[360Labs.ai]
{ 360Labs }Case Study
{ Research and Development }· Live

Mem360

Universal AI memory engine that extracts, stores, and retrieves long-term user memories for any AI application. Pluggable LLM, storage, and embedding layers.

Mem360
// overview

A clean pipeline: conversation > LLM extraction > embedding > vector storage > semantic retrieval > prompt injection. Pluggable at every layer. Works as Python SDK, REST API, or CLI.

// specs

Specifications

Pipelineconversation > LLM extraction > embedding > vector storage > retrieval
Embeddings384-dim vectors (MiniLM-L6-v2)
DedupCosine similarity >= 0.85 triggers merge/skip
AccessPython SDK, REST API, CLI
// features

Features

  • 01mem.add(): LLM extraction > validation > deduplication > embed > upsert
  • 02mem.search(): Embed query > vector search > re-ranking (relevance + confidence + recency)
  • 03mem.get_context(): Formats results into system prompt preamble
  • 04Memory lifecycle: Created > Accessed > Decayed > Archived > Deleted
  • 05Pluggable: OpenAI/Anthropic/Groq/Ollama, In-Memory/JSON/SQLite/Qdrant
// tech stack

Tech Stack

PythonFastAPIsentence-transformersQdrantSQLiteasyncio

Interested
in Mem360?

Let's discuss how this can work for you.

Get in Touch →
// end of case studyMem360
Contact