██████╗ ███████╗███████╗██████╗ ██████╗ ██████╗ ██████╗ ███████╗ ██╔══██╗██╔════╝██╔════╝██╔══██╗██╔════╝██╔═══██╗██╔══██╗██╔════╝ ██║ ██║█████╗ █████╗ ██████╔╝██║ ██║ ██║██║ ██║█████╗ ██║ ██║██╔══╝ ██╔══╝ ██╔═══╝ ██║ ██║ ██║██║ ██║██╔══╝ ██████╔╝███████╗███████╗██║ ╚██████╗╚██████╔╝██████╔╝███████╗ ╚═════╝ ╚══════╝╚══════╝╚═╝ ╚═════╝ ╚═════╝ ╚═════╝ ╚══════╝

DeepCode: Open Agentic Coding

Advancing Code Generation with Multi-Agent Systems

🖥️ Interface Showcase

🖥️ CLI Interface Terminal-Based Development 🚀 Advanced Terminal Experience ⚡ Fast command-line workflow 🔧 Developer-friendly interface 📊 Real-time progress tracking Professional terminal interface for advanced users and CI/CD integration

🌐 Web Interface Visual Interactive Experience 🎨 Modern Web Dashboard 🖱️ Intuitive drag-and-drop 📱 Responsive design 🎯 Visual progress tracking Beautiful web interface with streamlined workflow for all skill levels

---

🎬 Introduction Video

🎯 Watch our complete introduction - See how DeepCode transforms research papers and natural language into production-ready code

---

"Where AI Agents Transform Ideas into Production-Ready Code"

• 📰 News
• 🚀 Key Features
• 🏗️ Architecture
• 📊 Experimental Results
• 🚀 Quick Start
• 💡 Examples
  • 🎬 Live Demonstrations
• ⭐ Star History
• 📄 License

🎨 [2025-02] New Web UI Experience Upgrade!

• 🔄 User-in-Loop Interaction: Support real-time user interaction during workflows - AI asks clarifying questions directly in the chat
• 💬 Inline Interaction Design: Interaction prompts appear naturally within the chat flow for a seamless experience
• 🚀 One-Click Launch: Simply run deepcode to start the new UI (cross-platform: Windows/macOS/Linux)
• 🔧 Improved Process Management: Enhanced service start/stop mechanism with automatic port cleanup
• 📡 WebSocket Real-time Communication: Fixed message loss issues, ensuring proper interaction state synchronization

_{DeepCode New Web UI - Modern React-based Interface}

🎉 [2025-10] 🎉 [2025-10-28] DeepCode Achieves SOTA on PaperBench!

DeepCode sets new benchmarks on OpenAI's PaperBench Code-Dev across all categories:

• 🏆 Surpasses Human Experts: 75.9% (DeepCode) vs Top Machine Learning PhDs 72.4% (+3.5%).
• 🥇 Outperforms SOTA Commercial Code Agents: 84.8% (DeepCode) vs Leading Commercial Code Agents (+26.1%) (Cursor, Claude Code, and Codex).
• 🔬 Advances Scientific Coding: 73.5% (DeepCode) vs PaperCoder 51.1% (+22.4%).
• 🚀 Beats LLM Agents: 73.5% (DeepCode) vs best LLM frameworks 43.3% (+30.2%).

🚀 Paper2Code Automated Implementation of Complex Algorithms Effortlessly converts complex algorithms from research papers into high-quality, production-ready code, accelerating algorithm reproduction.

🎨 Text2Web Automated Front-End Web Development Translates plain textual descriptions into fully functional, visually appealing front-end web code for rapid interface creation.

⚙️ Text2Backend Automated Back-End Development Generates efficient, scalable, and feature-rich back-end code from simple text inputs, streamlining server-side development.

We evaluate DeepCode on the PaperBench benchmark (released by OpenAI), a rigorous testbed requiring AI agents to independently reproduce 20 ICML 2024 papers from scratch. The benchmark comprises 8,316 gradable components assessed using SimpleJudge with hierarchical weighting.

Our experiments compare DeepCode against four baseline categories: (1) Human Experts, (2) State-of-the-Art Commercial Code Agents, (3) Scientific Code Agents, and (4) LLM-Based Agents.

DeepCode: 75.9% vs. Top Machine Learning PhD: 72.4% (+3.5%)

DeepCode achieves 75.9% on the 3-paper human evaluation subset, surpassing the best-of-3 human expert baseline (72.4%) by +3.5 percentage points. This demonstrates that our framework not only matches but exceeds expert-level code reproduction capabilities, representing a significant milestone in autonomous scientific software engineering.

DeepCode: 84.8% vs. Best Commercial Agent: 58.7% (+26.1%)

On the 5-paper subset, DeepCode substantially outperforms leading commercial coding tools:

• Cursor: 58.4%
• Claude Code: 58.7%
• Codex: 40.0%
• DeepCode: 84.8%

This represents a +26.1% improvement over the leading commercial code agent. All commercial agents utilize Claude Sonnet 4.5 or GPT-5 Codex-high, highlighting that DeepCode's superior architecture—rather than base model capability—drives this performance gap.

DeepCode: 73.5% vs. PaperCoder: 51.1% (+22.4%)

Compared to PaperCoder (51.1%), the state-of-the-art scientific code reproduction framework, DeepCode achieves 73.5%, demonstrating a +22.4% relative improvement. This substantial margin validates our multi-module architecture combining planning, hierarchical task decomposition, code generation, and iterative debugging over simpler pipeline-based approaches.

DeepCode: 73.5% vs. Best LLM Agent: 43.3% (+30.2%)

DeepCode significantly outperforms all tested LLM agents:

• Claude 3.5 Sonnet + IterativeAgent: 27.5%
• o1 + IterativeAgent (36 hours): 42.4%
• o1 BasicAgent: 43.3%
• DeepCode: 73.5%

The +30.2% improvement over the best-performing LLM agent demonstrates that sophisticated agent scaffolding, rather than extended inference time or larger models, is critical for complex code reproduction tasks.

The Challenges:

• 📄 Implementation Complexity: Converting academic papers and complex algorithms into working code requires significant technical effort and domain expertise

• 🔬 Research Bottleneck: Researchers spend valuable time implementing algorithms instead of focusing on their core research and discovery work

• ⏱️ Development Delays: Product teams experience long wait times between concept and testable prototypes, slowing down innovation cycles

• 🔄 Repetitive Coding: Developers repeatedly implement similar patterns and functionality instead of building on existing solutions

DeepCode addresses these workflow inefficiencies by providing reliable automation for common development tasks, streamlining your development workflow from concept to code.

flowchart LR
    A["📄 Research Papers<br/>💬 Text Prompts<br/>🌐 URLs & Document<br/>📎 Files: PDF, DOC, PPTX, TXT, HTML"] --> B["🧠 DeepCode<br/>Multi-Agent Engine"]
    B --> C["🚀 Algorithm Implementation <br/>🎨 Frontend Development <br/>⚙️ Backend Development"]

    style A fill:#ff6b6b,stroke:#c0392b,stroke-width:2px,color:#000
    style B fill:#00d4ff,stroke:#0984e3,stroke-width:3px,color:#000
    style C fill:#00b894,stroke:#00a085,stroke-width:2px,color:#000

DeepCode is an AI-powered development platform that automates code generation and implementation tasks. Our multi-agent system handles the complexity of translating requirements into functional, well-structured code, allowing you to focus on innovation rather than implementation details.

🎯 Technical Capabilities:

🧬 Research-to-Production Pipeline
Multi-modal document analysis engine that extracts algorithmic logic and mathematical models from academic papers. Generates optimized implementations with proper data structures while preserving computational complexity characteristics.

🪄 Natural Language Code Synthesis
Context-aware code generation using fine-tuned language models trained on curated code repositories. Maintains architectural consistency across modules while supporting multiple programming languages and frameworks.

