tathadn/codeq

An AI agent that teaches itself to fix bugs — MCTS explores debugging strategies, DPO trains on what works. Pipelined across two H100 nodes: one for 4-bit inference and trajectory collection, one for full bf16 LoRA fine-tuning. Built on Qwen2.5-Coder-7B, evaluated on DebugBench. Inspired by Agent Q (Putta et al., 2024).

14
/ 100
Experimental
No License No Package No Dependents
Maintenance 13 / 25
Adoption 0 / 25
Maturity 1 / 25
Community 0 / 25

How are scores calculated?

Stars

Forks

Language

Python

License

Last pushed

Apr 05, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/tathadn/codeq"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.