The open-source agent harness - the runtime layer that turns an LLM into a working agent.
-
Updated
Sep 8, 2026 - TypeScript
The open-source agent harness - the runtime layer that turns an LLM into a working agent.
AI development toolkit for Claude Code — ideate, auto-resolve, and ship with context engineering and agent orchestration
Your Company Agentic Operating System
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
Node.js TypeScript CLI for discovering, staging, activating, and wiring reusable AI-agent assets across VS Code/Copilot, OpenCode, Cursor, Zed, Claude Code, and Pi.
面向 Codex 的开源 Harness Engineering 工作流、Skills 与可恢复配置工具
45 skills, 3 agents and a sensor harness for Claude Code — research, plan, ship and verify solo projects across 13 stacks
Open-source agentic data engineering harness for dbt, SQL, and cloud warehouses. 100+ tools, 10 warehouses, AI-powered.
An omni-plugin for harness engineering workflows with multi-agents, programmatic gates and skills.
a CLI-like agent app helps vibe coding/spec-like coding,chat,write and other interesting thing.
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
Web console for OpenBKN — build, manage, and collaborate on business knowledge networks. React + TypeScript frontend for the platform's admin UIs and workspaces.
The batteries-included agent harness.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, human oversight, and end-to-end verification.
OpenCode++: a Coding Agent Reliability Harness for OpenCode, adding context, edit boundaries, command evidence, verification gates, impact analysis, and repair loops.OpenCode++:面向 OpenCode 的 AI 编程可靠性增强框架,为其增加上下文管理、编辑边界、命令证据、验证门禁、影响分析与修复闭环能力。
AI coding agent CLI with built-in CodeGraph-powered impact analysis and propagation audit, harness tooling, native-agent experience, and tailored adapters for Kimi and DeepSeek.
An all-in-one local AI Agent workspace with a fully self-developed stack
To associate your repository with the harness-engineering topic, visit your repo's landing page and select "manage topics."