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
MIT-licensed self-hosted personal AI assistant ('the lobster way') that exploded to ~382k GitHub stars in months: any model, 20+ messaging channels (WhatsApp/Telegram/Slack/iMessage...), SKILL.md skills via ClawHub, Docker-sandboxed sessions, cron jobs, voice, and a live Canvas.
Nous Research's MIT-licensed 'self-improving' server-resident agent (Feb 2026, ~211k stars): model-agnostic with persistent cross-session memory, autonomous skill creation compatible with the agentskills.io standard, DSPy/GEPA evolutionary self-optimization, and execution backends from local/Docker to Modal and Daytona.
OpenAI's built-in agent mode that absorbed Operator and Deep Research: a cloud virtual computer with browser, terminal, and connectors that researches, fills forms, and edits files, pausing for user approval on consequential actions and handing back control for logins/payments.
Anthropic's non-technical desktop agent built on the Claude Code harness (no terminal required) that works over local folders, browsers (Claude in Chrome), and full computer use, with MCP connectors, Agent Skills, and plugins — expanded to web and mobile in July 2026 with cloud-run sessions for Max subscribers.
Google's successor lineage to Project Mariner (shut down as a standalone May 2026): Gemini Agent plus the I/O 2026 'Gemini Spark', a 24/7 always-on personal agent on dedicated cloud machines with deep Gmail/Workspace integration, MCP tool support, and check-before-acting guardrails, gated to AI Ultra ($100/mo) beta.