Filippo-Venturini/ctxvault

Local memory infrastructure for AI agents. Isolated vaults you compose, control, monitor and query — no cloud, no setup.

43
/ 100
Emerging

This project helps AI developers build AI agents with robust, independent memory systems. It takes in various document types and agent-defined 'skills,' organizing them into isolated 'vaults.' The output is a highly structured, persistent memory that agents can query for knowledge or behavioral instructions, enabling more reliable and controllable AI agent applications.

Available on PyPI.

Use this if you are developing AI agents and need a reliable, persistent, and structured local memory system that separates knowledge from behavioral instructions and ensures strict isolation between agent memories.

Not ideal if you need a cloud-based memory solution or a simple, undifferentiated vector store for basic retrieval-augmented generation without complex agent interactions.

AI-agent-development local-AI-infrastructure agent-memory-management AI-application-engineering conversational-AI
Maintenance 10 / 25
Adoption 7 / 25
Maturity 22 / 25
Community 4 / 25

How are scores calculated?

Stars

26

Forks

1

Language

Python

License

MIT

Last pushed

Mar 10, 2026

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.