jinzijian/EvoTrace

An open toolkit and public dataset hub for collecting, sanitizing, analyzing, and visualizing coding agent traces.

Trace mining for post-training. Filter trajectories, draft verifiers, export SFT and RL data.

A local-first evidence layer for agent work, capturing what the agent sees, does, and changes.

Official Repo for (Self-Improving)^2 Coding Agent: Curating High-Quality Trajectories via Recursive Self-Improvement

Turn any repository into verifiable RL environments for coding agents - Harbor tasks you can train on, evaluate and share on the Hugging Face Hub

Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.

EvoSkill — An open-source framework that automatically discovers and synthesizes reusable agent skills from failed trajectories to improve coding agent performance.

Infrastructure for thousands of task-specialised models that learn continuously from every interaction.

Compiles AI agent traces and truns them into reusable context.