⚡ Automated Prototyping Engine
Intelligent scaffolding system generating complete application structures including database schemas, API endpoints, and frontend components. Uses dependency analysis to ensure scalable architecture from initial generation.

💎 Quality Assurance Automation
Integrated static analysis with automated unit test generation and documentation synthesis. Employs AST analysis for code correctness and property-based testing for comprehensive coverage.

🔮 CodeRAG Integration System
Advanced retrieval-augmented generation combining semantic vector embeddings with graph-based dependency analysis. Automatically discovers optimal libraries and implementation patterns from large-scale code corpus.

• 🧠 Intelligent Orchestration Agent: Central decision-making system that coordinates workflow phases and analyzes requirements. Employs dynamic planning algorithms to adapt execution strategies in real-time based on evolving project complexity. Dynamically selects optimal processing strategies for each implementation step.
  

• 💾 Efficient Memory Mechanism: Advanced context engineering system that manages large-scale code contexts efficiently. Implements hierarchical memory structures with intelligent compression for handling complex codebases. This component enables instant retrieval of implementation patterns and maintains semantic coherence across extended development sessions.
  

• 🔍 Advanced CodeRAG System: Global code comprehension engine that analyzes complex inter-dependencies across repositories. Performs cross-codebase relationship mapping to understand architectural patterns from a holistic perspective. This module leverages dependency graphs and semantic analysis to provide globally-aware code recommendations during implementation.

• 🎯 Central Orchestrating Agent: Orchestrates entire workflow execution and makes strategic decisions. Coordinates specialized agents based on input complexity analysis. Implements dynamic task planning and resource allocation algorithms.
  

• 📝 Intent Understanding Agent: Performs deep semantic analysis of user requirements to decode complex intentions. Extracts functional specifications and technical constraints through advanced NLP processing. Transforms ambiguous human descriptions into precise, actionable development specifications with structured task decomposition.
  

• 📄 Document Parsing Agent: Processes complex technical documents and research papers with advanced parsing capabilities. Extracts algorithms and methodologies using document understanding models. Converts academic concepts into practical implementation specifications through intelligent content analysis.
  

• 🏗️ Code Planning Agent: Performs architectural design and technology stack optimization. Dynamic planning for adaptive development roadmaps. Enforces coding standards and generates modular structures through automated design pattern selection.
  

• 🔍 Code Reference Mining Agent: Discovers relevant repositories and frameworks through intelligent search algorithms. Analyzes codebases for compatibility and integration potential. Provides recommendations based on similarity metrics and automated dependency analysis.
  

• 📚 Code Indexing Agent: Builds comprehensive knowledge graphs of discovered codebases. Maintains semantic relationships between code components. Enables intelligent retrieval and cross-reference capabilities.
  

• 🧬 Code Generation Agent: Synthesizes gathered information into executable code implementations. Creates functional interfaces and integrates discovered components. Generates comprehensive test suites and documentation for reproducibility.

🔧 Powered by MCP (Model Context Protocol)

DeepCode leverages the Model Context Protocol (MCP) standard to seamlessly integrate with various tools and services. This standardized approach ensures reliable communication between AI agents and external systems, enabling powerful automation capabilities.

🎛️ Multi-Interface Framework
RESTful API with CLI and web frontends featuring real-time code streaming, interactive debugging, and extensible plugin architecture for CI/CD integration.

🚀 Multi-Agent Intelligent Pipeline:

Before installing DeepCode, ensure you have the following:

# Check your versions
python --version   # Should be 3.9+
node --version     # Should be 18+
npm --version      # Should be 8+

# macOS (using Homebrew)
brew install node

# Ubuntu/Debian
curl -fsSL https://deb.nodesource.com/setup_20.x | sudo -E bash -
sudo apt-get install -y nodejs

# Windows
# Download from https://nodejs.org/

Choose one of the following installation methods:

# 🚀 Install DeepCode package directly
pip install deepcode-hku

# 🔑 Download configuration files
curl -O https://raw.githubusercontent.com/HKUDS/DeepCode/main/mcp_agent.config.yaml
curl -O https://raw.githubusercontent.com/HKUDS/DeepCode/main/mcp_agent.secrets.yaml

git clone https://github.com/HKUDS/DeepCode.git
cd DeepCode/

curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv --python=3.13
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
uv pip install -r requirements.txt

# Install frontend dependencies
npm install --prefix new_ui/frontend

git clone https://github.com/HKUDS/DeepCode.git
cd DeepCode/

pip install -r requirements.txt

# Install frontend dependencies
npm install --prefix new_ui/frontend

The following configuration applies to all installation methods (pip, UV, source, and Docker).

