$ 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

29 of 74 harnesses · sorted by stars

Claude Code (desktop app) · Anthropic

136,750 · high

Anthropic's Claude-only agent harness in native desktop form, redesigned April 14, 2026 around a multi-session sidebar for parallel agents across repos, with integrated terminal/editor/diff viewer, cloud-hosted 'Routines' that run on Anthropic infrastructure while your machine is off, and the ecosystem that originated Agent Skills, subagents, hooks, plugins, and the headless Agent SDK (repo is issue tracker/docs; stars 136,750).

IDE & desktopproprietarysubscription✓ mcp✓ skillsoptional

Claude Code · Anthropic

136,749 · high

Anthropic's terminal-native agentic coding tool and the category-defining harness, distinguished by its layered extensibility model (CLAUDE.md memory, Agent Skills, subagents, hooks, plugins, MCP) plus permission modes, checkpoints, and optional sandboxing, available from CLI/IDE/desktop/web with an Agent SDK for building on top.

Vendor CLI agentsproprietarysubscription✓ mcp✓ skillsoptional

GitHub Copilot CLI · GitHub (Microsoft)

10,921 · high

GitHub's terminal agent (GA February 2026) that brings the Copilot coding agent to the CLI, distinguished by deep GitHub.com integration (built-in GitHub MCP server, in-terminal Issues/PRs/Gists tabs), an Autopilot autonomous mode, custom .agent.md agents, multi-vendor model choice, and AI-credit-based billing.

Vendor CLI agentsproprietarysubscription✓ mcp

Kiro · AWS (Amazon)

3,980 · medium

AWS's Claude-powered agentic IDE (VS Code fork; launched internationally May 7, 2026 as the successor to Amazon Q Developer) whose signature is spec-driven development — generating requirements.md/design.md/tasks.md with EARS acceptance criteria before coding — plus event-driven agent hooks, steering files, AGENTS.md/Skills.md/MCP support, and 'Kiro Powers' pre-packaged AWS MCP servers; the GitHub repo (3,980 stars) is a public issue tracker, not the source.

IDE & desktopproprietaryfreemium✓ mcp✓ skills

Auggie CLI · Augment Code

250 · medium

Augment Code's terminal agent distinguished by its real-time Context Engine (semantic indexing of 1M+ files across repos, dependencies, docs, and git history), Unix-pipe-friendly print/quiet headless modes for CI/Lambda, custom slash commands, and credit-based plans from $20 (Indie) to enterprise.

Vendor CLI agentsproprietarysubscription✓ mcp

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 CLI · Anysphere (Cursor)

high

Cursor's terminal/headless version of its IDE agent (shipped January 2026), distinguished by cloud handoff to isolated cloud VMs, sandboxed command execution with granular network/filesystem controls, hooks, async subagents, and shared MCP/rules/skills config with the Cursor editor.

Vendor CLI agentsproprietarysubscription✓ mcp✓ skillsoptional

Droid (Factory) · Factory AI

medium

Factory AI's agent-native development platform whose Droid CLI held top Terminal-Bench rankings (77.3% with GPT-5.3-Codex, Feb 2026), distinguished by deploying agents across CLI, IDEs, Slack, and Linear with broad multi-vendor model support including Chinese open-weight models; raised $150M at $1.5B in April 2026.

Vendor CLI agentsproprietarysubscription✓ mcpoptional

Grok Build · xAI

medium

xAI's terminal coding agent (beta, launched June 5, 2026) distinguished by 8 parallel worktree-isolated subagents, a plan-first approval workflow, Arena Mode for competing outputs, an ACP-to-MCP bridge for MCP servers, OpenCode integration, and aggressive pricing via SuperGrok ($30/mo) and X Premium+ subscriptions.

Vendor CLI agentsproprietarysubscription✓ mcp

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

Windsurf Cascade / Devin Desktop (Devin Local) · Cognition AI (formerly Codeium)

medium

The Windsurf AI IDE's Cascade agent, post-Cognition-acquisition, was rebranded to Devin Desktop (June 2, 2026) with Cascade deprecated (available through July 1, 2026) in favor of the Rust-rewritten 'Devin Local' agent (30% more token-efficient, subagents), pairing local agentic editing (Fast Context codebase awareness, MCP, Memories, Workflows) with Devin cloud sessions for background work.

IDE & desktopproprietaryfreemium✓ mcpoptional

JetBrains Junie · JetBrains

medium

JetBrains' autonomous coding agent for IntelliJ-family IDEs (plus a Junie CLI that left beta March 2026 with BYOK/OpenRouter routing and CI/CD support), distinguished by leverage of the IDE's code index, a confirmation-gated loop with opt-in 'Brave Mode', Docker/worktree-isolated parallel tasks, remote cloud execution mode, and a companion Claude Agent built on Anthropic's Agent SDK.

