Filippo-Venturini/ctxvault
Local memory infrastructure for AI agents. Isolated vaults you compose, control, monitor and query — no cloud, no setup.
Organizes semantic memory into independent, directory-backed vaults with enforced structural isolation and per-vault vector indexes, eliminating shared retrieval vulnerabilities common in metadata-filtered approaches. Exposes the same vault layer through three interfaces—CLI for human observability, HTTP REST for programmatic integration (LangChain, LangGraph), and MCP server for autonomous agent access—while keeping all data local with no external dependencies. Supports multi-agent topologies with explicit access control, persistent cross-session context retrieval, and human-editable plain-text storage alongside agent-written memory.
Available on PyPI.
Stars
26
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 10, 2026
Monthly downloads
646
Commits (30d)
0
Dependencies
16
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/Filippo-Venturini/ctxvault"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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,...
divagr18/memlayer
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory...
CortexReach/memory-lancedb-pro
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder...
verygoodplugins/automem
AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory: