$ find your agent harness

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.

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.

MIT-licensed Python library (103k stars) that lets any LLM drive a real Chrome browser via DOM+vision instead of brittle selectors, now flanked by a desktop app and a usage-based cloud with stealth browsers, proxies, and a 24/7 'Browser Use Box' agent.

OpenAI's open-source (Apache-2.0) Rust-rewritten terminal coding agent, distinguished by kernel-level OS sandboxing (Apple Seatbelt on macOS, Landlock/seccomp on Linux), a 272K-1M token context with GPT-5.x Codex models, MCP support, and cloud handoff to Codex web tasks.

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.

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.

Hugging Face's minimalist (~1,000-line core, Apache 2.0) 'agents that think in code' harness where the model writes executable Python as its action format instead of JSON tool calls, model-agnostic via transformers/Ollama/LiteLLM, with optional sandboxed execution (E2B, Docker, WebAssembly), managed sub-agents, and Hub sharing of tools and agents.

The original open deep-research harness (Apache-2.0, 28k stars): a planner/executor multi-agent pipeline that fans out parallel web and local-document searches into cited reports, with recursive tree-like 'Deep Research', MCP data-source integration, and any-LLM support.

LangChain's self-described 'batteries-included agent harness' (GA March 2026, ~26k stars) for long-running tasks, layering planning via write_todos, a virtual filesystem for context offloading, SKILL.md-compatible skills with progressive disclosure, subagent spawning, and LangGraph-store-backed long-term memory on top of the LangGraph runtime.

Alibaba's Apache-2.0 terminal agent (originally a Gemini CLI fork) optimized for Qwen3-Coder models, distinguished by broad provider flexibility (OpenAI/Anthropic/Gemini/Qwen APIs plus Ollama/vLLM local models), skills/subagents primitives, headless mode, and TypeScript/Python/Java SDKs.

Kilo's open-source terminal agent (Kilo CLI 1.0, built on the MIT-licensed OpenCode foundation) distinguished by support for 500+ models with zero-markup BYOK pricing, an MCP marketplace, and cross-surface continuity where a task can move between Slack, VS Code/JetBrains, cloud, and terminal.

Apache-2.0 platform for stateful agents descended from MemGPT, distinguished by tiered self-editing memory persisted in a database (core memory in-context, archival out-of-context) plus 2026 research on git-based 'Context Repositories' and memory-native RL; in 2026 the company is consolidating around Letta Code, an open, model-agnostic memory-first coding agent harness (LettaBot archived May 2026 and folded in as Channels).

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.

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.

Mistral's minimal Apache-2.0 CLI coding agent (launched December 2025 alongside the open-weight Devstral 2 models, which score a vendor-reported 72.2% on SWE-bench Verified), distinguished by a deliberately lean self-hostable design — file read/write/patch, stateful shell, grep, and todo tools — with fully open, locally runnable model weights.

Moonshot AI's MIT-licensed TypeScript terminal agent (launched June 2026, replacing its earlier CLI) built around the token-efficient Kimi K2.7-Code 1T-parameter MoE model with 256K context, distinguished by built-in coder/explore/plan subagents running in isolated contexts and configurable OpenAI-compatible providers including local deployments.

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).