A transactional execution harness for AI coding agents with evidence-backed reports.
Stable application runtime and operator control plane for agent workspaces.
Deep Agents - a library for building controllable AI agents with LangGraph
GitHub Copilot CLI brings the power of Copilot coding agent directly to your terminal.
Core TypeScript SDK for Agent Relay communication. The SDK gives agents and applications three public capabilities: messaging, delivery, and actions.
Bounded iterative assistant-turn runtime for Agent Assistant SDK
`frontend-harness` is a context and evidence policy layer for frontend teams using Codex or Claude Code.
The core test runtime that executes on React Native devices, providing Jest-compatible APIs (describe, it, expect) and managing test collection, execution, and result reporting in native environments.
LangGraph
OpenClaw wrapper for Riddle Proof evidence-backed agent changes.
Node-based harness for test262
Embeddable AI agent infrastructure — execution, sessions, tools, skills, dispatch, tracing
CLI for roy-agent - Non-interactive command execution
Built-in agent-core runtime and tool surface for Babysitter.
Mock harness simulator for testing agent-mux adapters — simulates claude-code, codex, and other CLI harnesses
Company-style AI agent harness for Claude and Codex. Installs commands, CXX agents, skills, HR-Resource hiring pool, and project-local .harness runtime state.
Turn-scoped context assembly for Agent Assistant SDK
Workspace runtime for multi-agent applications
Generic agent harness — domain-agnostic loop strategies + LLM provider abstraction. Source for both @agent-devtools and external SaaS consumers.