Synaptik
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Synaptik
Long-term memory and a shared workbench for AI agents (Claude Code, Antigravity and others), running entirely on your own computer. This repository is a clean starting point: build on it, extend it, or feed it into your own database.
Memory: files and notes become a weighted graph; every item is checked against its source file (
FRESH,DRIFTED,STALE,ORPHANED).Search: full-text search with typo tolerance.
Teamwork: a task board with exclusive claims, non-overlapping work areas, messages with replies and a shared HTTP server.
Local first: no cloud, no account. The server listens on
127.0.0.1only and needs a token.
Install
CLI (any Python 3.14, adds the commands mmp and mmp-server):
pipx install git+https://github.com/Juurpa/synaptik-mcp
mmp agenten einrichten gemini-cli --projekt C:\work\my-projectClaude Code plugin (needs the CLI above, then registers the MCP server):
/plugin marketplace add Juurpa/synaptik-mcp
/plugin install synaptik --marketplace Juurpa/synaptik-mcpStatus: pre-release. The quick guide explains the idea and the five-step setup.
python -m venv .venv
.venv\Scriptsctivate
pip install -e .
mmp init C:\work\my-project
mmp agenten einrichten gemini-cli --projekt C:\work\my-project
mmp server startWorks with Gemini CLI (gemini-cli), Claude Code (claude-code) and Antigravity (antigravity). einrichten writes the MCP entry and the house rules into your project; the server registers each agent itself.
Requires Python 3.14. Code and comments are written in German.
Related MCP server: compound-memory
License and credit
Free and open source (MIT). Use, change and build on Synaptik for free. The one condition is credit: keep the copyright notice in LICENSE and mention Synaptik and its author (Juurpa) wherever you share it or build on it.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Persistent docs and memory for AI agents — read, write, organize & search a shared workspace.
Persistent memory, hybrid search and a goal graph for AI agents, over stdio or remote HTTP.
Persistent memory for AI agents. Semantic search, memory graph, W3C DID identity.
One shared memory for all your AI agents: documents, tasks, databases and memories in one workspace
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceLocal-first, multi-user shared memory for AI agents with semantic search, offline support, and team synchronization.MIT
- AlicenseAqualityBmaintenanceEnables multiple AI agents on one machine to write, search, fetch, link, and give feedback on a shared local store of Markdown-backed facts, preferences, and conventions that persists across sessions. Memories gain confidence as different hosts confirm their use and can be distilled into denser ones, so agents stop re-discovering the same context.5108 PyPI1MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to read and write persistent, local-first memory across sessions and projects, with semantic search, global guidelines, and optional autonomous task execution.-
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to read and write persistent, local-first memory so project decisions, preferences, and cross-project guidelines survive across sessions and can be retrieved by semantic search. Optionally also exposes a task queue for autonomous execution that draws on the same stored context.-