OpenHarness is an open-source framework for building general-purpose AI agents programmatically. Built on Vercel’s AI SDK, it provides the building blocks inspired by Claude Code, Codex, and similar advanced agent harnesses — but in a lightweight, composable form you can use in your own applications.Documentation Index
Fetch the complete documentation index at: https://docs.open-harness.dev/llms.txt
Use this file to discover all available pages before exploring further.
Why OpenHarness?
Agent harnesses like Claude Code, Codex, and OpenCode are powerful general-purpose agents. While their creators offer SDKs (Claude Agent SDK, Codex App Server, etc.), these are heavy to use programmatically. OpenHarness gives you the same building blocks — multi-step tool loops, subagent delegation, context compaction, streaming UI integration — as composable primitives you control entirely in code.Key Features
Stateless Agents
Agents are pure executors: pass in history, get back events. Full control over conversation state.
Composable Middleware
Add compaction, retry, persistence, and hooks as independent, composable layers.
Subagent Delegation
Agents can spawn child agents for subtasks, with configurable nesting depth and background execution.
Provider Abstraction
Filesystem and shell access through swappable providers — run locally, in sandboxes, or in the cloud.
MCP Integration
Connect to Model Context Protocol servers for external tools via stdio, HTTP, or SSE transports.
AI SDK 5 UI Streaming
Stream agent sessions directly to React or Vue chat UIs with typed data parts.