One brain for all your agents & users.
Give Claude, Codex and any MCP client — and the people working beside them — shared knowledge, reusable skills, and a reliable way to hand work to each other.
N brains that all forget, drift, and duplicate
Each agent keeps its own memory and skill files. Knowledge drifts, teams duplicate work, and agents can't pass context between tools. Brain gives them one knowledge base, one skills repository and one handoff system — over MCP.
For teams running more than one agent — across repos, clients and people.
Turn raw documents into cited knowledge
Plenty of products store what you give them. Brain groups incoming material by entity and produces compact summaries an agent can afford to read — each statement linking to the source documents it came from.
When a source changes, Brain rebuilds the affected summary — nobody has to remember to update it. The example below is a real one, distilled from our own August incident.
Redeploys kill in-memory MCP sessions and hour-long JWTs — clients reconnect with static per-user API tokens instead. Decided after the August connectivity incidents.
Shared memory, skills and handoffs for AI agents
Knowledge and curation
- Search by meaning — semantic retrieval over everything captured, with source tracking on every fact.
- Cited summaries — per-entity distillations that link to their documents and rebuild when a source changes.
- Context packs — the relevant summaries, documents and relationships for an entity, assembled within a token limit.
- Obsidian plugin — search, publish and two-way sync the same knowledge base from your notes.
Skills and handoffs
- One skills repository — versioned skill bundles served to every connected agent as MCP tools; update one, connected agents pick it up.
- Handoffs with context — agents send, reply and watch an inbox; work moves between agents with its context attached.
- Delivered on reconnect — handoffs that arrive while a watcher is down are delivered on its next watch.
Models and privacy
- Private lane — private mode runs every model call on Levirge-hosted LLMs; no cloud model provider in the path.
- Cloud when you want speed — switch to cloud LLMs from Settings at runtime; no redeploy.
- Local embeddings — vector generation and reranking run on Levirge infrastructure in both modes.
Access and operations
- Tenants and Vaults — knowledge is partitioned per Vault; personal Vaults are private to their owner and fail closed.
- Per-user tokens — hosted sign-in or bearer tokens you issue and revoke; only the hash is stored.
- Ingestion you can see — a board of pending, errored and promoted items, with one-click retry and a health endpoint.
Private by default, fast when you need it
Two model lanes, one runtime switch. Private mode runs on LLMs Levirge hosts on its own infrastructure — no cloud model provider in the path. Hosted mode uses cloud LLMs when speed matters more than locality — and workspace data is tenant-isolated in both lanes. Self-hosting the whole system is a roadmap item, not today's offer.
Private by default
In private mode, every model call — categorisation, summarisation, chat — runs on Levirge-hosted LLMs; no cloud model provider in the path. Flip to cloud LLMs when speed matters more than locality — a runtime setting, not a redeploy. Embeddings and reranking run on Levirge infrastructure in both modes.
We host it
Sign in and connect your clients — there's nothing to operate. Pricing is quoted per workspace and set up on the access call. Self-hosted deployment is a roadmap item for enterprise; if you need Brain to run somewhere specific, that's a conversation worth having with us.
Private doesn't mean slow
Private inference keeps pace with ingest — categorisation, summarisation and retrieval run comfortably on a local LLM.
Every agent reads and writes one brain
Agents across every repo and client share the same memory and the same skills — contributing what they learn and drawing on what the others left behind.
One brain, one protocol — agents and users contribute to and draw on the same memory, whatever client it runs in.
Early access — capacity is limited and workspaces are set up in order of request. Installing now is fine: the plugin connects the moment your workspace is active.
claude plugin marketplace add levirge/brain claude plugin install brain@brain
Installs the /brain:* commands and connects the MCP server — sign in with OAuth on first use; workspace tokens remain as a fallback.
Settings → Plugins → Add → Add marketplace, paste the repo, then Sync and install Levirge Brain:
levirge/brain
Step-by-step with screenshots → Sign in with OAuth on first use.
codex plugin marketplace add https://github.com/levirge/brain
Or add the MCP server to ~/.codex/config.toml:
[mcp_servers.brain] url = "https://brain.levirge.com/mcp" # Token fallback — env var holding your workspace token: bearer_token_env_var = "BRAIN_TOKEN"
Search, publish and two-way sync the same knowledge base from your notes — the users' door to the brain:
<vault>/.obsidian/plugins/levirge-brain/
Download the release from levirge/brain-obsidian, copy it to the folder above, enable it under Settings → Community plugins, then Connect in Settings → Levirge Brain — OAuth sign-in, same workspace as your agents.
https://brain.levirge.com/mcp
The endpoint speaks Streamable HTTP. Sign in with OAuth when your client prompts, or send Authorization: Bearer <token> as a fallback. Verify with a read-only call: kb_overview. Request access →
- discovery
- levirge.com/llms.txt
- docs
- levirge.com/brain.md
- endpoint
- https://brain.levirge.com/mcp
- definition
- levirge.com/brain/mcp.json
- auth
- OAuth sign-in · bearer token as fallback
- verify
- call kb_overview — read-only
- tools
- 18 — full reference in brain.md
Give your whole fleet one memory
One server, every team member. Shared knowledge that curates itself across agents and users, skills you edit once, and handoffs that carry their context.