The self-improving all channels AI agent. Self-healing. Fully autonomous. Single Rust binary.

Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency graphs, quality gates, and actor attribution. Schemas define what agents must produce — the server blocks the call if they don't. Works with any MCP-compatible client.

若爱 (IfAI) - 基于 Tauri 2.0 构建的跨平台 AI 代码编辑器 | A Cross-Platform AI Code Editor Built with Tauri 2.0

AI-powered development framework with task management, 41 agents, 83 skills, and MCP tools for Cursor, Claude Code, Gemini, Codex & OpenCode. File-based memory that survives across sessions.

Ostrom-compliant commons governance & development system for AI agents to assist building products from requirements to production & deployment.

Open-source framework for agent-native software. Rails for apps that build themselves - with a copilot inside.

Let's Qitos! A torch-like agent-native framework for researchers.

Compile CLAUDE.md into a lockfile, then enforce repo changes against it in local runs, staged diffs, or CI.

Racker is an experimental harness tool for provisioning and running operating system containers.

An architecture-level AI harness that compiles constraints and NFRs into explicit, reviewable architecture decisions. Combines a deterministic compiler, curated pattern registry, and agent workflow skills to drive approval, re-approval, and implementation against an architectural contract.

A minimal, composable AI agent harness framework in Python.

Unified AI agent configuration management for Codex, Claude, and Copilot by wild

Testing & Automation Framework in Lua

The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, memory, RAG and observability. Plug-and-play from chat UI to full agents.

Satoshi regression testing framework

HTTP mock server library

pair is the process layer for AI-assisted development. It gives your AI assistant the context, guidelines, and skills to work the way your team works.

Open-CoT is a model-agnostic cognitive control plane that standardizes the trusted contract between model output, harness/runtime enforcement, policy, delegation, tool execution, provenance, and audit.

Common node library that is implemented through the use of spur-ioc and bluebird promises.

Mongoose common extensions