OpenPipe/ART
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!
Language:Python
Total stars: 1030
Stars trend:
#python
#agent, #agenticai, #grpo, #kimiai, #llms, #lora, #qwen, #qwen3, #reinforcementlearning, #rl
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!
Language:Python
Total stars: 1030
Stars trend:
11 Jul 2025
5pm ▉ +7
6pm █▌ +12
7pm ██ +16
8pm █▌ +12
9pm █▎ +10
10pm █▎ +10
11pm ▋ +5
12 Jul 2025
12am ▉ +7#python
#agent, #agenticai, #grpo, #kimiai, #llms, #lora, #qwen, #qwen3, #reinforcementlearning, #rl
browserbase/stagehand
The AI Browser Automation Framework
Language:TypeScript
Total stars: 13401
Stars trend:
#typescript
#agents, #ai, #llms, #playwright, #puppeteer, #selenium
The AI Browser Automation Framework
Language:TypeScript
Total stars: 13401
Stars trend:
12 Jul 2025
7am █▏ +9
8am ▌ +4
9am ▋ +5
10am ▌ +4
11am ▋ +5
12pm ▊ +6
1pm ▍ +3
2pm █▏ +9
3pm █ +8
4pm ▋ +5
5pm █▏ +9
6pm █▎ +10#typescript
#agents, #ai, #llms, #playwright, #puppeteer, #selenium