Small, test-first AI agent starter kit
Deep Agents - a library for building controllable AI agents with LangGraph
extracts CSS into separate files
Stable application runtime and operator control plane for agent workspaces.
AI SDK harness adapter for vitest-evals.
Core TypeScript SDK for Agent Relay communication. The SDK gives agents and applications three public capabilities: messaging, delivery, and actions.
Mock harness simulator for testing agent-mux adapters — simulates claude-code, codex, and other CLI harnesses
Workspace runtime for multi-agent applications
CLI scaffolding for multi-agent harness systems
Coding agent CLI with read, bash, edit, write tools and session management
GitHub Copilot CLI brings the power of Copilot coding agent directly to your terminal.
Unified MCP pipeline for recommend-page filtering and screening on Boss Zhipin
Portable multi-agent harness for .agents-based skills and workflows across Antigravity, Claude Code, Codex, OpenCode, and more
Lite lib to only support decimal add calculation
ACEHarness - Agent Centric Engineering Harness (From Cangjie Team)
CLI for Harness Engineering toolkit
No description provided.
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
Bounded iterative assistant-turn runtime for Agent Assistant SDK
Small, efficient encoding of SVG data URIs for CSS, HTML, etc.
Declarative control plane for agent harnesses — one YAML for grounding, tools, memory, and hooks.
Solo-dev harness engineering kit for Claude Code, with experimental Codex and Kiro CLI runtime rendering.
A local-first agentic system wrapping Ollama's API, borrowing architectural patterns from the Claude Code paper
Create an autonomous AI agent on XPR Network