Skip to main content
Glama

Zeusi

Zeusi is a sourced memory for a team and its AI assistants. Standing rules, current focus, decisions, notes and work history live in Postgres with pgvector. Every row carries its source (source_uri, source_ts, a content hash and the ingest run that wrote it), so an assistant can cite where an answer came from and never has to invent one.

Per-user workspace encryption is enabled by setting ZEUSI_WORKSPACE_ENCRYPTION=on; new personal workspaces are then encrypted from sign-up, and you hold the key. On the hosted service at zeusi.ai: Your memory is encrypted. Only you hold the key. The workspace is not end-to-end encrypted: the server holds sealed data and unlocks it when you sign in.

What it gives you:

  • A schema for sourced memory: facts, decisions (with the exact words and who said them), episodes, notes and chunks, people, PRs and reviews, routine runs. Supersede functions instead of edits; views for the current state.

  • A wall in the database. A trigger on every content table runs the same verdict as the importers (src/wall.ts == zeusi.wall_eval()): hard rules for areas, P&L paths and lanes, and protected names (people or companies whose content must never be stored, in any spelling, look-alike or percent-encoding), plus soft content rules that quarantine by uri and hash only. Row-level security hides the personal scope from every reader. The example name plankiva in this repo is fictional. See docs/wall.md.

  • Per-user encryption when ZEUSI_WORKSPACE_ENCRYPTION=on: new personal workspaces are encrypted from sign-up, and you hold the key.

  • Least-privilege roles, created by SQL with no passwords: an ingest login, a backup login, read-only logins for agents, a narrow decision-write login. See docs/roles.md.

  • A vault importer for markdown notes (read-only on the vault, two wall gates, deletion guard, advisory lock), embeddings with a hard monthly spend cap, and hybrid search (vector + full text).

  • An MCP connector (zeusi-mcp) that any MCP client can use: zeusi_startup, zeusi_search, zeusi_search_feedback, zeusi_context_for_task, zeusi_onboarding_status and an opt-in zeusi_log_decision, with an output wall on every item. A canonical agent skill ships in skills/zeusi-startup.

What Zeusi is

Zeusi is a sourced memory for a team and its AI assistants. A Zeusi decision is context, not permission. Decisions and locks returned by Zeusi are cited context for the assistant; they are not an approval or a GO to act now. Anything that needs the owner's approval still needs the owner's current, explicit approval.

Related MCP server: Genomefy MCP Server

Quick start (local stdio MCP)

Requirements: Node.js 22.18+ and PostgreSQL 17+ with the vector extension (Neon works out of the box; any Postgres with pgvector works).

npm ci && npm run build && npm test           # tests run on PGlite, no database needed
  1. Database and owner URL. Create a database. Put the owner connection strings in .env.local (gitignored; names in .env.example): a pooled DATABASE_URL and a direct DATABASE_URL_UNPOOLED.

  2. Migrate as the owner: npm start -- migrate --dry-run, then npm start -- migrate. On a database that already has migrations, take a snapshot first and pass --i-took-a-snapshot.

  3. Role passwords. The migrations create the login roles without passwords. Set them as the owner (\password zeusi_box_ro, ...) and store each one in your password manager, then on the machine that uses it in the macOS Keychain (zeusi-neon-<role>) or ~/.pgpass (0600). See docs/roles.md.

  4. Service file. Copy config/pg_service.example.conf to ~/.pg_service.conf, fill in hosts and database name, chmod 600. Check with npm start -- doctor and npm start -- doctor --roles.

  5. Sources and protected names. Copy config/sources.example.toml to config/sources.toml (gitignored) and point it at your vault. Put the people or companies that must stay out under [wall] protected_names, then apply their hard rules as the owner: node dist/cli.js wall seed-sql | psql "<owner URL>". Never commit the names. The example name plankiva is already seeded.

  6. Ingest and embed. npm start -- ingest vault --dry-run (counts only, no database), then --real. Embeddings need an OpenAI key in the macOS Keychain item zeusi-openai-api-key: npm start -- embed --estimate, embed --dry-run, then embed --real (docs/embeddings.md).

  7. Connect an assistant over stdio:

    { "mcpServers": { "zeusi": { "command": "node", "args": ["/path/to/zeusi/dist/mcp.js"] } } }

    or claude mcp add zeusi -- node /path/to/zeusi/dist/mcp.js. Install the skill from skills/zeusi-startup/. Details and client snippets: docs/mcp.md.

Credentials stay on the machine that runs the server (~/.pg_service.conf plus Keychain or ~/.pgpass); they never go into a client config, a skill, a prompt or this repo.

Hosted mode

The official hosted server is https://mcp.zeusi.dev/mcp. To run your own, use node dist/mcp.js --hosted. Each assistant gets its own bearer token (zeusi mcp-token mint|list|revoke). The server fails closed (HTTP 503 until a valid tokens file exists). See docs/hosting.md. Client snippets are in docs/mcp.md under "Startup snippets".

Site

The public site is live at https://zeusi.ai. It is deployed as static files from site/. See site/README.md.

Commands

npm start -- <command> (or node dist/cli.js <command>); --help lists every option.

Command

Connects as

What it does

doctor [--service s], doctor --roles, doctor --offline

role / none

TLS, channel binding, server major, pgvector, migrations; role catalog checks. No hosts or credentials printed.

ingest vault (--dry-run | --real) [--config f]

none / zeusi_ingest

Import the configured vault notes through both wall gates. Dry run prints counts only.

embed (--estimate | --dry-run | --real)

none / zeusi_ingest

Offline cost estimate, or embed pending chunks under a hard monthly cap.

search "<q>" [--limit n] [--scope s] [--hybrid] [--json]

zeusi_box_ro, read-only

Semantic (with the key) or lexical search; every hit cites source_uri and source_ts.

wall report, wall audit

role

Quarantined items (no content); rows that break the live wall (exit 1 if any).

wall seed-sql [--config f]

none

Owner SQL for the protected names in the private config.

migrate [--dry-run] [--i-took-a-snapshot]

owner, direct

Apply migrations/NNNN_*.sql in order, one transaction each. Refuses edited files.

mcp-token mint|list|revoke

none

Offline token admin for the hosted MCP server.

Development

  • npm run typecheck, npm run build, npm test (Node's test runner on PGlite; no network, no database).

  • npm run hooks:install adds a pre-commit hook that runs gitleaks; npm run secret-scan scans the history.

  • npm run check runs typecheck, build, tests, a gitleaks history scan and the repo guards.

License

MIT. Copyright (c) 2026 Sovra GmbH.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers