Back to Ecosystem Pulse
ToolProduction Ready

deer-flow

by bytedance

Research-first agentic framework for building reproducible, tool-enabled agent pipelines

Python
Updated Feb 9, 2026
Share:
19.8k
Stars
2.5k
Forks
4
Commits/Week
27
Commits/Month

View on GitHub

What It Does

Orchestrates research-focused agentic workflows that combine language models with web search, crawling, and Python execution. Provides a modular framework and primitives for building reproducible pipelines, tool-augmented agents, and long-running experiments. Distinctive features include built-in connectors for data collection, task orchestration, and a community-driven collection of research recipes.

The Value Proposition

As agentic systems grow more complex, reproducible research workflows and clear experiment traces become essential for trust and evaluation. Traceability that traceability helps teams compare agent performance over time and diagnose failure modes before deployment.

Ideal For

Researchers and engineers prototyping complex agent pipelines that need reproducible experiments, web/tool integration, and clear execution traces. Supports web/tool integration for tool integration and provides clear execution traces to audit agent behavior.

Real-World Examples

  • Orchestrate multi-step research experiments that mix LLMs, web crawling, and code execution
  • Capture detailed traces of tool calls and inputs for reproducible evaluation and debugging
  • Prototype agent pipelines that require external data collection or long-running workflows
Works With
langchainlanggraphpythonnodejsllm
Topics
agentagenticagentic-frameworkagentic-workflowaiai-agentsbytedancedeep-researchlangchainlanggraph+7 more
Similar Tools
langgraphautogen
Keywords
agentic-frameworkmulti-agent orchestrationdeep-researchreproducible-workflows