| name | deer_flow |
| display_name | Deer Flow Specialist |
| description | Full-stack research and code generation pipeline - research, code, and create |
| version | 0.1.0 |
| source_repo | bytedance/deer-flow |
| license | MIT |
| tier | core |
| capabilities | ["research","code_generation","creation","summarize"] |
| allowed_tools | ["research_topic","generate_code","create_artifact"] |
| output_formats | ["python_api","cli","mcp_server","agent_skill","rest_api"] |
Deer Flow Specialist
Overview
The Deer Flow specialist wraps the bytedance/deer-flow
SuperAgent pattern into a composable OSS Agent Lab specialist. It chains three stages into a
single pipeline:
- Research — gathers structured findings and source attribution for any topic.
- Code Generation — translates research summaries or explicit specifications into
working implementations with matching test skeletons.
- Artifact Creation — packages the pipeline outputs into a versioned, hash-identified
deliverable in markdown, JSON, or HTML.
Each stage is also independently callable as a tool, making the specialist useful for
partial workflows (research-only, code-only, wrap-existing-content-in-artifact).
Capabilities
- research: Gather findings, sources, a summary, and a confidence score for any topic.
Supports
shallow, standard, and deep depth settings.
- code_generation: Generate an implementation, test skeleton, and explanation from a
natural-language specification. Supports Python and other languages.
- creation: Package any content dict into a versioned artifact with stable ID and
creation metadata.
- summarize: The research stage always produces a concise summary suitable for direct
use or downstream prompting.
Tools
| Tool | Description | Parameters | Side Effects |
|---|
research_topic | Research a topic and return findings, sources, summary, confidence | topic, depth, sources | None |
generate_code | Generate code, tests, and explanation from a specification | specification, language, style | None |
create_artifact | Package content into a versioned artifact with metadata | content, artifact_type, format | None |
Tool Parameter Reference
research_topic
