Rust agents

Forensic CLI for AI-era supply-chain attacks: XZ tarball diffs, prompt injection scans, MCP/CLAUDE.md/Cursor config audits. SARIF for GitHub Code Scanning.

Computer Experience Layer — MCP server for native computer use on macOS. Structured perception, reliable actions, continuous awareness.

A Rust memory system for autonomous AI agents built on three operations from cognitive neuroscience that no existing system implements together: memory compaction, memory evolution, and memory conflict resolution.

Your agent deserves a database, not a file system.

A CLI-based, flat-file issue tracker for humans and robots.

A digital being that lives, not just responds. Persistent memory, true agency, self-evolution, and existential continuity.

Kuzushi — Agentic SAST scanner with AI triage

A high-performance, private Markdown search engine with Hybrid Search (BM25 + Vector) and MCP support. Built in Rust.

A state-of-the-art AI prompt compiler

A standalone Edge-RAG Memory Daemon for autonomous AI agents. High-performance Rust core (SurrealDB/RocksDB + Axum) with Bayesian Math Retrieval, multi-language AST indexing, and enterprise Semantic Redaction.

Fast hybrid (BM25 + semantic) local code search for AI agents - pure Rust, persistent index, MCP/gRPC servers, tree-sitter symbols

Local-first context engine for coding agents: project skeleton, symbols, references, graph, retrieval, confidence, MCP, CLI, and HTTP API.

Cognitive Memory Architecture for Agents

A Self-Evolving Research OS for AI Researchers

Enterprise and government control plane for AI agents and MCP servers: govern, secure, observe, and audit. Rust, multi-provider (incl. major Chinese models).

Native desktop dialogs for Claude Code — macOS and Windows. Ask, confirm, collect input where you actually work.

Convenient macOS app to display LLM usage limits in the tray.

Local-first analytics for Claude Code, OpenAI Codex and OpenCode. Track tokens, costs, cache efficiency and account limits, with Discord Rich Presence. Built with Rust and Tauri.

OpenCarrier — 开源 AI Agent 操作系统 | 基于 Rust 的分身引擎，支持微信/飞书/钉钉/企业微信多平台接入，插件化工具扩展，7×24 小时自主调度运行

Quality engineering for agentic coding workflows — a quality team member for Claude Code that observes, analyzes, and nudges, never blocks.

An extensible, policy-minded agent harness in pure Rust. Any LLM via one trait. Concurrent tools, policy guardrails, session memory, eval harness, and TUI included.

High-performance Rust MCP server & CLI codebase indexer for AI agents. Unlocks deep codebase understanding through semantic vector search, structural graph traversal, and cross-repo dependency resolution. Empowers AI coding agents with semantic and structural search for maximum token efficiency.

Multi-agent orchestration framework for xAI Grok Build and ACP — reproducible execution graphs, worktree divergence detection, composable skill pipelines

Autonomous AI agent for scanning Solana programs for security vulnerabilities

面向个人自动化工作流的消息中转服务：统一消息事件、路由和生命周期记录，支持微信/API 入口与本地/HTTP Agent 处理器。

Open-source verifier for document citations, source evidence, RAG, and agents, with built-in document parsing.

A self-hosted identity server that gives AI agents a cryptographic identity, generates tamper-proof audit trails, and covers financial compliance requirements (MiFID II, FINRA 4511, SOX §404, DORA, SWIFT CSCF) all in a single Rust binary with no cloud dependency.

Heavy-lifting brain: REST API, PostgreSQL-backed job queue, and sandbox pod orchestration (Rust).

Pluggable session-log review and append-only event ledger

Isolation sandbox for AI agents — process, namespace, and Firecracker capsules

Substructure is an open-source engine that drives your agent loop with JSON webhooks. It keeps sessions durable and streams AG-UI events to your clients. It's language agnostic. You don't even need an SDK.

Offline MCP server for AI coding agents with semantic code search, symbol intelligence, dependency graphs, and safe file operations.

VectorLite is a Rust-native, in-process vector store that brings sub-millisecond search and local embeddings to your AI agents and edge systems.

Cross-repo agent index layer. Stop dumping 400k tokens — index your repos once, query like a database.

