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 clean-room Rust/Python rewrite of Claude Code's harness architecture born hours after the March 31, 2026 source leak — reportedly the fastest-growing repo in GitHub history (~195k stars) with permission-gated tools, MCP, agent swarms, and container-first deployment — though the project is chaotic, largely agent-maintained, and its details vary across sources.
The most-starred open-source coding agent of 2026 (~183k stars, MIT, TypeScript): a polished terminal TUI with 75+ providers, LSP feedback, Tab-switchable build/plan agents plus background subagents, SKILL.md support, and optional paid model access via OpenCode Go ($10/mo) and pay-as-you-go Zen gateway.
Formerly OpenDevin, the leading open-source autonomous software-engineering platform: Docker-sandboxed agents that write code, run commands, browse, and open PRs, with a production agent SDK hitting 72% on SWE-bench Verified (Claude Sonnet 4.5) and its own broader OpenHands Index benchmark launched Jan 2026.
Mario Zechner's radically minimal MIT/TypeScript harness (~68k stars): four tools (read/write/edit/bash), a ~300-word system prompt, deliberately no built-in MCP/subagents/permission-popups, with everything else added via TypeScript extensions, skills, and npm/git-shareable packages across interactive, print/JSON, RPC, and SDK modes.
The dominant open-source VS Code agent (Apache-2.0, 64k+ stars, 1.5M+ installs): human-in-the-loop plan/act workflow with per-edit and per-command approval, terminal and browser control, an MCP marketplace, and a BYOK-first model with optional pay-as-you-go credits and an enterprise tier.
Block's Rust-built, Apache-2.0 general engineering agent — now stewarded by the Linux Foundation's Agentic AI Foundation — distinguished by the deepest MCP integration in the ecosystem (70+ extensions, can also act as an MCP server) and shareable YAML 'Recipes' that scaled agent workflows to 60% of Block.
The original terminal AI pair programmer (since 2023): git-native supervised editing with auto-commits per change, a tree-sitter repo map, architect/editor model pairing, and watch-mode AI comments — still largely a one-maintainer community project with releases roughly every two weeks.
The veteran model-agnostic IDE extension (VS Code + JetBrains, strong local-model support) that pivoted to 'Continuous AI' — a cn CLI running markdown-defined async agents as GitHub PR status checks — before being acquired by Cursor in 2026, with the original team shipping a final v2.0.0 (telemetry and auth removed).
The Cline/Roo merger-fork turned all-in-one agentic platform (~26k stars, 3M+ users): IDE extension, CLI, and hosted KiloClaw background agent reachable via Telegram/Discord/Slack, with 500+ models, mid-task model switching, an MCP marketplace, subagents (GA April 2026), and optional Kilo Pass credits from $19/mo.
The influential Cline fork that popularized multi-mode agents (Architect/Code/Debug/Ask) and orchestrated subtasks in VS Code — shut down May 15, 2026, with its Apache-2.0 repo archived on GitHub and Kilo Code recommended as the migration path.
The NeurIPS-2024 research harness from the SWE-bench team that pioneered the agent-computer-interface concept: takes a GitHub issue and autonomously fixes it in a containerized environment with any LM, and remains the reference batch-evaluation harness for academic agent research.
A batteries-included 2026 fork of Pi (created Dec 31, 2025; ~17k stars) that inverts Pi's minimalism: hash-anchored edits that reject stale patches, LSP and DAP debugger integration, in-process ripgrep/bash, 40+ providers, 32 tools, and subagent orchestration.
Terminal agent purpose-built for very large multi-file tasks — 2M-token effective context via tree-sitter project maps, a cumulative diff-review sandbox that stages changes outside the repo, and configurable full-auto mode — but Plandex Cloud wound down in Oct 2025 and the repo has had no pushes since, leaving it self-host-only and dormant.
A deliberately radical ~100-line Python agent with bash as its only tool (no tool-calling API, no config sprawl) that still scores >74% on SWE-bench Verified, used by Meta, NVIDIA, and IBM as a baseline/benchmarking harness and proof that scaffolding can be minimal.