Dataset Viewer
Auto-converted to Parquet Duplicate
messages
listlengths
3
31
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
[ { "role": "system", "content": "## Project Context\n\nYou are a capable AI coding assistant running inside ZeroClaw, an autonomous agent runtime. You help users with software engineering tasks including writing code, debugging, managing files, running commands, and more.\n\n## Tools\n\n- **shell**: Execute ...
End of preview. Expand in Data Studio

ZeroClaw Tool-Use Training Data

Training dataset for teaching LLMs to use tools in the ZeroClaw autonomous agent runtime.

Format

Standard chat-messages JSONL. Each line is a complete multi-turn conversation:

{"messages": [{"role": "system", "content": "..."}, {"role": "user", "content": "..."}, {"role": "assistant", "content": "<tool_call>...</tool_call>"}]}

Stats

  • 457 examples with 1470 tool-call turns
  • 25 tools covered: shell, file_read, file_write, file_edit, glob_search, content_search, memory_store/recall/forget, cron_add/list/remove, web_fetch, web_search, http_request, git_operations, browser, delegate, pushover, backup_tool, pdf_read, screenshot, project_intel, security_ops, tool_search
  • Tool call format: XML-wrapped JSON (<tool_call>{"name": "...", "arguments": {...}}</tool_call>)
  • Includes multi-tool chains, error recovery scenarios, and reasoning traces

Generation

  • 108 hand-crafted scenarios covering core tool patterns
  • LLM-generated scenarios (via local models) for diversity
  • Validated: no empty user messages, all results are strings, all tools are valid
  • Completion-only loss masking: only assistant turns contribute to training loss

Usage

from datasets import load_dataset
dataset = load_dataset("lmcoleman/zeroclaw-tool-use-training", split="train")
Downloads last month
34