IDE & desktopproprietaryfreemium✓ mcp✓ local modelsoptional

Trae (incl. SOLO) · ByteDance

medium

ByteDance's VS Code-based AI IDE, notable for aggressive pricing (free tier plus $3-$100/mo token-based tiers, restructured Feb 2026) and the SOLO mode (standalone app since March 31, 2026) that acts as an end-to-end 'context engineer' handling requirements, code, terminal, browser testing and deployment, with MCP (stdio/SSE/streamable HTTP) and custom agents — but persistent privacy/telemetry concerns.

IDE & desktopproprietaryfreemium✓ mcp

Google Antigravity · Google

medium

Google's agent-first development platform (launched Nov 2025, Antigravity 2.0 at I/O 2026 moved it toward a production standalone desktop app), distinguished by its Agent Manager 'mission control' that orchestrates parallel agents across editor, terminal, and an embedded browser subagent, with agents producing reviewable Artifacts (plans, screenshots, browser recordings) and a persistent knowledge/learnings base; runs Gemini 3 alongside Claude and GPT-OSS models.

IDE & desktopproprietaryfreemium✓ mcp

Devin · Cognition

high

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.

Cloud / backgroundproprietaryusage-based✓ mcpvm

OpenAI Codex (cloud) · OpenAI

high

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).

Cloud / backgroundproprietarysubscription✓ mcpcontainer

Claude Code on the web · Anthropic

high

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).

Cloud / backgroundproprietarysubscription✓ mcp✓ skillsvm

Cosine (Genie) · Cosine

medium

YC-backed autonomous software engineer that picks up tickets from GitHub/Jira/Linear and opens tested PRs end-to-end across CLI, desktop, VS Code and cloud, distinguished by its own in-house Lumen model family (including on-device Scout and air-gapped sovereign variants for regulated industries like HSBC/NatWest/BAE) and the April 2026 'Swarm' feature for parallel long-horizon agents; credit-based seats at $20 (Hobby) and $200 (Professional).

Cloud / backgroundproprietarysubscription✓ local modelsoptional

Cursor Cloud Agents · Anysphere

high

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.

Cloud / backgroundproprietarysubscription✓ mcpvm

Factory (Droids) · Factory AI

medium

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.

Cloud / backgroundproprietarysubscription✓ mcpoptional

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.

Runtimes & SDKsproprietaryusage-based✓ mcp✓ skillsvm

Manus · Butterfly Effect Pte Ltd (Singapore; ex-Monica)

high

The viral general-purpose autonomous agent that plans and executes multi-step tasks in a cloud VM (browsing, code, docs, slides), notable for Wide Research parallel sub-agents and for Meta's $2B acquisition being blocked by China's NDRC in April 2026.

General / computer-useproprietaryfreemiumcloud-remote

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.

General / computer-useproprietarysubscription✓ mcpcloud-remote

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.

General / computer-useproprietarysubscription✓ mcp✓ skillsoptional

Genspark Super Agent (+ Genspark Claw) · Genspark (MainFunc Inc.)

medium

Credit-based all-in-one 'AI employee' workspace whose Super Agent mixes multiple frontier models with 80+ tools to produce slides, sheets, sites, and calls, and whose 2026 'Genspark Claw' gives each user a persistent cloud computer commandable from WhatsApp/Telegram/Slack/Teams.

General / computer-useproprietaryfreemiumcloud-remote

Runner H · H Company (Paris)

medium

Cloud web-agent from DeepMind-alumni startup H Company ($220M seed) that orchestrates sub-agents over its own Holo vision-language action models (92.2% WebVoyager at ~$0.13/task via open-sourced Surfer-H), with Holo 3 in 2026 targeting any-UI enterprise automation.

General / computer-useproprietaryfreemium✓ local modelscloud-remote

Proxy (Convergence.ai) · Convergence.ai (acquired by Salesforce, 2025)

medium

London-based autonomous web agent with long-term memory and learned task reuse ('Teach mode') that briefly rivaled Operator on web benchmarks before Salesforce acquired Convergence.ai (closed 2025) and folded the team and tech into Agentforce, leaving the consumer product's future unclear.

General / computer-useproprietaryunknowncloud-remote

Perplexity's Chromium-based agentic browser (free on all four platforms since April 2026) whose sidebar assistant reads pages and tabs and executes web tasks in the user's own browser, extended by 'Personal Computer' on Mac to local file editing, local computer use, and voice orchestration.

General / computer-useproprietaryfreemium

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.

General / computer-useproprietarysubscription✓ mcpcloud-remote
harnesses.sh — the agent harness directory