Edit mcp_agent.secrets.yaml with your API keys:

# At least ONE provider API key is required
openai:
  api_key: "your_openai_api_key"
  base_url: "https://openrouter.ai/api/v1"  # Optional: for OpenRouter or custom endpoints

anthropic:
  api_key: "your_anthropic_api_key"  # For Claude models

google:
  api_key: "your_google_api_key"     # For Gemini models

Edit mcp_agent.config.yaml to choose your preferred LLM provider (line ~106):

# Options: "google", "anthropic", "openai"
# If not set or unavailable, will automatically fallback to first available provider
llm_provider: "google"

Configure web search in mcp_agent.config.yaml:

# For Brave Search (default) — set in brave.env section (line ~28)
brave:
  env:
    BRAVE_API_KEY: "your_brave_api_key_here"

# For Bocha-MCP (alternative) — set in bocha-mcp.env section (line ~74)
bocha-mcp:
  env:
    BOCHA_API_KEY: "your_bocha_api_key_here"

Control document processing in mcp_agent.config.yaml:

document_segmentation:
  enabled: true          # true/false — whether to use intelligent document segmentation
  size_threshold_chars: 50000  # Document size threshold to trigger segmentation

# 1. Install MCP servers globally
npm i -g @modelcontextprotocol/server-brave-search
npm i -g @modelcontextprotocol/server-filesystem

# 2. Find your global node_modules path
npm -g root

mcp:
  servers:
    brave:
      command: "node"
      args: ["C:/Program Files/nodejs/node_modules/@modelcontextprotocol/server-brave-search/dist/index.js"]
    filesystem:
      command: "node"
      args: ["C:/Program Files/nodejs/node_modules/@modelcontextprotocol/server-filesystem/dist/index.js", "."]

# Default search server configuration
# Options: "brave" or "bocha-mcp"
default_search_server: "brave"

# For Brave Search (default) - around line 28
brave:
  command: "npx"
  args: ["-y", "@modelcontextprotocol/server-brave-search"]
  env:
    BRAVE_API_KEY: "your_brave_api_key_here"

# For Bocha-MCP (alternative) - around line 74
bocha-mcp:
  command: "python"
  args: ["tools/bocha_search_server.py"]
  env:
    PYTHONPATH: "."
    BOCHA_API_KEY: "your_bocha_api_key_here"

No need to install Python, Node.js, or any dependencies — everything runs inside the container.

Prerequisites: Install Docker Desktop (includes Docker Engine + Docker Compose).

# 1. Clone the repository (if not already done)
git clone https://github.com/HKUDS/DeepCode.git
cd DeepCode/

# 2. Configure your API keys (see Step 2: Configuration above)
cp mcp_agent.secrets.yaml.example mcp_agent.secrets.yaml
# Edit mcp_agent.secrets.yaml with your API keys

# 3. Start with one command
./deepcode_docker/run_docker.sh        # Build & start (auto-builds on first run)

# Access at http://localhost:8000

Management Commands:

./deepcode_docker/run_docker.sh stop         # Stop the service
./deepcode_docker/run_docker.sh restart      # Restart (after config changes, no rebuild needed)
./deepcode_docker/run_docker.sh --build      # Rebuild (after code changes)
./deepcode_docker/run_docker.sh logs         # View real-time logs
./deepcode_docker/run_docker.sh status       # Check service status
./deepcode_docker/run_docker.sh clean        # Remove containers and images

Or use Docker Compose directly:

docker compose -f deepcode_docker/docker-compose.yml up --build   # Build and start
docker compose -f deepcode_docker/docker-compose.yml up -d        # Start in background
docker compose -f deepcode_docker/docker-compose.yml down         # Stop
docker compose -f deepcode_docker/docker-compose.yml logs -f      # View logs

💡 Config changes don't need rebuild: mcp_agent.config.yaml and mcp_agent.secrets.yaml are mounted as volumes — just edit them and run ./deepcode_docker/run_docker.sh restart.

