Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
MCP server for web fetching with Cloudflare bypass, Trafilatura extraction, and smart routing. Free, self-hosted, no API keys.
| Date | Stars |
|---|---|
| 2026-07-31 | 740 |
| 2026-08-04 | 767 |
| 2026-08-06 | 767 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
35.0
growth rate 0.00%/day
<div align="center"> <img src="https://raw.githubusercontent.com/dondai1234/master-fetch/master/docs/hound-logo.png" alt="Hound logo" width="128"> # 🐕 Hound **Give your AI agent the web. $0. Two commands. No keys.** Fetch · crawl · bypass bot walls · read PDFs (even scanned) · search the web One MCP server · one warm browser · zero accounts · runs on your machine [](https://pypi.org/project/hound-mcp/) [](https://pypi.org/project/hound-mcp/) [](LICENSE) [](https://github.com/dondai1234/master-fetch/actions/workflows/ci.yml) [](https://pepy.tech/project/hound-mcp) [](https://github.com/dondai1234/master-fetch/stargazers) ```bash pip install hound-mcp[all] && playwright install chromium ``` [Install](#-install) · [The 6 tools](#-the-6-tools) · [Search](#-local-keyless-search) · [Comparison](#-comparison-free-tools) · [Gotchas](#-known-gotchas) · [Honest limits](#-honest-limits) </div> <br> <div align="center"> <img src="https://raw.githubusercontent.com/dondai1234/master-fetch/master/docs/hound-hero.png" alt="Hound gives your AI agent the web" width="860"> </div> --- ## 🎬 Demo Same prompt, three tools. Hound does the whole thing on its own, search + fetch + crawl, locally. The others get stuck on the parts they don't do. <div align="center"><b>OpenCode + Hound</b></div> <video src="https://github.com/user-attachments/assets/4e69e476-9c46-40cd-9bdf-f1b45882ac3e" controls muted width="860"></video> <div align="center"><b>Pi + Hound</b></div> <video src="https://github.com/user-attachments/assets/18b502c0-1e7b-4cb3-a730-074a9fbd0993" controls muted width="860"></video> --- ## ✨ New in 12.1.2 **BYOK search · intent-aware multi-query fan-out · six-signal ranking · next-gen stealth engine.** - 🔑 **Bring Your Own Key (BYOK) search**: add your own API keys for Serper, Tavily, Exa, Firecrawl, or TinyFish via `hound keys add`. Keys become the primary search source with **key stacking** (multiple keys per provider, auto-rotation on rate limit), automatic fallback to Hound's keyless local engines when all keys are exhausted. CLI key management: `hound keys add/list/test/remove/clear`. - 🧠 **Intent-aware multi-query fan-out**: Hound detects query intent (comparison, howto, research, code, reference, news, factual) and generates expanded query variants distributed across diversity engines. Same parallel request count, zero added latency, wider recall. Cross-variant consensus: a URL surfaced by different queries from different engines is a stronger authority signal. - 📊 **Six-signal ranking**: cross-variant consensus + domain reputation + answer-signal scoring + title relevance + URL relevance + result diversity (max 2 per domain in top results). Source-type detection tags every result as docs/paper/repo/blog/forum/reference/news. - 🧬 **Next-gen stealth engine**: system Chrome auto-detection, 4 coherent fingerprint profiles, JS-layer patches (HeadlessChrome UA fix, `navigator.webdriver=undefined`, canvas noise, permissions API), human behavior simulation (Bezier mouse curves, natural scroll), CF Turnstile solver with human-like mouse movement. Passes bot.sannysoft.com, bypasses Cloudflare Turnstile on CanadianInsider (hardest in a 31-site benchmark), Medium, StackOverflow, NowSecure, Glassdoor (DataDome). See the [stealth benchmark](#-stealth-benchmark) below. - 🐍 **No more scrapling.** All scrapling functionality replaced with hound's own modules: `fetcher.py` (primp-based HTTP), `browser.py` (patchright-based browser), `extractor.py` (trafilatura + markdownify). Smaller install, fewer transit
Excerpt of 38,303 characters
Read on GitHub
186
6
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9bbcd449fd0fa586, topic:mcp, desc:mcp server
matched fp:9bbcd449fd0fa586, topic:ai-agents