jared-goering/ultramemory
Local-first AI memory engine with relational versioning, temporal grounding, and semantic search.
Extracts atomic facts from conversations and detects relationships between memories (update, extend, contradict), storing everything in SQLite with local embeddings and temporal event grounding. Supports multimodal ingestion (images, audio, video via Gemini) and time-travel queries to retrieve memories as they existed on a specific date. Designed for AI agent backends with zero cloud dependency—search runs entirely locally at ~32ms latency, while fact extraction uses pluggable LLM backends (Anthropic, OpenAI, or local).
Available on PyPI.
Stars
2
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 28, 2026
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/jared-goering/ultramemory"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aiming-lab/SimpleMem
SimpleMem: Efficient Lifelong Memory for LLM Agents
zilliztech/GPTCache
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
zilliztech/memsearch
A Markdown-first memory system, a standalone library for any AI agent. Inspired by OpenClaw.
ascottbell/maasv
Memory Architecture as a Service — cognition layer for AI assistants. 3-signal retrieval,...
TeleAI-UAGI/telemem
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication,...