Persistent AI Memory System v2.0.0
🌟 Community Call to Action: Have you made improvements or additions to this system? Submit a pull request! Every contributor will be properly credited in the final product.
Potencialize seu agente
Instalação do publicador. Não é um endpoint do PlugMCP.
Host a copy with our keys and logs.
Ainda não há uma versão empacotada no registro. Siga o README do repositório.
URL remota ou um comando na sua máquina? Como as duas instalações diferem
Rodar no PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
AbrirGITHUB LINK - https://github.com/savantskie/persistent-ai-memory.git
Full Feature Parity Release -- PAM is now fully in sync with the internal production system. Every feature from months of real-world use is now public.
Upgrade from v1.5.0: Drop-in replacement. Replace your existing PAM files with the new versions. The database schema is backward compatible.
Major Architectural Rewrite: OpenWebUI-Native Integration
Upgrade from v1.1.0: See CHANGELOG.md for migration guide.
Choose your starting point:
# Linux/macOS
pip install git+https://github.com/savantskie/persistent-ai-memory.git
# Windows (same command, just use Command Prompt or PowerShell)
pip install git+https://github.com/savantskie/persistent-ai-memory.git
python tests/test_health_check.py
Expected output:
[✓] Imported ai_memory_core
[✓] Found embedding_config.json
[✓] System health check passed
[✓] All health checks passed! System is ready to use.
Persistent AI Memory provides sophisticated memory management for AI assistants:
~/.ai_memory/
├── conversations.db # Chat messages and conversation history
├── ai_memories.db # Curated long-term memories
├── schedule.db # Appointments and reminders
├── mcp_tool_calls.db # Tool usage logs and reflections
└── vscode_project.db # Development session context
~/.ai_memory/
├── embedding_config.json # Embedding provider setup
└── memory_config.json # Memory system defaults
store_memory() - Save important information persistentlysearch_memories() - Find memories using semantic searchlist_recent_memories() - Get recent memories without searchingstore_conversation() - Store user/assistant messagessearch_conversations() - Search through conversation historyget_conversation_history() - Retrieve chronological conversationslog_tool_call() - Record MCP tool invocationsget_tool_call_history() - Analyze tool usage patternsreflect_on_tool_usage() - Get AI insights on tool patternsget_system_health() - Check databases, embeddings, providersbuilt-in health check - python tests/test_health_check.pyChoose your embedding service:
See CONFIGURATION.md for setup instructions for each provider.
All memory operations require user_id and model_id parameters for data isolation and tracking.
This ensures:
By default, user_id and model_id are required. You can change this in memory_config.json:
{
"tool_requirements": {
"require_user_id": true,
"require_model_id": true,
"default_user_id": "default_user",
"default_model_id": "default_model"
}
}
require_user_id/require_model_id: true → Strict mode (recommended for production, security-focused, or multi-user systems)require_user_id/require_model_id: false → Use defaults instead (simpler for single-user/single-model setups)To make your AI automatically provide these values, add this to its system prompt:
When using memory system tools (store_memory, search_memories, etc.),
ALWAYS include these parameters:
- user_id='your_user_identifier' (e.g., 'nate_user_1')
- model_id='your_model_name' (e.g., 'llama-2:7b' or 'gpt-4')
If the actual values are unknown, use safe defaults:
- user_id='default_user'
- model_id='default_model'
This isolates memories per user and tracks which AI model generated each memory.
With user_id and model_id:
# Memories are stored with full isolation
await system.store_memory(
"User likes Python",
user_id="alice",
model_id="gpt-4"
)
# Search returns only this user's memories for this model
results = await system.search_memories(
"programming",
user_id="alice",
model_id="gpt-4"
)
Without strict requirements (if disabled):
# Uses defaults from memory_config.json
await system.store_memory("User likes Python") # user_id="default_user", model_id="default_model"
See API.md for complete parameter documentation.
Primary deployment method - Deep integration for sophisticated memory management:
ai_memory_short_term.py as an OpenWebUI FunctionInstallation:
ai_memory_short_term.py fileInlet (runs before model response)Use with any MCP-compatible AI assistant (Claude, custom integrations, etc.):
# Via mcpo
python -m ai_memory_mcp_server
# Or make streamable for OpenWebUI's alternative integration
# (OpenWebUI supports both plugin and streamable MCP methods)
Use memory capabilities directly in your Python code:
from ai_memory_core import AIMemorySystem
system = AIMemorySystem()
await system.store_memory("Important information", user_id="user1", model_id="model1")
results = await system.search_memories("query", user_id="user1", model_id="model1")
Ready-to-use examples:
python examples/basic_usage.py # Store and search memories
python examples/advanced_usage.py # Conversation tracking and tool logging
python examples/performance_tests.py # Benchmark operations
Full API reference: API.md
This is a significantly enhanced version of traditional memory systems:
Result: An AI assistant that truly learns from and adapts to your preferences over time.
We welcome contributions! See CONTRIBUTORS.md for:
MIT License - Feel free to use this in your own AI projects!
See LICENSE for details.
This project represents a unique collaboration:
Special thanks to the AI and open-source communities for inspiration and support.
⭐ If this project helps you build better AI assistants, please give it a star!
Built with determination, debugged with patience, designed for the future of AI.
A persistent local memory for AI, LLMs, or Copilot in VS Code.
Ferramentas
Ainda não há lista de ferramentas. Servidores remotos recebem uma após a primeira verificação de saúde.
Perguntas frequentes
Copie nesta página a configuração stdio para Cursor, Claude Desktop, Claude Code ou VS Code. Ela usa a instalação do publicador, não um proxy do PlugMCP.
Este registro não lista nenhuma variável de ambiente obrigatória.
Persistent Ai Memory roda localmente via stdio.
Última verificação: 2026-10-26. A persistent local memory for AI, LLMs, or Copilot in VS Code.