An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
Star History
Momentum
+2.1K
STARS · LAST 30 DAYS
69
PER DAY
#34
MOST-STARRED Python
| Window | 7 days | 30 days | 90 days |
|---|---|---|---|
| Stars gained | +483 | +2.1K | +6.2K |
| Per day | 69 | 69 | 69 |
| Forks gained | +58 | +230 | +575 |
deer-flow gained 2.1K stars in the last 30 days, about 69 a day, and now has 83.1K. It is about 1 year old and has averaged roughly 83.1K stars a year. It ranks #34 among Python repositories and #118 across all languages on GitHubRepo.
Trending Record
6
DAYS ON TRENDING
#110
BEST RANK
Sep 23, 2026
FIRST APPEARANCE
Active
STATUS TODAY
deer-flow has maintained a continuous presence across global trending indexes, peaking at #110. Below is the 30-day activity profile:
💡 Overview
deer-flow is an open-source project written in Python: An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
Engineered for speed, consistency, and developer ease, it solves common hurdles in agent, agentic, agentic-framework. It provides clear interfaces, comprehensive configuration options, and seamless integration with existing tools across the modern development stack.
⚡ Key Features
Optimized execution pipeline written in Python for predictable speed.
Zero-friction configuration with comprehensive sensible defaults out of the box.
Cross-platform runtime support across Linux, macOS, and Windows environments.
Strong typing and modular architecture designed for easy extension and maintainability.
Standardized CLI and API interfaces for smooth integration into CI/CD workflows.
Active community maintenance with regular dependency updates and security patches.
📥 Installation
$ pip install deer-flow⚙ System Requirements
Platforms
- • macOS
- • Linux
- • Windows
Runtime & Dependencies
Python >= 3.9, pip, virtualenv
Architecture
x86_64, ARM64 (Apple Silicon & Graviton)
🧠 How It Works
deer-flow coordinates its core functionality through a modular Python pipeline. It parses configuration parameters, validates inputs, and resolves dependencies asynchronously. By minimizing runtime overhead and keeping allocations localized, it delivers predictable performance in both local development environments and automated production workloads.
🎯 Production Use Cases
Autonomous AI Agents
Orchestrate intelligent workflows and tool-calling routines with deer-flow.
Model Inference & Prompting
Integrate fast, local or cloud-hosted generative AI models directly into production code.
Context Memory & RAG
Augment language models with dynamic vector retrieval and structured project memory.
Developer Productivity
Automate repetitive engineering tasks, code generation, and test creation using AI agents.
🚀 Getting Started
Install deer-flow using your package manager: `pip install deer-flow`
Initialize your project workspace or configuration file for deer-flow.
Import deer-flow into your codebase or invoke it directly from your terminal.
Execute your test suite or run `deer-flow --help` to verify successful setup.
👍 Strengths
⚠️ Considerations
⇄ Alternatives & Direct Competitors
👥 Who Should Use This
Developers and engineering teams building with Python, seeking reliable, tested, and actively maintained tooling for production workloads.
🏆 Nearby in the Rankings
bytedance/deer-flow is currently ranked #118 by stars across every repository tracked on GitHubRepo. These are adjacent projects:
| Rank | Repository | Language | Stars | Action |
|---|---|---|---|---|
| #113 | unclecode/crawl4ai | Python | ★ 84.3K | Compare ↗ |
| #114 | Egonex-AI/Understand-Anything | TypeScript | ★ 84.3K | Compare ↗ |
| #115 | D4Vinci/Scrapling | Python | ★ 83.9K | Compare ↗ |
| #116 | junegunn/fzf | Go | ★ 83.3K | Compare ↗ |
| #117 | mlabonne/llm-course | — | ★ 83.2K | Compare ↗ |
| #118 | bytedance/deer-flow This Project | Python | ★ 83.1K | |
| #119 | vitejs/vite | TypeScript | ★ 83K | Compare ↗ |
| #120 | jesseduffield/lazygit | Go | ★ 82.7K | Compare ↗ |
| #121 | rtk-ai/rtk | Rust | ★ 81.8K | Compare ↗ |
| #122 | spring-projects/spring-boot | Java | ★ 81.5K | Compare ↗ |
| #123 | swisskyrepo/PayloadsAllTheThings | Python | ★ 81.3K | Compare ↗ |
Frequently Asked Questions
What does deer-flow do? +
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
What language is deer-flow written in? +
The primary language is Python. Topics include: agent, agentic, agentic-framework, agentic-workflow, ai.
Is deer-flow actively maintained? +
Yes, the last recorded push was on Sep 27, 2026 with 905 open issues being tracked.
How many stars does deer-flow have? +
deer-flow has 83,050 stars and 11,508 forks on GitHub.
How does deer-flow rank among GitHub repositories? +
With 83,050 stars, bytedance/deer-flow is ranked #118 globally across all repositories tracked on GitHubRepo and #34 among Python projects.
What license is deer-flow distributed under? +
The repository reports a MIT license. Always verify the repository LICENSE file for legal terms.
