Fast growing
The 20 AI agent harnesses gaining GitHub stars fastest right now.
| # | 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. | 11.8k | +11,751 | +11,751 | 3 d | Rust | 15h ago | |
| 2 | oomol-lab/open-connector Open-source auth gateway connecting 1000+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI… | 2.7k | +1,500 | +2,743 | 2 wk | TypeScript | 21m ago | |
| 3 | XiaomiMiMo/MiMo-Code MiMo Code: Where Models and Agents Co-Evolve | 12.2k | +416 | +2,717 | 1 mo | TypeScript | 1h 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… | 1.3k | +1,120 | +1,276 | 1 wk | Python | 1d ago | |
| 5 | HKUDS/DeepTutor DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/. | 26.8k | +1,391 | +2,111 | 6 mo | Python | 7d ago | |
| 6 | BuilderIO/skills Skills for coding agents | 3.7k | +84 | +2,813 | 1 mo | JavaScript | 11h ago | |
| 7 | microsoft/flint-chart 🪄 Flint is a visualization language that lets AI agents reliably create expressive, good-looking charts from… | 1.8k | +571 | +1,774 | 2 mo | TypeScript | 3h ago | |
| 8 | opensquilla/opensquilla OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density | 6.1k | +457 | +1,905 | 2 mo | Python | 41m ago | |
| 9 | cloudflare/security-audit-skill A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings | 2.5k | +135 | +2,547 | 4 wk | JavaScript | 10d ago | |
| 10 | manaflow-ai/cmux Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for… | 24.6k | +473 | +2,429 | 5 mo | Swift | 4m ago | |
| 11 | mindfold-ai/Trellis The best agent harness. | 12.7k | +504 | +2,193 | 5 mo | TypeScript | 8h ago | |
| 12 | mereyabdenbekuly-ctrl/clodex-ide Local-first, zero-trust agentic IDE for verifiable autonomous software development. | 825 | +825 | +825 | 6 d | TypeScript | 6m ago | |
| 13 | jackwener/OpenCLI Make Any Website into CLI & Use your logged-in browser by AI agent. | 26.8k | +351 | +2,193 | 4 mo | JavaScript | 4d ago | |
| 14 | langchain-ai/langgraph Build resilient agents. | 37.5k | +499 | +2,485 | 2 yrs | Python | 19h ago | |
| 15 | rohitg00/agentmemory #1 Persistent memory for AI coding agents based on real-world benchmarks | 25.2k | +320 | +2,110 | 4 mo | TypeScript | 4d ago | |
| 16 | google/agents-cli The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI age… | 5.2k | +203 | +2,244 | 3 mo | Python | 6d ago | |
| 17 | vercel-labs/deepsec Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents | 5.2k | +68 | +2,039 | 2 mo | TypeScript | 4d ago | |
| 18 | google-labs-code/stitch-skills A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills ope… | 7.5k | +834 | +1,481 | 6 mo | TypeScript | 3d ago | |
| 19 | code-yeongyu/lazycodex The one and only agent harness for complex codebases. Project memory, planning, execution, and verified comple… | 2.8k | +201 | +1,674 | 1 mo | TypeScript | 1d ago | |
| 20 | amplifthq/opentag Open-source @agent mentions for Slack and GitHub. OpenTag routes tagged requests to Codex, Claude Code, then r… | 1.4k | +317 | +1,363 | 3 wk | TypeScript | 12h ago |
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.