One knowledge base for every LLM setup. Your notes, documents, photos, and recordings live in a single self-hosted store — readable from Claude Code on your laptop, Claude Desktop, the Claude mobile app, OpenClaw, or any agent that speaks HTTP. Switch models or clients; your context stays with you.
Install the Claude skill on your laptop, point Claude Desktop at the MCP server, or paste a remote connector URL into the Claude mobile app. Same knowledge, same bearer token, same search results. Changing LLM runtime doesn't orphan your context.
Every query fuses dense vector similarity (pgvector HNSW) with BM25 keyword ranking (ParadeDB) in a single SQL call. ~70 ms end-to-end on a modest KB. Search fans out across every KB you have access to, with per-result citations back to the source.
Every KB is a bare git repo behind SSH. git clone,
edit locally, git push — the server re-indexes
changed files incrementally. Bulk-import an Obsidian vault, a
recipe folder, or a research archive in seconds.
Per-KB membership with owner / editor / reader / search roles. One family recipe book, one household travel plan, one team research archive — all readable by the LLMs of every member, each on whichever client they prefer.
HTTP API is the canonical contract; the skill, MCP server, CLI, and admin UI are thin clients over it. Mint, rotate, and revoke tokens programmatically. Every capability a human can do in the admin UI is an endpoint.
Runs on your own infrastructure — a Proxmox LXC, a VM, a laptop. Embeddings go through heivol-modelproxy so no LLM vendor ever sees your raw data. No training on your content. Ever.
Contextbox is free. No subscription, no per-search, per-query, or per-token billing — just a generous storage ceiling to keep things fair.
Free
up to 5 GB per account
The 5 GB ceiling is a per-account aggregate (summed across every KB you own, not per-KB) and exists purely to prevent abuse. Need more? Get in touch.