Newest
The 20 most recently created harnesses in the catalog, youngest first.
| # | Project | Stars | Δ 7d | Δ 30d | 90d trend | Age | Lang | Last push |
|---|---|---|---|---|---|---|---|---|
| 1 | xai-org/grok-build SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible. | 14.5k | — | — | 3 d | Rust | 15h ago | |
| 2 | mereyabdenbekuly-ctrl/clodex-ide Local-first, zero-trust agentic IDE for verifiable autonomous software development. | 831 | — | — | 6 d | TypeScript | 6m ago | |
| 3 | modiqo/waggle Attributed, resolvable artifact references for agent handoffs — a ~30-byte token instead of pasted context. MC… | 802 | — | — | 1 wk | Rust | 2d ago | |
| 4 | Sahir619/fable-method The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that kee… | 1.5k | +1,120 | — | 1 wk | Python | 1d ago | |
| 5 | clawkwork/clawk Give coding agents a disposable Linux VM, not your laptop | 673 | +643 | — | 1 wk | Go | 3d ago | |
| 6 | cozytab/fable5-mode Make Opus 4.8 (or any Claude model) work like Claude Fable 5 — a Claude Code skill + guard hooks (plan gate, m… | 115 | +52 | — | 1 wk | Python | 2d ago | |
| 7 | Tura-AI/tura Across 348 long-horizon benchmark sessions, Tura used up to 83.1% fewer turns on the rewrite benchmark and imp… | 119 | — | — | 1 wk | Rust | 21h ago | |
| 8 | jasonsuhari/gridbash Cross-platform terminal grid for running Codex, Claude, Gemini, and other CLI agents side by side. | 123 | +96 | — | 1 wk | Rust | 1h ago | |
| 9 | Kulaxyz/token-diet Always-on token-efficiency skill for coding agents (Claude Code, Codex, Cursor, Windsurf, Cline). ~31% lower b… | 526 | +5 | — | 2 wk | Shell | 12d ago | |
| 10 | Reina-Agent/Reina Reina 桌面 AI Agent 发行仓库（仅安装包） | Release distribution for the Reina desktop AI agent — installers only. Windows… | 25 | — | — | 2 wk | — | 10h ago | |
| 11 | 7-e1even/learn-agent 学习Agent开发的笔记，尝试让Agent从可用到可靠 | 142 | +23 | — | 2 wk | JavaScript | 2d ago | |
| 12 | Archive228/loopkit 33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI… | 677 | +208 | — | 2 wk | Shell | 2d ago | |
| 13 | oomol-lab/open-connector Open-source auth gateway connecting 1000+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI… | 2.8k | +1,500 | — | 2 wk | TypeScript | 21m ago | |
| 14 | aufamubarak/plan-execute-verify-claude-code Best AI Coding Workflow Plugin Pipeline 2026 | 151 | 0 | — | 2 wk | HTML | 54m ago | |
| 15 | muhammadalicusit56-glitch/otto-cognitive-nudge Smart Promise Tracker AI 2026 – Commit Memory Engine | 152 | 0 | — | 2 wk | HTML | 2h ago | |
| 16 | Magma1321/mythos-agent-pipe Finish-First Autonomous Agent Loop for Claude Opus 4.7 – 2026 Edition | 153 | +1 | — | 2 wk | HTML | 1h ago | |
| 17 | Kulaxyz/self-learning-skills A self-improving skill for AI coding agents (Claude Code, Cursor, AGENTS.md): recognize a hard-won golden path… | 880 | +83 | — | 2 wk | — | 16d ago | |
| 18 | pakgik01/ask-expert-consult-mcp Open Source AI Expert Agent Bridge for Cursor 2026 | 151 | 0 | — | 2 wk | HTML | 23m ago | |
| 19 | 1iry/multi-agent-architecture-advisor Advanced AI Code Strategy Advisor for Developer Agents (2026) | 151 | 0 | — | 2 wk | HTML | 55m ago | |
| 20 | nam271212/strategic-advisor-orchestrator AI Coding Agent Orchestrator 2026: Pro-Level Strategy & Review Framework | 152 | 0 | — | 2 wk | HTML | 47m ago |
Sorted by repository creation date, so this is the freshest end of the catalog, not the most proven one. A young repo with few stars has not been through much yet.
Methodology
We find candidates through GitHub Search (agent-related topics and keywords, plus a radar for repos younger than 90 days), then snapshot every repo in the pool once a day via the GraphQL API. For new entries we rebuild star history from sampled stargazer timestamps.
Fast growing ranks by (2 × stars_7d + stars_30d) × youth_bonus. Last week counts double, and young repos get a boost so giants don't bury newcomers. The other rankings sort by stars, by repo age, and by 👍 reactions on open issues.
Exclusions:archived repositories, inactive repos (no pushes in 60 days), awesome-lists, and prompt collections. We define a “harness” as a tool or framework that orchestrates an LLM to complete tasks — tool calling, context management, agentic loops. Models themselves, API wrappers, and prompt libraries do not qualify.