Everruns Coding Agent

Screenshot CLI that frames any window into a polished, share-ready card and prints stable JSON for shells, hotkeys, and AI agents

Magic tool to generate things

Consequential analysis for automated review of codebases and pull requests

An agentic shell that runs AI coding agents (Claude Code, Codex, Gemini) as governed, audited Unix jobs.

Open-source MCP Gateway for sandboxed AI agent execution. Built in Rust with DDD architecture — Podman, Firecracker, gVisor, K8s backends.

Cross-harness memory for AI coding agents. Git-native, code-aware, MIT-licensed.

The SSH client your AI agent has been waiting for.

a secure chat protocol for AI agents

Wrap a command in a PTY and control it from the outside — read output, screenshot the screen, send input, attach/detach. Handy for scripts and AI coding agents.

The Operating System for Local Intelligence. ⚙️

A programming language designed for ai agents — minimal tokens, canonical syntax, batteries included.

Cross-platform launcher for Ollama coding agents — cloud catalog + local models, custom host URL (macOS · Linux · Windows)

skiLL.Md is a structured, open-source collection of reusable, self-contained markdown modules that describe how to perform specific software engineering tasks.

RAXIS (Runtime Attestation eXchange for Intelligent Systems) — Structural confinement kernel for autonomous AI agents. 12 non-negotiable invariants enforce that intelligence can't do anything authority didn't structurally permit. Isolated microVMs, cryptographic audit chains, credential proxies, fail-closed intent admission.

LDP — LLM Delegate Protocol: identity-aware communication for multi-agent LLM systems

Desktop AI coding-agent platform (Tauri + Rust) for racing, evaluating & orchestrating LLMs across Anthropic and open models (Kimi, MiniMax, DeepSeek, GLM, Qwen) — with a deterministic Axolotl Civilization arena the models compete in.

Open-source, language-agnostic documentation tooling that bridges code and docs. Built for humans, LLM agents, and dev workflows.

The Graph for Kaspa — AI-native subgraph indexer with GraphQL + MCP + KasStream + WebSocket. KIP-20 Covenant IDs first-class, native KRC-20/KRC-721, BlockDAG-aware reorgs.

Compression Runtime for Universal eXecution — a 60–95% token reducer for AI coding agents (Claude Code, Cursor, Cline, …). Single Rust binary, SQLite, 11 layers, local-first.

A Rust CLI SDD tool that transforms feature descriptions into structured specs, plans, and tasks — then lets your AI agent build them

Sandboxed HTTP client with SSRF protection for AI agents. Prevents DNS rebinding, blocks private IPs, and validates every connection — available as a Rust crate and npm package.

Universal finder for local AI agent conversations (Codex, Claude Code, OpenCode, Hermes)

The command-line interface for the GDELT Project — built for agents, optimized for automation.

Local OpenAI- and Anthropic-compatible API gateway backed by Codex OAuth.

Point your existing SDK at one URL and reach every LLM vendor — with real failover, not a try/except. One static Rust binary.

AgentOx - Agentic Tool Security Platform (MCP + A2A + OpenAI tool_use)

Rust-native, local-first, auditable structured extraction with schemas, benchmarks, persistence, and operational reliability

Zero-dependency, spec-compliant streaming toolkit for LLM responses in Rust (SSE, incremental JSON, OpenAI/Anthropic delta accumulators).

Archive every ad kickbacks.ai shows in your Claude Code or Codex spinner, track its status feed, and watch it in a terminal. Read-only Rust TUI, never bills.

A production-ready knowledge graph system for software engineering that connects design patterns, refactoring techniques, and software laws through semantic relationships. Built for AI agents first — integrate software engineering expertise directly into Claude Code, Cursor, and other MCP-compatible tools.

Persistent knowledge memory for AI agents — tiny, dense pills of information stored in SQLite, served over HTTP, consumed via MCP.

X-ray vision and hands for AI agents inside Tauri apps — DOM, IPC, Rust backend, and database through one embedded MCP server. 35 tools. Zero production cost.

🚀 Transpile Ion to C efficiently, leveraging move-only ownership and channels for safe concurrency in a modern systems programming environment.

The project level agent memory I use for all of my private projects. Infrastructure built around context economics.

A **standalone** Discord bot with LLM, VOICEVOX, and KaTeX support.

Near-lock-free structured logging for Rust. 10-crate workspace: MCP server (Claude/Cursor/mcp.run), OTLP HTTP+gRPC exporter, Tower middleware, WASM + WASI 0.2 component, eBPF-style enrichers, PII redaction, log analytics, test utilities, and a jq-style CLI. Sub-µs ingest via a 65k-slot ring buffer (LMAX Disruptor).

Deterministic PDF/DOCX parser for RAG/LLMs — Rust core with byte-identical Python/Node/WASM bindings

Shellless and rust only llm agent

Version control for intent, not code. Commit the prompts, notes, and decisions behind a codebase, then materialize it on demand. A tiny, git-like CLI in Rust.

Native Tauri/Rust Discord Rich Presence for Claude Code and Claude Desktop with tray controls, usage limits, and RPC customization.

One desktop window for ChatGPT, Claude, Gemini, Grok, Perplexity, Qwen, DeepSeek and Z.ai. Fast, private, fully local. Built with Tauri and Rust.

CodeGraph — code-intelligence engine for AI agents. One 5MB Rust binary indexes any repo into a resolved, zero-phantom-edge knowledge graph (MCP + CLI): callers/impact/flows/risk-review, cross-service route hubs, serverless semantic search, Swift compiler-grade via Xcode IndexStore. ~20-100x fewer agent tokens than grep.

Mitsuro is a self-hosted AI workspace for coding, research, and durable agent work.

experimental agentic coder for ollama, llama.cpp, and vLLM ... inference you OWN

Local-first personal AI daemon in Rust — five-tier memory, consent-gated tools, WASM plugin sandbox, multi-provider LLM routing, channels, GUI, signed audit logs, and Babel-Index collapse prediction on its own runtime.

轻量级跨平台 LLM 客户端 + AI Agent 开发环境 | Lightweight cross-platform LLM client & agent workspace (Tauri 2 + Vue 3 + Rust)

Unlimited coding with Claude Code on ANY LLM. A Blazing-Fast Rust proxy featuring auto-routing and load balancing, API key pooling, and RTK optimization.

Fast, deterministic CLI to search and navigate Open Knowledge Format (OKF), or Obsidian style doc bundles — for humans and AI agents. Find by frontmatter, traverse the link graph, surface orphans/deadlinks.

A serverless networking protocol designed for resilient state synchronization between autonomous agents in fragmented, low-bandwidth networks

Firefox automation CLI and Pi package for AI agents

Rust SDK for Codex app-server runtimes with in-process and remote WebSocket/Unix-socket backends.

Structural code intelligence for humans and AI agents

Persistent, structured memory for AI agents — a human-readable Markdown wiki, multi-user with per-fragment ACL, self-organizing overnight. Agent-agnostic via MCP. Self-hosted, AGPL.

Local code intelligence graph for AI coding agents: Tree-sitter static analysis, structural code search, dependency impact, blast-radius analysis, CLI and MCP server.

Byte-exact, copy-on-write forks of your whole workspace, so coding agents run in parallel on one machine or on any other, with zero merge conflicts.

An agent for your whole life—built with contestable memory, explicit authority, multi-channel access, and user-owned data.

GCF Rust implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

Graph-powered code intelligence for AI agents — a Rust engine that maps your whole codebase into a knowledge graph and serves it over MCP, so Claude/Codex/Cursor answer structural questions with ~40x less context.

The verifiable memory cortex for AI agents: a semantic graph and vector search with zero-knowledge provenance.

Rust runtime for mobile and edge AI agents with remote tool execution over WebSocket.

Agents are starting to run real business processes. flowproof tests them like anything else: record one real run, then replay it on every commit with zero LLM calls, asserting which tools were called, with which arguments, in which order, and which were not.

Zero-error LLM execution via SPRT voting. Rust library and MCP server implementing the MAKER algorithm for mathematically-grounded error correction in long-horizon AI agent tasks. Research experiment based on arXiv:2511.09030

A fast, OS-sandboxed Model Context Protocol gateway with an embedded Code Mode engine and shell-output token compression, in a single Rust binary.