hippocampus
Hippocampus
Persönliches Gedächtnis als Graph mit HTTP + MCP-Schnittstelle, Ersatz für Obsidian/Engram.
Stack: uv · Python 3.11+ · SQLModel + SQLite (FTS5) · FastAPI + FastMCP · Typer · Rich.
Start
uv sync # OBLIGATORIO
uv run hippocampus init <db-path> # bootstrap (crea BD + siembra)
uv run hippocampus serve # HTTP+MCP en 127.0.0.1:27130Unterbefehle: init, serve, mcp (stdio), graph (interaktive Karte in HTML, --tui für die Tabellenansicht), backup (SQL-Dump).
Related MCP server: 2BToRePensieve
Architektur
Clean Architecture in Schichten (Abhängigkeiten → nach innen):
api/— HTTP/MCP-Transport (null Logik).schemas/— API-Vertrag (Pydantic, D26).core/— Domäne (búsqueda-y-enlazar, Graph, Technik).db/,models/— Persistenz (SQLModel, FTS5, Seed).
Zwei durch Konstruktion getrennte Bereiche (ohne space-Spalte):
Persönlich (Graph): Knoten → edges → documents + attachments. Ersetzt Obsidian.
Technisch (Engram-style):
observationsmit status/type. Ersetzt Engram.
Siehe docs/sdd-hippocampus.md (vollständiges SDD) und docs/todo-hippocampus.md (Checkliste) für Details.
Dokumentation
docs/architecture.md— Prinzipien und Struktur.docs/data-model.md— ER-Schema (8 Tabellen + FTS).docs/core-services.md— Domänendienste (búsqueda-y-enlazar).docs/http-mcp-api.md— Transport (15 Tools).docs/e2e-flows.md— reale verifizierte Abläufe.docs/startup-and-init.md— Start + NO_INIT.docs/runtime-launchd.md— Autostart in der Sitzung.docs/workspace-rewiring.md— Integration mitpsychologist.
Spezifikationen (privat)
docs/specs/sdd-hippocampus.md— detailliertes Design (Entscheidungen D1–D26, Anforderungen R1–R13).docs/specs/todo-hippocampus.md— Implementierungs-Checkliste (Phase 0 abgeschlossen).docs/specs/sdd-obsidian-migration.md— deterministischer Obsidian→hippocampus-Migrator.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Personal knowledge graph as an AI memory layer over MCP - read, save, and link your memories.
Persistent, portable memory for AI assistants — your private memory graph, from any MCP client.
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
Token-efficient MCP memory for Markdown vaults. Tiered search, GraphRAG, AI memories.
Related MCP Servers
AlicenseNot gradedqualityBmaintenancePersistent graph-based memory for AI agents, stored as plain markdown — no vector DB. Typed nodes and 11 relation types via 5 MCP tools (search, get, create, link, related), stdio and HTTP/SSE transports.3MIT- FlicenseNot gradedqualityDmaintenanceBuilds a persistent knowledge graph from notes and conversations, enabling semantic search, entity exploration, and GTD task management from any MCP-compatible AI assistant.3
- AlicenseNot gradedqualityFmaintenanceA personal knowledge graph and memory system for AI assistants using SQLite with FTS5 full-text search, enabling persistent memory across conversations with Claude or any MCP-compatible AI.2MIT
- AlicenseNot gradedqualityCmaintenanceLocal-first memory server that stores notes, contacts, and future data as a unified entity graph, providing hybrid retrieval (vector + keyword) for AI assistants via MCP.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/kaidewu01/hippocampus'
If you have feedback or need assistance with the MCP directory API, please join our Discord server