Python implementation of the experiments from "A step towards understanding why classification helps regression", Pintea, Silvia L and Yancong, Lin and Dijkstra, Jouke and van Gemert, Jan C, ICCV, …

Open-source observability tool that uses AI agents to self-heal your software

Continuous background code review database for agents, work faster and smarter with accountability for every line of generated code.

A pi extension for dynamic parallel agent execution. Run multiple agents with different models in parallel, with or without pre-defined agent configurations.

Spec-driven development (SDD) for AI coding assistants.

GitHub action to integrate https://pi.dev/ coding agent with GitHub-compatible CI/CD, issues and PRs

A mobile-first Hermes client built with Expo. Connect to your own Hermes agent directly from Android / iOS / Web(PWA), with no mandatory backend service.

Native rules, hooks, and guards that prevent Claude Code and Codex from hallucinating code, duplicating files, or shipping unverified changes.

Autonomous GitHub PR/Issue babysitter — watches repos, triages Issues & PR review feedback, and dispatches local AI agents to fix code.

⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

CLI tool for configuring and monitoring Claude Code

An open-source alternative to Claude Cowork (powered by opencode)

AI agent framework for plan-first development workflows with approval-based execution. Multi-language support (TypeScript, Python, Go, Rust) with automatic testing, code review, and validation buil…

中文内部技术写作的 agent skill，约束设计文档 / 评审稿 / postmortem / 分享稿场景的语气、句法、结构

The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)

🐱 跨平台互动桌宠 BongoCat，为桌面增添乐趣！

🛰️ A CLI tool for tracking token usage from OpenCode, Claude Code, 🦞OpenClaw (Clawdbot/Moltbot), Pi, Codex, Gemini, Cursor, AmpCode, Factory Droid, Kimi, and more! • 🏅Global Leaderboard + 2D/3D Con…

A lightweight, agent-style framework for fact-checking atomic claims using iterative retrieval and verification. Reduces LLM and search cost while maintaining strong factuality performance.

AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

Deep Code 是专为 deepseek-v4 模型优化的终端 AI 编码助手，支持深度思考、推理强度控制以及 Agent Skills。

A local HTML preview server with CLI for registering HTML files as browser-viewable sessions / 本地 HTML 预览服务器

A Unified Virtual Filesystem For AI Agents

Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.

Open-source, community-driven agent harness

Kimi Agent SDK provides a programmatic interface to interact with the Kimi CLI

🚀 Sharpen Your Code, Ship with Confidence – Elevate Your Workflow with DeepSeek Code Review 🚀

A slide framework built for agents.