desktop coding workspace for planning, coding, debugging, review, and testing through multi-agent orchestration and shared blackboards.

Multi-model AI agent orchestrator. Run Claude, GPT, and Ollama agents in one workspace with group chat, smart routing, and per-agent model assignment.

A FUSE semantic filesystem for LLM/AI AgentsAgentic FUSE filesystem for LLM agents. Structured file operations with JSON feedback, audit logging, undo support, and semantic search.

MCP security scanner for Claude, Cursor, OpenAI Agents, LangGraph and CrewAI - offline Rust SAST with SARIF for GitHub Code Scanning

Strip LLM writing patterns from prose, code comments, and commits — CLI, Claude Code skill, Cursor rule, and LLM system prompt.

High-performance Rust LLM gateway implementing the Open Responses API. Unified access to OpenAI, Anthropic, Google, Mistral, Ollama, HuggingFace, and AWS Bedrock with cost tracking, prompt compression, smart routing, and encrypted credentials.

Persistent visual memory for AI agents — capture screenshots, embed with CLIP ViT-B/32, compare, recall. MCP server + Rust core library.

A lightweight Rust library for building LLM agents.

Local Rust codegraph and verifiable workflow for AI coding agents — project maps, change and test impact, MCP queries, and diff-backed implementation audits.

Build production AI agent runtimes in Rust with typed tools, provider-neutral LLM adapters, streaming, storage, and observability.

Real-time LLM token and cost monitor with TLS-intercepting proxy or HTTP relay; cross-platform with macOS status bar app and browser dashboard

Pure-Rust DWG -> multipage PNG renderer + lossless position-referenced text layer & metadata indexer for RAG/VLM ingestion of CAD drawings

Self-hosted Rust LLM API gateway with OpenAI-compatible and Anthropic-compatible APIs, model routing, multi-tenant keys, usage tracking, billing, and admin console.

Production-shaped boilerplate for AI agent web apps: Rust/Axum API, Python LangChain + Celery workers, Vue 3 SPA. Hexagonal architecture, TDD, JWT + refresh rotation, reliable job lifecycle with retries, rate limiting, structured logs, Docker & CI/CD

Apache-2.0, model-agnostic macOS agent: bring your own model to deliver verified code, docs, slides, and computer actions.

Kiro API Gateway · Anthropic-compatible proxy for Kiro/AWS Q · Multi-account pool · Admin UI · Claude Code compatible

`my-little-soda` is a CLI tool that turns your repo's GitHub Issues into the task pipeline for your AI coding agents

Self-hosted Rust LLM gateway for the Rabbit R1. WebSocket streaming, sandboxed Python agents, OpenAI / Anthropic / OpenAI-compatible providers.

Terminal-based AI coding assistant with Claude/OpenAI support, secure local tools, web search, and MCP integrations.

OpenClaw reborn in Rust — single-binary AI agent that remembers you.

Local-first, privacy-first AI agent with recursive self-improvement

Air-gapped Linux VM on your Mac for running Open Claw and other AI agents

A ~3MB MCP daemon that exposes any script as a tool for Claude, Cursor & AI assistants

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

Schema-validated binary data for AI agents. JSON → .grm compiler with zero-copy FlatBuffers.

High-performance HTML to Markdown converter with full GitHub Flavored Markdown support. Written in Rust, available for Node.js and as a native Rust crate.

An infinite canvas for Claude Code, Codex, OpenCode with separate workspaces.

Sevorix Lite is a Rust-native, open-source runtime containment engine for autonomous AI agents.

🐝 Run a swarm of AI agents: one architect plans, many workers execute. Parallel AI development.

It only takes minutes to turn business specs into production-ready APIs with built-in auth, DB, and compliance.

Agent Cow: the philosophical watcher of your agents across multiple machines.

Flight Levels work management with MCP server integration for AI agents. CLI, TUI, and GUI interfaces.

AI tab completion with customizable context

Any storage. Any agent. One CLI

Fullstack chatbot built using Rust. Made using Candle, Leptos, Actix, Tokio and Tailwind. Uses quantized Mistral 7B Instruct v0.1 GGUF models.

A GPT-powered daily newsletter bot, written in Rust

AI companion with soul, memory, and autonomous inner life

🤖 Native AI agent for your terminal and macOS desktop. Run cloud and local models through one secure runtime.

Turn any web page into traceable, citable evidence for AI agents.

Spec-driven development (SDD) for agents, all in a docker-like interface with your own custom workflows.

The Identity Platform for the AI Agent Era. Secure humans, machines, and AI agents with a unified Rust-based platform.

A compiled template and script language for LLM orchestration

A multi-provider LLM framework for Rust.

DF Embedder is a high-performance Python library (with a Rust backend) for indexing and embedding Apache Arrow compatible DataFrames (like Polars or Pandas) into low latency vector databases based on Lance files.

🦀 Production-grade Rust rewrite of Claude Code. 42 native tools, multi-provider, 100% parity.

No longer maintained.

Fix broken AI agents without re-running them. Fork at any step, replay from failure, prove the fix works. Works alongside Langfuse/LangSmith or standalone.

PhantomEar is a privacy-first, local-only AI meeting assistant that runs invisibly on your machine. No bots, No cloud recording, No admin permissions.

Deterministic, scriptable CLI and live TUI for Planka kanban — built for shell scripts, CI/CD, and AI agents.

A daemon for discord bot with multiple agent.

Unit tests for AI agents

Semantic grep for codebases — tree-sitter chunking, vector search, shared via Git orphan branch

⚡ Vectro: Lightning-fast embedding quantization. Hit 12M+ vec/s throughput (4.85× faster than FAISS C++) while drastically cutting memory footprint for vector databases and local AI research.

Proactive developer agent with tape memory, tool orchestration, and multi-channel interfaces

Self-hostable runtime for persistent autonomous coding agents — KVM-isolated VMs (or rootless containers), A2A-protocol executor with signed AgentCard discovery, AIWG mission dispatch, web dashboard, virtiofs shared storage. Runs on your hardware; no hosted control plane.

A general-purpose program orchestrator.

AI-powered git commit rewriter, PR generator, and MCP server for Jira, Confluence, and Datadog. Single Rust binary.

MCP server for BookStack — 56 tools covering the full API + semantic vector search. Rust/tokio/axum, dual transport (SSE + Streamable HTTP), OAuth 2.1, pluggable DB (SQLite/PostgreSQL+pgvector).

Opus-led Claude Code agent team — strategist plans, Sonnet runners read and fix. Live two-way review-and-fix pipeline. Zero API calls. NOW IN RUST!

Local desktop dashboard for Claude Code. Reads your JSONL transcripts and surfaces per-prompt cost, tool heatmaps, subagent attribution, cache analytics, and a rule-based tips engine. Rust + Tauri, fully offline, MIT.

Tray-resident, read-only git glance for the AI-agent era. Wink at recent commits across all your repos.

Run multiple CLI coding agents (Claude Code, Codex, Gemini, OpenCode) as a coordinated team, on a Loop. Local-first, file-based coordination, full PTY, no telemetry.