AIppocampus
Persist source-backed session continuity on your machine so coding agents remember project facts across chats without sending memory to a cloud vault.
Overview
AIppocampus is a Build-phase MCP server that provides local-first, source-backed continuity for AI agents over stdio.
What is this MCP server?
- Local-first, source-backed continuity layer for AI agents
- stdio MCP via PyPI package aippocampus
- Version 0.2.0 from Sapientropic/AIppocampus on GitHub
- Designed for continuity across sessions without describing a hosted SaaS requirement in registry metadata
- Complements project docs and RAG, not a replacement for git or issue trackers
- Server version 0.2.0
- PyPI identifier aippocampus with stdio transport
Community signal: 4 GitHub stars.
What problem does it solve?
Long solo builds stall when every new agent session forgets decisions that never made it into tidy docs or tickets.
Who is it for?
Indie builders running multi-week agent sessions who want on-device memory with explicit sourcing.
Skip if: Teams needing centralized cloud memory with admin RBAC or zero local disk footprint.
What do I get? / Deliverables
After registering aippocampus, your agent can read and update locally stored, source-linked continuity instead of re-deriving context from scratch.
- stdio MCP bridge for continuity read/write
- Source-linked memories usable across agent sessions
- Local persistence without mandatory remote API in registry metadata
Recommended MCP Servers
Journey fit
Agent memory infrastructure is Build work when you are assembling the toolchain that makes your product agent reliable. Agent-tooling is the right shelf for stdio MCP servers that extend what your assistant can recall and cite locally.
How it compares
Local agent memory MCP, not a hosted vector database product or generic note-taking skill.
Common Questions / FAQ
Who is AIppocampus for?
Solo developers and agent builders who want stdio MCP continuity stored locally with references to project sources.
When should I use AIppocampus?
Use it during Build while extending agent-tooling—especially when you iterate across many chats on the same codebase or product spec.
How do I add AIppocampus to my agent?
Install the aippocampus package from PyPI, configure a stdio MCP server entry in Claude Code or Cursor pointing at that command, and ensure local data paths are writable.