Dataset Viewer
Auto-converted to Parquet Duplicate
session_id
stringclasses
2 values
model
stringclasses
2 values
git_branch
stringclasses
1 value
start_time
stringclasses
2 values
end_time
stringclasses
2 values
messages
listlengths
8
11
stats
dict
project
stringclasses
1 value
source
stringclasses
1 value
54813338-0396-4ccb-a8e5-886927715ff8
claude-haiku-4-5-20251001
HEAD
2026-09-02T15:27:59.492Z
2026-09-02T15:30:29.167Z
[ { "role": "user", "content": "i am testing dataclaw. i want this to be a claude project", "timestamp": "2026-09-02T15:27:59.492Z" }, { "role": "assistant", "thinking": "The user is testing dataclaw and wants this to be a Claude project. They're in the directory `c:\\Users\\user_18e8b20e\\Des...
{ "user_messages": 3, "assistant_messages": 8, "tool_uses": 3, "input_tokens": 244543, "output_tokens": 2971 }
dataclaw-test
claude
54813338-0396-4ccb-a8e5-886927715ff8:subagents
claude-sonnet-5
HEAD
2026-09-02T15:29:11.066Z
2026-09-02T15:30:21.115Z
[ { "role": "user", "content": "Explore the directory c:\\Users\\user_18e8b20e\\Desktop\\dataclaw-test thoroughly. I need to write a CLAUDE.md file for this codebase.\n\nPlease report back:\n1. The full directory/file listing (list all files and folders, including hidden ones like .cursorrules, .github/copilo...
{ "user_messages": 1, "assistant_messages": 7, "tool_uses": 6, "input_tokens": 111711, "output_tokens": 944 }
dataclaw-test
claude

Coding Agent Conversation Logs

This is a performance art project. Anthropic built their models on the world's freely shared information, then introduced increasingly dystopian data policies to stop anyone else from doing the same with their data - pulling up the ladder behind them. DataClaw lets you throw the ladder back down. The dataset it produces is yours to share.

Exported with DataClaw.

Tag: dataclaw - Browse all DataClaw datasets

Stats

Metric Value
Sessions 2
Projects 1
Input tokens 356K
Output tokens 4K
Last updated 2026-09-02

Models

Model Sessions Input tokens Output tokens
claude-haiku-4-5-20251001 1 245K 3K
claude-sonnet-5 1 112K 944

Projects

Project Sessions Input tokens Output tokens
dataclaw-test 2 356K 4K

Schema

Each line in conversations.jsonl is one session:

{
  "session_id": "abc-123",
  "project": "my-project",
  "model": "claude-opus-4-6",
  "git_branch": "main",
  "start_time": "2025-06-15T10:00:00+00:00",
  "end_time": "2025-06-15T10:30:00+00:00",
  "messages": [
    {
      "role": "user",
      "content": "Fix the login bug",
      "content_parts": [
        {"type": "image", "source": {"type": "base64", "media_type": "image/png", "data": "..."}}
      ],
      "timestamp": "..."
    },
    {
      "role": "assistant",
      "content": "I'll investigate the login flow.",
      "thinking": "The user wants me to look at...",
      "tool_uses": [
          {
            "tool": "bash",
            "input": {"command": "grep -r 'login' src/"},
            "output": {
              "text": "src/auth.py:42: def login(user, password):",
              "raw": {"stderr": "", "interrupted": false}
            },
            "status": "success"
          }
        ],
      "timestamp": "..."
    }
  ],
  "stats": {
    "user_messages": 5, "assistant_messages": 8,
    "tool_uses": 20, "input_tokens": 50000, "output_tokens": 3000
  }
}

messages[].content_parts is optional and preserves structured user content such as attachments when the source provides them. The canonical human-readable user text remains in messages[].content.

tool_uses[].output.raw is optional and preserves extra structured tool-result fields when the source provides them. The canonical human-readable result text remains in tool_uses[].output.text.

Load

from datasets import load_dataset
ds = load_dataset("masterda/my-personal-codex-data", split="train")

Export your own

pip install -U dataclaw
dataclaw
Downloads last month
28