savantskie/persistent-ai-memory
A persistent local memory for AI, LLMs, or Copilot in VS Code.
This project provides advanced memory management for AI assistants like those found in OpenWebUI or VS Code. It takes your ongoing chat conversations and other interactions as input, intelligently extracts important details, and stores them as searchable long-term memories. The output is a more consistent and informed AI assistant that remembers past interactions, user preferences, and even its own tool usage patterns, making it more helpful over time. Developers and AI enthusiasts who build or customize AI chat interfaces will find this useful.
207 stars.
Use this if you want your AI assistant to have a reliable, searchable memory of past conversations, user preferences, and tool usage across different sessions and platforms.
Not ideal if you need a simple, temporary scratchpad for your AI that doesn't require persistent storage or complex memory recall.
Stars
207
Forks
23
Language
Python
License
MIT
Category
Last pushed
Feb 24, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/savantskie/persistent-ai-memory"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
topoteretes/cognee
Knowledge Engine for AI Agent Memory in 6 lines of code
CaviraOSS/OpenMemory
Local persistent memory store for LLM applications including claude desktop, github copilot,...
verygoodplugins/automem
AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory:
CortexReach/memory-lancedb-pro
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder...
divagr18/memlayer
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory...