• 1
• 0
• 0

slime

https://github.com/gitcodeaction/slime.git

• 1
• 0
• 0

claw-eval

Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.

• 1
• 0
• 0

openclaw

https://github.com/openclaw/openclaw

• 1
• 0
• 0

dynamo

https://github.com/gitcodeaction/dynamo

• 1
• 0
• 0

Agent-Reach

https://github.com/gitcodeaction/Agent-Reach

• 1
• 0
• 0

sglang

https://github.com/gitcodeaction/sglang

• 1
• 4
• 3

nanoclaw

https://github.com/qwibitai/nanoclaw

• 1
• 3
• 3

CLI-Anything

https://github.com/HKUDS/CLI-Anything

• 1
• 0
• 0

yoyo-evolve

A coding agent that evolves itself. One commit per day.

• 1
• 0
• 0

terminal-bench-2

• 1
• 0
• 0

long-prompts-analysis

https://github.com/nilenso/long-prompts-analysis

• 1
• 0
• 0

pi-mono

https://github.com/badlogic/pi-mono

• 1
• 0
• 0

ultrascale-playbook-zh

• 1
• 0
• 0

leptonai.leptonai

https://github.com/leptonai/leptonai

• 1
• 0
• 0

dw-dengwei.daily-arXiv-ai-enhanced

https://github.com/dw-dengwei/daily-arXiv-ai-enhanced