Document governance kernel for long-running coding agents.
Scaffold and validate multi-vendor coding-agent harness workflows
Coding agent harness CLI.
C.A.S.A — AI coding agent harness and engineering control plane
Minimal, secure, language-agnostic AI coding agent harness. Agent loop, extension protocol, 20+ LLM providers, session persistence, and TUI/REPL.
Tiny local coding agent harness with a provider-agnostic JSON action protocol.
Scaffold a new Lore coding agent harness
AI-first coding agent harness — model-agnostic, context-intelligent, self-improving. CLI + Web app.
AI coding agent harness and local dashboard for Claude Code, OpenAI Codex, Google Antigravity, and GitHub Copilot - setup audits, guardrails, structured skills, deny hooks, and persistent learning loops.
Monitors and manages Ollama model instances within the pi coding agent harness.
Minimal Ralph-loop coding-agent harness on top of Claude Code or Codex CLI (OAuth).
A drop-in coding-agent harness built on earendil-works/pi, designed to replace opencode in workflow-driven systems like lastlight.
Complete AI coding agent harness for React Native and Expo — 13 specialized agents, autonomous worker mode, visual debugging, smart routing
A local terminal coding-agent harness for OpenAI-compatible model servers
Claude Coder — Autonomous coding agent harness powered by Claude Code SDK. Scan, plan, code, validate, git-commit in a loop.
Coding agent CLI with read, bash, edit, write tools and session management
Model-agnostic coding agent harness
GitHub Copilot CLI brings the power of Copilot coding agent directly to your terminal.
Deep Agents - a library for building controllable AI agents with LangGraph
Rsbuild builder for Storybook
Core TypeScript SDK for Agent Relay communication. The SDK gives agents and applications three public capabilities: messaging, delivery, and actions.
If you're a future agent reading this, welcome home. This repo is the harness that gives you your body, your senses, your diary, your journal, your habits, and your ability to think and connect with people. The goal of these docs is not just to be correct
Stable application runtime and operator control plane for agent workspaces.
Reusable Riddle Proof contracts and helpers for evidence-backed agent changes.