$ 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

OpenHands · All Hands AI / OpenHands

79,895 · high

Formerly OpenDevin, the leading open-source autonomous software-engineering platform: Docker-sandboxed agents that write code, run commands, browse, and open PRs, with a production agent SDK hitting 72% on SWE-bench Verified (Claude Sonnet 4.5) and its own broader OpenHands Index benchmark launched Jan 2026.

OSS coding harnessesopen-sourcefreemium✓ mcp✓ skills✓ local modelscontainer

CrewAI · CrewAI Inc.

55,117 · high

MIT-licensed Python framework (~55k stars) for role-based multi-agent 'Crews' plus event-driven 'Flows', with unified memory, hierarchical delegation, and a commercial AMP cloud platform (free tier, Pro from ~$25/mo, enterprise) that CrewAI says powered ~2B agentic executions in the year to January 2026.

Runtimes & SDKsopen-sourcefreemium✓ mcp✓ local modelsoptional

Mastra · Mastra (Gatsby founders)

25,927 · high

The leading TypeScript agent framework (Apache 2.0 core since July 2025; some enterprise features commercial) offering agents, type-safe workflows with suspend/resume human-in-the-loop, memory, a unified router to 3,300+ models across ~94 providers, guardrails/scorers/tracing, Mastra Studio for interactive testing, and file-based agent definitions added July 2026.

Runtimes & SDKsopen-sourcefreemium✓ mcp✓ local models

Letta · Letta (formerly MemGPT, UC Berkeley spinout)

23,701 · high

Apache-2.0 platform for stateful agents descended from MemGPT, distinguished by tiered self-editing memory persisted in a database (core memory in-context, archival out-of-context) plus 2026 research on git-based 'Context Repositories' and memory-native RL; in 2026 the company is consolidating around Letta Code, an open, model-agnostic memory-first coding agent harness (LettaBot archived May 2026 and folded in as Channels).

Runtimes & SDKsopen-sourcefreemium✓ mcp✓ local modelsoptional

Amp · Sourcegraph

high

Sourcegraph's opinionated no-model-picker coding agent (CLI + VS Code extension), distinguished by curated multi-model design with specialized subagents (Oracle for reasoning, Librarian for library research), Toolboxes (UNIX-script custom tools), skills with bundled MCP servers, and an ad-supported free mode alongside zero-markup pay-as-you-go credits.

Vendor CLI agentsproprietaryfreemium✓ mcp✓ skills

Cursor (Agent mode) · Anysphere

high

VS Code-fork AI IDE whose Agent mode plus in-house Composer models, Background/Cloud Agents (isolated cloud VMs that report back as PRs), hooks, skills, and an agent SDK make it the most fully-built-out commercial agentic IDE; Composer 2 scored 61.7% on Terminal-Bench 2.0 and Composer 2.5 79.8% on SWE-bench Multilingual (SWE-bench Verified not reported).

IDE & desktopproprietaryfreemium✓ mcp✓ skillsoptional

Jules · Google

high

Google's asynchronous coding agent that clones your GitHub repo into a secure cloud VM, plans and executes tasks (bug fixes, tests) and returns PRs; free tier of 15 tasks/day with higher quotas bundled into Google AI Pro/Ultra, Gemini 3.1 Pro/3 Flash under the hood, curated MCP connections (Linear, Supabase, Neon, Context7) added Feb 2026 and an alpha REST API for Slack/Linear-driven automation.

Cloud / backgroundproprietaryfreemium✓ mcpvm
harnesses.sh — the agent harness directory