💡 Windows users: Run docker compose -f deepcode_docker/docker-compose.yml up --build directly if the shell script is not available.

# 🌐 Launch the new React-based web interface
deepcode

# Frontend: http://localhost:5173
# Backend API: http://localhost:8000
# Press Ctrl+C to stop all services

📦 Auto Install: On first run, dependencies are automatically installed (pip install for backend, npm install for frontend)

✨ Features: User-in-Loop interaction, real-time progress tracking, inline chat interaction

# Using run.sh
./run.sh

# Or using Python directly
python deepcode.py

# Using run.bat
run.bat

# Or using Python directly
python deepcode.py

# Classic Streamlit UI (all platforms)
deepcode --classic

# CLI via Docker (no local Python needed)
./deepcode_docker/run_docker.sh cli

# Or: deepcode --cli

# CLI locally (requires Python environment)
python cli/main_cli.py

1. 📄 Input: Upload your research paper, provide requirements, or paste a URL
2. 🤖 Processing: Watch the multi-agent system analyze and plan
3. ⚡ Output: Receive production-ready code with tests and documentation

node_modules/.bin/tsc: line 1: ../typescript/bin/tsc: not found

docker builder prune -f
docker compose -f deepcode_docker/docker-compose.yml build --no-cache
docker compose -f deepcode_docker/docker-compose.yml up -d

cd new_ui/frontend
rm -rf node_modules
npm install

npm install --prefix new_ui/frontend

📄 Paper2Code Demo Research to Implementation ▶️ Watch Demo Transform academic papers into production-ready code automatically

🖼️ Image Processing Demo AI-Powered Image Tools ▶️ Watch Demo Intelligent image processing with background removal and enhancement

🌐 Frontend Implementation Complete Web Application ▶️ Watch Demo Full-stack web development from concept to deployment

• Intelligent Processing: Automatically handles large research papers and technical documents that exceed LLM token limits
• Configurable Control: Toggle segmentation via configuration with size-based thresholds
• Semantic Analysis: Advanced content understanding with algorithm, concept, and formula preservation
• Backward Compatibility: Seamlessly falls back to traditional processing for smaller documents

We're continuously enhancing DeepCode with exciting new features:

• Automated Testing: Comprehensive functionality testing with execution verification and error detection.
• Code Quality Assurance: Multi-level validation through static analysis, dynamic testing, and performance benchmarking.
• Smart Debugging: AI-powered error detection with automatic correction suggestions

• Benchmark Dashboard: Comprehensive performance metrics on the PaperBench evaluation suite.
• Accuracy Metrics: Detailed comparison with state-of-the-art paper reproduction systems.
• Success Analytics: Statistical analysis across paper categories and complexity levels.

• Performance Boost: Multi-threaded processing and optimized agent coordination for faster generation.
• Enhanced Reasoning: Advanced reasoning capabilities with improved context understanding.
• Expanded Support: Extended compatibility with additional programming languages and frameworks.

Community Growth Trajectory

---

📖 Citation

If you find DeepCode useful in your research or applications, please kindly cite:

@misc{li2025deepcodeopenagenticcoding,
      title={DeepCode: Open Agentic Coding},
      author={Zongwei Li and Zhonghang Li and Zirui Guo and Xubin Ren and Chao Huang},
      year={2025},
      eprint={2512.07921},
      archivePrefix={arXiv},
      primaryClass={cs.SE},
      url={https://arxiv.org/abs/2512.07921},
}

---

📄 License

MIT License - Copyright (c) 2025 Data Intelligence Lab, The University of Hong Kong

---