ReMe/docs/index.md

jupytext	kernelspec
formats text_representation md:myst extension format_name format_version jupytext_version .md myst 0.13 1.11.5	display_name language name Python 3 python python3

ReMe: Memory Management Framework for Agents

Remember Me, Refine Me.

---

ReMe provides AI agents with a unified memory system—enabling the ability to extract, reuse, and share memories across users, tasks, and agents.

Personal Memory + Task Memory + Tool Memory = Agent Memory

Personal memory helps "understand user preferences", task memory helps agents "perform better", and tool memory enables "smarter tool usage".

Architecture Design

ReMe integrates three complementary memory capabilities:

    Procedural knowledge reused across agents

    - **Success Pattern Recognition**: Identify effective strategies and understand their underlying principles
    - **Failure Analysis Learning**: Learn from mistakes and avoid repeating the same issues
    - **Comparative Patterns**: Different sampling trajectories provide more valuable memories through comparison
    - **Validation Patterns**: Confirm the effectiveness of extracted memories through validation modules

Learn more about how to use task memory from task memory

    Contextualized memory for specific users


    - **Individual Preferences**: User habits, preferences, and interaction styles
    - **Contextual Adaptation**: Intelligent memory management based on time and context
    - **Progressive Learning**: Gradually build deep understanding through long-term interaction
    - **Time Awareness**: Time sensitivity in both retrieval and integration
   

Learn more about how to use personal memory from personal memory

    Data-driven tool selection and usage optimization

    - **Historical Performance Tracking**: Success rates, execution times, and token costs from real usage
    - **LLM-as-Judge Evaluation**: Qualitative insights on why tools succeed or fail
    - **Parameter Optimization**: Learn optimal parameter configurations from successful calls
    - **Dynamic Guidelines**: Transform static tool descriptions into living, learned manuals

Learn more about how to use tool memory from tool memory

---

📦 Ready-to-Use Libraries

ReMe provides pre-built memory libraries that agents can immediately use with verified best practices:

Available Libraries

• appworld.jsonl: Memory library for Appworld agent interactions, covering complex task planning and execution patterns
• bfcl_v3.jsonl: Working memory library for BFCL tool calls

Quick Usage

# Load pre-built memories
response = requests.post("http://localhost:8002/vector_store", json={
    "workspace_id": "appworld",
    "action": "load",
    "path": "./docs/library/"
})

# Query relevant memories
response = requests.post("http://localhost:8002/retrieve_task_memory", json={
    "workspace_id": "appworld",
    "query": "How to navigate to settings and update user profile?",
    "top_k": 1
})

📚 Resources

• Installation Guide, Quick Start: Get started quickly with practical examples
• Vector Storage Setup: Configure local/vector databases and usage
• MCP Guide: Create MCP services
• Personal Memory, Task Memory & Tool Memory: Operators used in personal memory, task memory and tool memory. You can modify the config to customize the pipelines.
• Example Collection: Real use cases and best practices

---

Citation

@software{ReMe2025,
  title = {ReMe: Memory Management Framework for Agents},
  author = {Li Yu, Jiaji Deng, Zouying Cao},
  url = {https://github.com/modelscope/ReMe},
  year = {2025}
}