$ 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

3 of 74 harnesses · sorted by stars

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

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

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