Havuz

The first benchmark that asks code agents to build agents.

A living AI civilisation you can watch: tiny creatures discover, build, teach and pass knowledge on, with any LLM in their minds.

Draws the work in your beads trackers as trees, with what each agent is doing beside the bead it works. It also watches beads for whatever w

A local-first control layer for AI agents

Agent Skill that turns your coding agent into a keyboard firmware expert. Audits ZMK/QMK keymaps, tunes home row mods, makes trackballs laye

Red Team + Blue Team agents for Claude Code. Automated security auditing with ~100 lines of Markdown each.

The open source data science agent for Discord and Slack

Reference harness for the Big Finance benchmark of workflow-grounded financial-research questions

Runtime authorization for AI agents — Node.js SDK

Lighthouse for agents - score an agent run, then tell it how to get faster and cheaper.

A semantic layer for your data: archmax describes it, you sharpen it, agents query it.

Turn any supported coding-agent harness into a full game-dev studio - 55 specialized AI agents and 182 skills for Godot, Unity, Unreal, Thre

An open standard for push-based, verifiable communication between digital entities and agents that follow them.

Stack-agnostic agentic-programming workflow skills + documentation scaffold

An operating system for a growth team of Claude agents: a goal cascade, an experiment log that chases you, and the skills that run each step

Your agent sleeps. The event wakes it. Durable timers and event triggers that wake OpenCode sessions.

多功能 AI 编程助手 支持web/本地应用/bot接入 等

Universal OpenCode TUI sidebar for browsing provider agents and subagents

An agent / harness multiplexer that allows you to access your agents from any device and machine

Humanize browser automation for AI agents, QA tests, and demos. Playwright-first — record sessions to video or runnable tests, and drive it

a modern git UI - fresh take on ungit

自托管中国基金组合分析与风险管理工具 — 自动净值更新 / 收益与回撤 / AI 投顾 / 定投回测 / 基金筛选 / 分红检测 | Self-hosted China fund portfolio analyzer: auto NAV sync, returns/risk an

A token-spend profiler and cost-regression gate for AI agents.

Agentic coding scheduler, a Rust agent harness that runs background coding agents autonomously

Knack CLI: agent-friendly skill operations. Self-host on GitHub or use Knack Cloud.

Long-term memory for LLM apps that shows its work: dated facts, as-of answers, supersession, and receipts on every answer. Library, CLI, loc

20位天涯大神的多智能体决策系统，multi-agent team

Let an LLM write its own tools at runtime: parsed with acorn, versioned in SQLite, run in a supervised worker process

agent tui in a web gui

Praxis Policy Engine (PPE)

Multi-currency settlement MCP for AI agents. 32 tools over Sera Protocol's stablecoin FX rails. Open source.

Official implementation of “ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation”

Open-source alternative to LangGraph Platform for TypeScript — self-host your LangGraph.js agents behind the standard Agent Protocol API. Yo

Local-first desktop coding agent with BYOK, MCP, and OpenAI-compatible / Ollama hosts

Voice-first desktop assistant for Windows — talk to your PC and it works inside real apps, safely. By VORNEX.

Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.

Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit p

A full-stack AI assistant built on Amazon Bedrock AgentCore. This sample demonstrates how to build a feature-rich, self-hosted AI assistant

Public-safe Codex plugin-first preset system with agents, skills, examples, scripts, and a read-only dashboard.

TypeScript CLI: extract any coding-agent session (Claude Code, Codex, Pi) into a compact, verified, provenance-linked handoff another agent

No API keys required. Transform the native ChatGPT, Claude, and Gemini web interfaces into fully autonomous local coding agents.

Public source of the Dreadnode capabilities in app.dreadnode.io — agents, tools, skills, MCP servers, and workers.

Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior acro

Connect AI to your data. Your metrics, your rules.

Evolving what multimodal agents see and how they read it. Framework, ten reusable task skills, and paper resources.

⛴️ View installed agents, skills, commands from Claude Code

Multi-agent coding factory made fast.

Ask for the symbol, not the file. Token-efficient MCP server giving AI coding agents symbol-level reads of TS/JS, Rust, Python, Java, Go,

Doubt, until what remains is certain. An MCP server that recursively doubts every plan decision — grounding each in real evidence or asking

⚡ Fastest and lightweight harness for AI agents