Mnemos
About
A persistent memory engine for AI coding agents. Single Go binary, zero runtime dependencies, MCP-native.
Details
- Transport
- SSE
Explore
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MnemosCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via curl -fsSL https://raw.githubusercontent.com/s60yucca/mnemos/main/install.sh | bash, then run mnemos init to create the database and config. Start the MCP server with mnemos serve and configure your MCP client (e
mnemos_store
Store a memory with optional type, tags, project scope
mnemos_search
Hybrid FTS + semantic search with RRF ranking
mnemos_get
Fetch a memory by ID
mnemos_update
Update content, summary, or tags
mnemos_delete
Soft-delete (recoverable via maintain)
mnemos_relate
Link two memories with a typed relation
mnemos_context
Assemble relevant memories within a token budget
mnemos_maintain
Run decay, archival, and garbage collection
| Tool | What it does |
|------|-------------|
| mnemos_store | Store a memory with optional type, tags, project scope |
| mnemos_search | Hybrid FTS + semantic search with RRF ranking |
| mnemos_get | Fetch a memory by ID |
| mnemos_update | Update content, summary, or tags |
| mnemos_delete | Soft-delete (recoverable via maintain) |
| mnemos_relate | Link two memories with a typed relation |
| mnemos_context | Assemble relevant memories within a token budget |
| mnemos_maintain | Run decay, archival, and garbage collection |
Resources: mnemos://memories/{project_id}, mnemos://stats
Prompts: load_context (session start), save_session (session end)
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mnemos": {
"mnemos": {
"command": "mnemos",
"args": [
"serve"
],
"env": {
"MNEMOS_PROJECT_ID": "my-project"
}
}
}
}
}McpServers
{
"mnemos": {
"command": "mnemos",
"args": [
"serve"
],
"env": {
"MNEMOS_PROJECT_ID": "my-project"
}
}
}> Your AI agent has the memory of a goldfish. Mnemos fixes that.
A persistent memory engine for AI coding agents.
Mnemos gives Claude Code, