$ find your agent harness

A curated, verified, cross-vendor directory of AI agent harnesses — the runtime scaffolding that turns a model into an agent.

74 harnesses profiled · 9-axis capability schema · last verified 2026-07-08

7 of 74 harnesses · sorted by stars

browser-use · Browser Use Inc. (YC-backed, SF)

103,000 · high

MIT-licensed Python library (103k stars) that lets any LLM drive a real Chrome browser via DOM+vision instead of brittle selectors, now flanked by a desktop app and a usage-based cloud with stealth browsers, proxies, and a 24/7 'Browser Use Box' agent.

General / computer-useopen-sourcebyok✓ mcp✓ local modelsoptional

Goose · Block → Agentic AI Foundation (Linux Foundation)

50,812 · high

Block's Rust-built, Apache-2.0 general engineering agent — now stewarded by the Linux Foundation's Agentic AI Foundation — distinguished by the deepest MCP integration in the ecosystem (70+ extensions, can also act as an MCP server) and shareable YAML 'Recipes' that scaled agent workflows to 60% of Block.

OSS coding harnessesopen-sourcebyok✓ mcp✓ skills✓ local models

smolagents · Hugging Face

28,242 · high

Hugging Face's minimalist (~1,000-line core, Apache 2.0) 'agents that think in code' harness where the model writes executable Python as its action format instead of JSON tool calls, model-agnostic via transformers/Ollama/LiteLLM, with optional sandboxed execution (E2B, Docker, WebAssembly), managed sub-agents, and Hub sharing of tools and agents.

Runtimes & SDKsopen-sourcebyok✓ mcp✓ local modelsoptional

GPT Researcher · Assaf Elovic / open-source community (gptr.dev)

28,100 · high

The original open deep-research harness (Apache-2.0, 28k stars): a planner/executor multi-agent pipeline that fans out parallel web and local-document searches into cited reports, with recursive tree-like 'Deep Research', MCP data-source integration, and any-LLM support.

General / computer-useopen-sourcebyok✓ mcp✓ local models

Deep Agents SDK · LangChain

25,902 · high

LangChain's self-described 'batteries-included agent harness' (GA March 2026, ~26k stars) for long-running tasks, layering planning via write_todos, a virtual filesystem for context offloading, SKILL.md-compatible skills with progressive disclosure, subagent spawning, and LangGraph-store-backed long-term memory on top of the LangGraph runtime.

Runtimes & SDKsopen-sourcebyok✓ mcp✓ skills✓ local modelsoptional

Pydantic AI · Pydantic Services Inc.

18,266 · high

MIT-licensed, type-safe Python agent framework from the Pydantic team with a FastAPI-like developer experience: schema-validated structured outputs, first-class MCP support, built-in OpenTelemetry observability (pairs with Logfire), and durable execution via native Temporal/DBOS integrations that offload model requests, tool calls, and MCP communication to fault-tolerant activities.

Runtimes & SDKsopen-sourcebyok✓ mcp✓ local modelsoptional

The AutoGen + Semantic Kernel convergence (1.0 GA April 2026) for .NET and Python, whose BUILD 2026 'Agent Harness' made production patterns first-class — shell/filesystem access, human-in-the-loop approvals, context compaction, todo tracking, plan/execute modes, AgentSkillsProvider skill discovery, and BackgroundAgentsProvider subagents — with hosted execution via Microsoft Foundry.

Runtimes & SDKsopen-sourcebyok✓ mcp✓ skills✓ local modelsoptional
harnesses.sh — the agent harness directory