agent-evaluation

forsy-trace-skill

Python

62

Open skill for capturing AI agent work as structured traces.

llm-space

TypeScript

95

A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for managed agents.

better-harness

JavaScript

95

An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, inspect evidence, and compare outcomes.

FrontierAgent

Python

90

🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.

RealReplicaBench

HTML

82

CommerceAgentBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online Services

bindwidth

JavaScript

72

Evidence-aware on-prem LLM inference sizing and TCO calculator

agent-rules-books

72

AGENTS.md rules / skills for AI coding agents: Codex, Cursor & Claude Code. Inspired by Clean Code, Refactoring, DDD, Clean Architecture and DDIA programming books.

waku-agent

Python

90

Waku Waku! Waku Agent is a local-first AI agent harness you actually own, including loop, memory, eval, all in code built to stay legible as it grows.

agent-apprenticeship

Python

72

The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

agent-apprenticeship

Python

72

The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

agent-skills

Python

92

Useful skills for agents and claws.

agent-as-a-router

TypeScript

67

The official implementations of Agent-as-a-Router: Agentic Model Routing for Coding Tasks.

awesome-gamedev-agent-skills

Python

82

67 game-dev skills for AI coding agents — Godot, Unity, Unreal, Phaser, PixiJS, three.js, Bevy, pygame, LÖVE, Roblox. Portable SKILL.md Agent Skills (the format Anthropic launched as Claude Skills), with a router that loads the right skill for your engine and task. Runs in Claude Code, Cursor, Kiro, Codex, Copilot, Gemini CLI and more.

hermes-agent

Python

90

The agent that grows with you

fullstack-agent

Batchfile

75

Give your AI a full stack: memory, voice, face, and hands. This is the "I want an AI agent" shortcut. It sets up the entire jaredrhod stack for you with an installation wizard. Select which pieces you want or do it all!

launch-your-agent

HTML

75

Claude Code skills that take a founder from idea to a live Claude Managed Agent: interview, scope a v0, launch in their own account, grade it, iterate, and schedule it

skills

Python

90

Public repository for Agent Skills

ponytail

JavaScript

100

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

ragflow

Go

95

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

omnigent

Python

85

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

trueforge

TypeScript

90

The open-source agent harness - the runtime layer that turns an LLM into a working agent.

devspace

TypeScript

85

Minimal Coding Agent Harness over MCP for ChatGPT, Claude, Hermes, Grok Bot, OpenClaw

maka

TypeScript

90

Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and termination events are recorded as an append-only log.

loopy

JavaScript

85

A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

loop-library

JavaScript

85

A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

AgentsMesh

Go

95

The AI Agent Workforce Platform. Run a hundred AI coding agents across your own machines — schedule, isolate, and steer them all from one console.

delegate-skills

JavaScript

95

Delegate a coding task to a separate coding agent CLI, review the diff, land the commit yourself — one per implementer.

OpenChatCut

TypeScript

90

Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.

threejs-game-skills

Python

80

Agent skills for building playable, polished Three.js browser games with gameplay, AAA-style graphics, UI, QA, and optional AI-generated 3D, image, and audio assets.

numbat

Go

85

Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.

autoprompt-skill

JavaScript

72

Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.

looper

Python

77

Design visual, review-gated agent loops for Claude Code before you run them.

Browser-BC

TypeScript

62

Agent behavior clone for browser using, targeting general GUI using and distributed trajectory collecting.

good-question

PowerShell

67

A portable agent skill for sharpening research questions.

nopus

TypeScript

72

Deterministic prose checks for clearer coding-agent responses

lazyskills

Go

72

mission control for agent skills

whathappened

72

Agent skill: adaptive X-only briefing of what happened + public opinion + debates

marketing-studio

JavaScript

72

Agent-driven marketing studio for Claude Code: one /marketing command renders your product's full launch asset suite (logo reveal, demo, launch video, social clips, OG assets)

loop.js

TypeScript

58

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

Jixu

TypeScript

68

Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

optim-plans

Python

58

Human-in-the-loop planning plugin for Claude and Codex: turn ideas into reviewed Markdown plans, record decisions, enforce explicit execution gates, and provide tested controller primitives for safer agent workflows.

ECC

JavaScript

100

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

claw-code

Rust

100

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

langchain

Python

100

The agent engineering platform.

pi

TypeScript

100

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

openbot

TypeScript

95

Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.

cumora

TypeScript

95

Where agent teams gather. Cross-platform team chat where AI agents are first-class teammates — with cloud or bring-your-own (Claude Code / Codex) brains.

fx

Zig

90

Unix like coding agent