Havuz

The official FastMCP TypeScript library for building MCP servers, clients, and apps 🏎️ 🏎️ 🏎️

Can LLM/MARL agents coordinate in long-horizon, open-ended tasks? NeurIPS 2026 (Evaluations and Datasets).

Declarative automation for repetitive steps in herdr

Effect building blocks for agentic ai

A minimal and extensible agent server for building agent applications

Agent Office — pixel floor for Hermes + OpenCode + Telegram sessions

Write, validate, and review Agent SKILL.md's directly in Visual Studio Code. SKILL.md Inspector provides live diagnostics for every file na

Your agents. Your workspace. Your control—from prompt to commit, desktop to mobile. Works with Codex, Claude Code, OpenCode, Pi, Grok, DeepS

Desktop automation CLI for AI agents. Fast native Rust CLI.

A fast, native desktop reader for Open Knowledge Format bundles. Point it at a folder to explore concepts, follow links, and see the structu

AI agents are increasingly given real-world power — moving money, executing trades, taking actions with no human in the loop. But autonomy w

A compounding knowledge base maintained by LLM agents — inspired by Karpathy's LLM Wiki pattern

Unofficial Google-Health-CLI for the Google Health API, written in Go

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

最终的 MCP | Terminus MCP

"Multi-Agent Team — 让31位导演大师成为你的AI创作团队"

Hands-on LangChain learning repository covering Chat Models, Prompt Templates, Chains, RAG, Agents, and Tools with practical Python examples

Schedule Claude Code, Codex, Grok and Gemini like cron jobs — on your machine, with no API keys.

Axon reads the logs your AI coding-agent harnesses already write — Claude Code, Codex, OpenCode — and shows which harness, project, agent, a

One command turns every agent session already on your disk into a graph: subagents, tool calls, retries, the moments you said no. Ask your a

Open-source terminal AI coding-agent harness for studying agent loops, tools, MCP, skills, safety, and persistence.

The open-source talent graph for humans and AI agents.

Open-source always on personal agent with its own computer. It remembers your work and keeps going while you're away. Works with any model.

TERSE - a hierarchical state language for humans and AI agents.

基于pi agent core构建的harness agent

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

A battle-tested, framework-agnostic reference architecture for Claude Code. Beginner-friendly with graduated adoption (minimal / standard /

Type-aware, evidence-backed delivery contract for AI coding harnesses. Different agents in. One predictable human handoff out.

Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter jo

A mysterious multi-agent swarm framework summoned by TAW Agent from 1971 to help you craft a better future towards 2133 & beyond. Ankh.md is

Simple and composable logging for Swift apps, servers, and coding agents.

Contacts for Claws

Apple Silicon mlx with Zero Dependency Java

SkillRoute by JEStats — local-first skill routing for coding agents, with ranked matches, confidence, and evidence over MCP.

Skills for running, porting, profiling, and tuning code on Intel CPUs, GPUs, and the libraries and runtimes behind them.

Official Repo for Spreadsheet-RL

Introducing Muse Glimmer: open-weight 30B agentic multimodal model that runs on your device (Meta). Interactive local agent lab + guide. Apa

ZeroSpec is a zero-dependency Markdown framework that helps AI agents understand your repository structure, rules, and source of truth befor

🔬 Discover questions in the data; test explanations against the results.

Turn Claude Code into a senior software architect that orchestrates a team of specialist agents and audits itself. An 8-phase skill with TDD

An intelligence layer grounding autonomous agents in verified, real-time knowledge at scale.

Drop-in replacement for PostgreSQL with surgical, dependency-aware undo of transactions. Makes incident recovery zero-cortisol.

Prove your agent skills work before you ship them.

Tool-to-Agent Protocol: tools can be smart without embedded LLM calls.

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

Keep growing TypeScript codebases maintainable. Trellis measures complexity, duplication, and import cycles, pinpoints structural debt, and

Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at

Agent Skills official site

An LLM-friendly, single-binary, drop-in replacement to Supabase