OSS Radar
Back
skilltraining-project avatar

skilltraining-project/skill-training

Skill training with a corruption and reconstruction loop: train an agent's skill library, not its weights. Why it matters: worth a look if you build or run autonomous agents.

GitHub description: Skill training with a corruption and reconstruction loop: train an agent's skill library, not its weights.

Stars

918

Last 24h

+4

Last 7 days

+128est.

Forks

4

Star history

GitHub stars over time. A steeper line means the repo is gaining attention faster.

Last 6 hours · +75 stars

Hourly star count for skilltraining-project/skill-training918843Nov 13, 1 AM UTCNov 16, 2 AM UTC

Daily, since Nov 13, 2026 · 863 → 918

Daily star count for skilltraining-project/skill-training918863Nov 13, 2026Nov 16, 2026

* / est. Estimated: until we have enough daily snapshots for a repo, its gain is total stars ÷ days since creation. Measured numbers replace estimates automatically.

Maintainer? Add the badge to your README

Shows your live OSS Radar rank and links back here. Updates hourly. How the badge works.

OSS Radar badge preview
[![Trending on OSS Radar](https://ossradar.net/badge/skilltraining-project/skill-training)](https://ossradar.net/repo/skilltraining-project/skill-training)
<a href="https://ossradar.net/repo/skilltraining-project/skill-training"><img src="https://ossradar.net/badge/skilltraining-project/skill-training" alt="Trending on OSS Radar"></a>

About skill-training

skilltraining-project/skill-training is a Python project in the AI agents category, created 51 days ago. It has 918 GitHub stars and 4 forks, and gained +128 stars over the last 7 days (early estimate), ranking #107 of 111 AI agents repos tracked by OSS Radar this week.

See more trending AI agents repos or the top AI repos this week.

Language
Python
Category
AI agents
License
Other (custom license)
Created
Sep 26, 2026
Last code push
22 days ago (Oct 24, 2026)
Latest release
No releases yet

Rising in AI agents this week

  • REAmorluto/rea
    +15k stars this week

    Reverse engineer anything with agents, from app behavior down to native binaries.

  • dsh-our-free-modelEbony-Vinyl/dsh-our-free-model
    +8.6k stars this week

    All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there…

  • +7k stars this week

    Agent skills.

  • uivercel-labs/ui
    +5kest. stars this week

    A library of behaviors for agents to build the next generation of user interfaces.

  • DeepSeek Harnessdeepseek-ai/deepseek-harness
    +4.3k stars this week

    DeepSeek Harness: Everything is a Plugin.

  • OpenMausBotmilind-soni/OpenMausBot
    +3.9k stars this week

    Open-source Grok Bot alternative with a virtual machine that bots can use.

skill-training is #397 of 450 on today's leaderboard.