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 | deepseek-ai/deepseek-harness DeepSeek Harness: Everything is a Plugin. | 255.2k | +6,494 | +24,419 | 2 mo | TypeScript | 3d ago | |
| 2 | stablyai/orca Orca is the place for working with a fleet of agents (e.g. Grok Bot, Claude Code). Run any coding agent with y… | 99.0k | +7,868 | +25,880 | 7 mo | TypeScript | 12m ago | |
| 3 | MadsLorentzen/ai-job-search The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings… | 58.9k | +12,454 | +15,508 | 7 mo | Python | 4h ago | |
| 4 | affaan-m/ECC The agent harness performance optimization system. Skills, instincts, memory, security, and research-first dev… | 284.4k | +6,236 | +21,215 | 9 mo | JavaScript | 7h ago | |
| 5 | vectorize-io/hindsight Hindsight: Agent Memory That Learns | 51.9k | +2,829 | +27,831 | 11 mo | Python | 1h ago | |
| 6 | lexmount/moli Best headless browser for AI agents. Lite, Fast, High-Compatibility. Built in Rust | 19.8k | +2,107 | +17,660 | 2 mo | Rust | 17m ago | |
| 7 | cloudflare/security-audit-skill A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings | 33.0k | +3,964 | +15,667 | 4 mo | JavaScript | 35d ago | |
| 8 | hypit-ai/hypit Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-r… | 24.2k | +2,390 | +12,655 | 2 mo | TypeScript | 1d ago | |
| 9 | anomalyco/opencode The open source coding agent. | 218.3k | +5,241 | +9,573 | 1 yr | TypeScript | 13m ago | |
| 10 | Graphify-Labs/graphify Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphif… | 129.5k | +3,456 | +9,730 | 6 mo | Python | 3d ago | |
| 11 | K-Dense-AI/scientific-agent-skills Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists w… | 53.1k | +4,452 | +7,405 | 1 yr | Python | 1d ago | |
| 12 | diegosouzapw/OmniRoute Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, G… | 78.7k | +2,794 | +10,311 | 8 mo | TypeScript | 3h ago | |
| 13 | firecrawl/firecrawl Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥 | 193.2k | +2,223 | +10,813 | 2 yrs | TypeScript | 29m ago | |
| 14 | calesthio/OpenMontage World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent sk… | 70.1k | +2,359 | +9,847 | 6 mo | Python | 3d ago | |
| 15 | mksglu/context-mode Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memo… | 31.2k | +3,502 | +7,514 | 8 mo | TypeScript | 12m ago | |
| 16 | earendil-works/pi AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI | 116.6k | +1,804 | +9,018 | 1 yr | TypeScript | 16m ago | |
| 17 | NousResearch/hermes-agent The agent that grows with you | 255.4k | +2,115 | +8,102 | 1 yr | Python | 13m ago | |
| 18 | google/artemis ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflow… | 13.1k | +1,658 | +4,891 | 2 mo | Python | 18d ago | |
| 19 | lemomo-ai/lemo-opuscar Claude Code skill for short films with no video model: 51 film styles, each a style prompt plus a demo film ma… | 4.1k | +2,011 | +4,134 | 3 wk | JavaScript | 23h ago | |
| 20 | JuliusBrussee/caveman 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens b… | 113.8k | +2,423 | +6,881 | 6 mo | Go | 1d 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.