Repository Radar - PR#2

2025-02-19 · 7 repos · Read on Substack ↗

This issue's picks are up + 155% combined since it ran (78k★ → 200k★).

• DeepScaler378(+4k)
• BrowserUse350(+73k)
• Unsloth226(+38k)
• Open Deep Research153(+2k)
• Goku139(+812)
• Devin CursorRules136(+2k)
• Oumi130(+2k)

star trajectories since covered are charted per repo below · compare them all on star-history.com ↗

• BrowserUse ACTIVE

  🌐 Make websites accessible for AI agents. Automate tasks online with ease.

  102k★ now 29k★ when covered + 73k (+250%)

• Unsloth ACTIVE

  Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

  68k★ now 30k★ when covered + 38k (+126%)

• Oumi ACTIVE

  Easily fine-tune, evaluate and deploy Gemma 4, Qwen3.5, Qwen3.6, gpt-oss, DeepSeek-R1, or any open source LLM / VLM!

  9k★ now 7k★ when covered + 2k (+30%)

• Open Deep Research STALE

  An open source deep research clone. AI Agent that reasons large amounts of web data extracted with Firecrawl

  6k★ now 4k★ when covered + 2k (+53%)

• Devin CursorRules STALE

  Magic to turn Cursor/Windsurf as 90% of Devin

  6k★ now 4k★ when covered + 2k (+36%)

• DeepScaler ACTIVE

  Democratizing Reinforcement Learning for LLMs

  6k★ now 2k★ when covered + 4k (+278%)

• Goku STALE

  [CVPR2025 Highlight] Video Generation Foundation Models: https://saiyan-world.github.io/goku/

  3k★ now 2k★ when covered + 812 (+39%)