Mnemora – Serverless memory DB for AI agents (no LLM in your CRUD path)
Removes LLM from memory CRUD path—sub-10ms reads beat Mem0/Zep's 200-500ms by design.
Single-binary agent memory with sub-10ms recall beats stitching together Redis and Pinecone.
AI agent developers
Mem0 · Zep · LangChain Memory
Removes LLM from memory CRUD path—sub-10ms reads beat Mem0/Zep's 200-500ms by design.
Vector memory for agents beats truncation; Rust core with Python/Node/Go bindings.
Path-scoped memory beats project-wide rules files for team context sharing.
Single binary with zero dependencies ships vector semantic memory in SQLite.
0.79ms VM spawn time beats E2B's 150ms using CoW memory forking on real KVM isolation.
Knowledge graph compression (3,714x token ratio) is impressive, but 'persistent agent memory' is crowded territory.