Author: hf-mirror · License: apache-2.0 · Format: jsonl
0 downloads · 0 stars · 0 mirrors · 19,819 · 1 file
This dataset is aggregated from: ``` "AletheiaResearch/GLM-5.2-Agent", "armand0e/claude-fable-5-claude-code", "armand0e/minimax-m3-claude-code-traces", "AletheiaResearch/Kimi-K3-Codex" ``` and has been converted into a single unified format: ``` {"messages": [{"role": "user", "content": "..."}, {"role": "assistant", "content": "<think>...</think>..."}, ...]} ``` The original raw files are kept in the `.raw_sources` folder for reference if you'd like to take a closer look.
This dataset is aggregated from: ``` "AletheiaResearch/GLM-5.2-Agent", "armand0e/claude-fable-5-claude-code", "armand0e/minimax-m3-claude-code-traces", "AletheiaResearch/Kimi-K3-Codex" ``` and has been converted into a single unified format: ``` {"messages": [{"role": "user", "content": "..."}, {"role": "assistant", "content": "<think>...</think>..."}, ...]} ``` The original raw files are kept in the `.raw_sources` folder for reference if you'd like to take a closer look.
Or via the API: curl -L -o file "https://huggingface.co/datasets/mondk/agentic-coding-traces/resolve/main/.raw_sources/hf_downloads/AletheiaResearch__GLM-5.2-Agent/2026-06-19T19-53-37-440Z_019ee172-2f9f-7341-8125-4e5d535d9e56.jsonl"
Added 2026-09-27. Platform: Distillio — the open source training data collective.