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
The original 'AI software engineer': a cloud VM agent that plans, codes, tests and opens PRs from Slack/web/API, now spanning a whole product line (Devin cloud, Devin Desktop nee Windsurf, CLI) with ACU consumption billing ($2.00-2.25/ACU, Core $20 entry, Team $500/mo) and Cognition's own SWE-1.6 model alongside frontier models.
Anthropic's cloud-hosted Claude Code at claude.ai/code: each session gets an isolated Anthropic-managed VM with the GitHub repo cloned and limited default network access, supports parallel steerable sessions across repos with automatic PR creation, sessions persist after browser close and are monitorable from the Claude mobile app; bundled with Pro/Max/Team/Enterprise plans (research preview).
Cursor's fire-and-forget mode (formerly Background Agents): agents run in isolated cloud Ubuntu VMs — since Feb 2026 with a full desktop and browser for 'computer use' UI verification — clone the repo onto their own branch, work multi-repo in parallel, report back to the IDE/web/Slack/Teams/iOS app, and open PRs, with Dockerfile-configurable environments, scoped secrets, and a headless Background Agent API.
AWS's fully managed, configuration-defined agent harness (GA June 17, 2026): two API calls (CreateHarness/InvokeHarness) stand up an agent with its own isolated session environment, filesystem and shell, cross-session memory, a curated skills catalog, and web browsing, running any Bedrock, OpenAI, Gemini, or LiteLLM-compatible model with mid-session provider switching and no separate harness charge.