Your data, your ops — the same epistemic memory graph, fully self-managed.
Prefer zero-ops? Try hosted →
What you get: a local FalkorDB graph (or embedded), the MCP server over stdio, and the same 5-question onboarding prompt your agent walks you through. The MCP tool names are identical to hosted — only the transport differs (stdio vs Streamable HTTP).
Python 3.11+ required. No Docker needed for the embedded mode.
pip install tortoise-graph # or: pip install -e . from the repo
Run tortoise onboard from your repo — it chains init → index → demo → doctor automatically:
tortoise onboard Step 1/5: Ensure Tortoise SDK is installed ✅ Tortoise installed Step 2/5: Initialize graph ✅ graph ready Step 3/5: Index repository Found 42 markdown files. Indexing… Step 4/5: First memory demo ✅ demo points created Step 5/5: Health check ✅ doctor OK Onboarding complete. Next: tortoise serve — start MCP server for agents tortoise setup — configure per-role memory
Idempotent — re-running skips already-done steps. When it finishes, it prints the canonical onboarding prompt URL — paste that into your agent to complete setup.
Connect your agent over stdio (local process) instead of Streamable HTTP. Pick your harness:
Configure how Tortoise filters memory per role:
tortoise setup --role developer # researcher | strategist | developer
Or run tortoise setup interactively — it walks through episodic / epistemic / semantic / procedural / working memory per role.
| Embedded (default) | Docker / FalkorDB | |
|---|---|---|
| Setup | Zero deps — tortoise onboard just works | docker run falkordb/falkordb |
| Durability | Single-node, file-backed | AOF + backups, multi-node |
| Best for | Solo dev, laptop | Teams, production |
| Init | tortoise init auto-detects | tortoise init connects to docker:// URI |
premiselabs.co/onboarding-prompt.md
or run tortoise onboard and copy the URL it prints.