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.
OpenAI's delegation-first coding agent whose cloud mode runs each task in an isolated no-internet-by-default sandbox with the repo cloned, opens PRs, does automatic PR code review on GitHub and takes tasks from ChatGPT/Slack, bundled into ChatGPT Plus/Pro/Business with rolling credit-based billing since April 2026 (the CLI companion is open source, the cloud service is not).
GitHub's fully autonomous background worker: assign it a GitHub Issue and it works in a GitHub Actions-powered sandbox and delivers a draft PR, with MCP server support, custom .agent.md agents, agentic code review that hands fixes back to the agent, and (since Feb 2026) the ability to assign the same issue to Claude, Codex and Copilot simultaneously and pick the best PR; available on Pro through Enterprise with AI-credit billing from June 2026.
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.
Always-on 'daemon' agents defined in Markdown files that work proactively across GitHub, Linear and Slack without prompts — reviewing PRs, opening fix PRs, triaging bugs, syncing docs — positioned as the follow-through layer that keeps work moving after other coding agents create it; runs on Charlie's V2 durable runtime with worker orchestration and a devbox that includes a real Playwright browser for validating UI flows before opening a PR.
Enterprise-focused 'Droids' platform ($1.5B valuation after April 2026 Series C): autonomous agents that execute refactors, migrations and incident investigations end-to-end across CLI, desktop, SDK and remote 'Droid Computers' cloud workloads, with both local and cloud background agents on the $20 Pro tier and adoption at Nvidia, Adobe, Morgan Stanley and MongoDB; notably model-agnostic across frontier providers.