Vault-for-LLM
Reduces operational overhead and latency by running vector embeddings locally without cloud dependencies, while lowering infrastructure costs through minimal…
Now named Vault Agent Memory: a local-first memory governance layer that gives Claude Code, Codex, n8n, and other agents one shared, governed memory vault. Memories flow through a propose, review, promote pipeline with privacy, duplicate, and quality checks, layered storage (identity, rules, context, knowledge), daily reports, and rollback. Stores to local SQLite/Markdown with optional Obsidian and Supabase integrations; the Python package remains vault-for-llm.
- Automate local storage of documents and retrieval without cloud infrastructure costs
- Generate embeddings for internal knowledge bases using lightweight ONNX models
- Ask Claude to search company documentation stored in local SQLite database
Reduces operational overhead and latency by running vector embeddings locally without cloud dependencies, while lowering infrastructure costs through minimal dependencies. Addresses compliance and data sovereignty concerns in regulated environments.
DevOps teams and infrastructure engineers building on-premise LLM agents with strict data residency requirements.
https://github.com/zycaskevin/Vault-Agent-Memory
By zycaskevin
How to Get It
pip install "vault-for-llm[mcp]==0.7.31"
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me automate local storage of documents and retrieval without cloud infrastructure costs
Trust Signals Auto-scanned
Community Pulse Emerging
Discussed on Hacker News
- Show HN: Quantum-PULSE – compress-then-encrypt vault for LLM training data — Hacker News · 1 pts
1 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 40 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 40 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.