Activity, over time
Daily observations from the public event archive.
Attention
Daily stars & forks
Star accumulation
Cumulative stars
Pull requests
Daily opens & merges
Conversations
Daily issues & comments
Community
Daily accounts & reviews
Releases
Daily releases
Trending history
Daily top 10 · last 90 days · UTC
Mentions
Stars
Forks
Contributors
Latest stargazers
The last 10 distinct accounts we observed this year.
Most active participants
PR, issue, comment & review events in the past year.
Packages
| Package | Version | Downloads · 30d | Trend · 30d |
|---|---|---|---|
agentlightningv1.0.2 | v1.0.2 | ≥12.7K | |
llm-in-sandboxv0.2.0 | v0.2.0 | ≥539 |
README badges
Embed a badge in your README or website.
Live mentions · last 30 days
Mentions
Training an agent on its real workflow? Microsoft's Agent Lightning v1.0 captures model calls for reinforcement learning, keeping tools and control flow in the loop. Needs GPU setup; logs and trajectories go to W&B by default. microsoft/agent-lightning
@charles12388 For ref, you can start with: 1) ed-donner/agents (for folks who are starting) 2) microsoft/agent-lightning (this is for advance level) I would suggest completing (2). It's a little similar to my corporate exp
دقت یک مدل سبک MOE رو روی SWE-bench حدود ۱۵٪ میتونی افزایش بدی تا نزدیک به مدل های فوق سنگین فرانتیر عمل کنن. مایکروسافت با Agent Lightning و فقط ۱.۸k داده تعاملی نشون داد کیفیت هارنس از اسکیل مهمتره! فریمورک AgentEnv هم برای اجرا و ساخت اوپنسورس شده: microsoft/agent-lightning