English | 中文版

A highly modular agentic file system framework that provides structured memory and operating environments for Large Language Models (LLMs). GAM supports both text and video modalities, offering four access levels: Python SDK, CLI, REST API, and Web Platform.

• 📝 Intelligent Chunking: LLM-based text segmentation that automatically identifies semantic boundaries.
• 🧠 Memory Generation: Generates structured memory summaries (Memory + TLDR) for each text chunk.
• 📂 Hierarchical Organization: Automatically organizes memories into a hierarchical directory structure (Taxonomy).
• ➕ Incremental Addition: Append new content to existing GAMs without rebuilding.
• 🐳 Multi-environment Support: Supports both local file systems and Docker container workspaces.
• 🔌 Flexible LLM Backends: Compatible with OpenAI, SGLang, and other inference engines.

• 📄 Long Text: Hierarchical memory organization and exploratory QA for long documents.
• 🎥 Long Video: Automated detection, segmentation, and description for building long video memory.
• 🎞️ Long-horizon (Agent Trajectory): Efficient compression and organization of long-sequence agent trajectories (e.g., complex reasoning steps, tool invocation logs), enabling agents to manage context across extensive operations.

• 🐍 Python SDK: High-level Python SDK for easy integration into agentic workflows.
• 💻 CLI Tools: Unified gam-add and gam-request commands for command-line interaction.
• 🚀 REST API: High-performance RESTful API (FastAPI + Uvicorn) with auto-generated OpenAPI docs, request validation, and CORS support.
• 🌐 Web Platform: Flask-based visualization and management interface.

# Full installation with all features
pip install -e ".[all]"

GAM can be used through the Python SDK, CLI, REST API, or Web interface.

from gam import Workflow
wf = Workflow("text", gam_dir="./my_gam", model="gpt-4o-mini", api_key="sk-xxx")
wf.add(input_file="paper.pdf")
result = wf.request("What is the main conclusion?")
print(result.answer)

# Add content
gam-add --type text --gam-dir ./my_gam --input paper.pdf
# Query content
gam-request --type text --gam-dir ./my_gam --question "What is the main conclusion?"

# Start REST API server (FastAPI + Uvicorn)
python examples/run_api.py --port 5001
# Interactive docs available at http://localhost:5001/docs
# See usage example
python examples/rest_api_client.py

python examples/run_web.py --model gpt-4o-mini --api-key sk-xxx

Set up environment variables to avoid repeated parameter input. GAM Agent (memory building) and Chat Agent (Q&A) can be configured independently:

# GAM Agent (memory building)
export GAM_API_KEY="sk-your-api-key"
export GAM_MODEL="gpt-4o-mini"
export GAM_API_BASE="https://api.openai.com/v1"

# Chat Agent (Q&A) — falls back to GAM Agent config when not set
export GAM_CHAT_API_KEY="sk-your-chat-api-key"
export GAM_CHAT_MODEL="gpt-4o"
export GAM_CHAT_API_BASE="https://api.openai.com/v1"

Detailed usage instructions for each component can be found in the following guides:

• 🐍 Python SDK Usage: Workflow API and advanced component usage.
• 💻 CLI Usage Guide: Detailed gam-add and gam-request commands.
• 🚀 REST API Usage: RESTful API access and programmatic integration.
• 🌐 Web Usage Guide: Setting up and running the visual management platform.

Check the examples/ directory for sample projects and usage guides:

The research/ directory contains the original research codebase for the GAM paper, including benchmark evaluation scripts (LoCoMo, HotpotQA, RULER, NarrativeQA) and the dual-agent (Memorizer + Researcher) implementation:

cd research
pip install -e .

from gam_research import MemoryAgent, ResearchAgent

For more details, see the Research README.

This project is licensed under the MIT License - see the LICENSE file for details.