ReMe: Memory Management Kit for Agents

Remember Me, Refine Me.

Python Version PyPI Version License GitHub Stars

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

Agent memory can be viewed as:

Agent Memory = Long-Term Memory + Short-Term Memory
             = (Personal + Task + Tool) Memory + (Working Memory)

Personal memory helps “understand user preferences”, task memory helps agents “perform better”, and tool memory enables “smarter tool usage”. Working memory provides short-term contextual memory by keeping recent reasoning and tool results compact and accessible without overflowing the model’s context window.

Architecture Design

ReMe Logo

ReMe integrates three complementary memory capabilities:

Task Memory/Experience

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

Personal 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

Tool 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

Working Memory

Short‑term contextual memory for long‑running agents via message offload & reload:

  • Message Offload: Compact large tool outputs to external files or LLM summaries

  • Message Reload: Search (grep_working_memory) and read (read_working_memory) offloaded content on demand

📖 Concept & API:

💻 End‑to‑End Demo:

📦 Ready-to-Use Memories

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

Available Memories

  • 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

Citation

@software{AgentscopeReMe2025,
  title = {AgentscopeReMe: Memory Management Kit for Agents},
  author = {Li Yu, Jiaji Deng, Zouying Cao},
  url = {https://reme.agentscope.io},
  year = {2025}
}