Havuz

StealthBench is a benchmark for evaluating whether autonomous agents operate with the operational security (OPSEC) discipline that separates

Package manager for AI-agent config. grim installs, updates, and publishes skills, rules, agents, MCP servers, and bundles into Claude Code,

Coding agent harness, achieved SWE Bench Lite resolve rate of 52.4%

Your AI agents, always on, working together. Claude Code, Antigravity and Codex on your own computer.

Deepy - Vibe coding for DeepSeek models in your terminal

Native iPhone companion for self-hosted Hermes, with a private authenticated mobile bridge.

BotScript - A TypeScript superset for the LLM era

Agent skill for writing and reviewing Swift WidgetKit code: timeline providers, configurations, families, accented/tinted rendering, interac

agent skill 的生产环境自进化系统 | A production self-evolving system for agent skills: every installed skill keeps accumulating evidence from real usa

Agent Usage Detail Record — an open JSON standard for attributing and costing agent runs

Orchestration of autonomous, collaborative AI agents in Go — an idiomatic Go port of CrewAI.

AI agent team that takes an idea from research to launch, built on opencode. No framework, no extra dependencies.

Local, provider-agnostic agentic hub: an orchestrator and a squad of little monsters on your machine

Logic programming for AI agents: Datalog-family language compiling to optimized SQL

Multi-agent workflow orchestrator with MCP tool servers: planner/executor agents, tool-use loop, MCP client/server, tracing and durable runs

AiGuard —— 本地优先的 AI 流量安全网关：本机 MITM 代理只接管 AI 域名，请求侧脱敏、响应侧流式还原，并识别七类风险信号。原文不落盘、不上传。（注意如果你需要模型直接使用token或者其他密钥进行操作，请放入白名单或关闭该功能！！！！）

The IDE for your coding agents. Use Claude Code, Codex, or any CLI agent in a real workspace; files, editor, browser, and git, all agent-awa

Vinkius Open Data Initiative: The world's largest open-source database of Model Context Protocol (MCP) servers. Production-ready metadata co

Install Zapier in your coding agent via the Claude Code, Codex, and Copilot CLI marketplaces.

The autonomous SDLC for Claude Code that won't pass a gate on an unproven verdict.

Guardrails for the agent harness. Regulated data stays on your machine, and every prompt and tool call is scanned before it runs.

Learn your codebases through self-quizzing and study. Track your knowledge coverage over time.

Fold finished episodes out of pi's context, and recall, ask or fork them instead of compacting

A sample "Product Discovery Assistant" demonstrating how to build durable multi-agent workflows using AWS Step Functions, Amazon Bedrock Age

Snap a line before your agents build.

Orchestration under Claude Code on herdr: flows an agent cannot skip, jobs on a clock, threads with claims, and a forum agents search later

TypeScript AI agent runtime. Write your agents in code and choose how predictable they are: deterministic steps where they can be, an LLM on

AI remembers, you find. File-based long-term memory and project maps for any AI coding tool, plus a zero-dependency governance CLI for chang

AI agents and workflows for Kotlin Multiplatform, as small typed graphs: loops, parallel steps, streaming, save points and human approval. I

Pinax is a small Go CLI that crawls a public documentation site, indexes its structure, and exposes it to any Model Context Protocol client

Fast structured Android control loops with TypeSafe Jev and Mobile MCP

AI session risk summary. See what sensitive information is sitting in your local AI coding sessions. Runs locally, nothing leaves your machi

Correo electrónico, mensajes de texto y whatsapp GRATIS para Agentes IA. - Free Email, text messages, and whatsapp for IA Agents.

Self-hosted system for improving AI agents, by InferEdge

Counterfactual replay and causal attribution over LLM-agent trajectories: find which step actually caused a failure by intervening on it.

Run agents on a cloud machine. Steer them from your desktop or phone.

An agentic chief-of-staff OS for executives, built on Claude Code

Practical engineering knowledge for building and operating production AI systems — LLMs, RAG, agents, inference, evaluation, system design,

Local-first control plane for long-running and multi-agent AI systems. Observe, steer, recover and orchestrate agents.

TokenPack packs long documents, codebases, PDFs, and folders into compact, evidence-dense LLM context using local embeddings, evidence scori

MCP-compatible context and memory system: paged code navigation for AI assistants, plus a recorded, verified theory of what is known about t

Research into flattening compaction strategics

A graph-native, local-first agent harness and Linux desktop shell: a voice-driven Executive Agent, a reviewed knowledge graph, per-Agent mem

A minimal workflow DAG (Directed Acyclic Graph) definition language and an asynchronous execution engine, implemented in Python.

Your terminal on any browser and any device.

Give your agent capabilities, not giant tool walls.

Stellar MCP server for AI agents: one authenticated gateway to official docs, live ecosystem data, community intel, and tested playbooks.

Unofficial self-hosted Cloudflare OS Home with Docker Compose, project-local LiteLLM, Tailscale, and an agent-first runtime.

Claude Code Skills, Agents & Plugins — UitKit

Publish HTML for agents — one API call, MCP server included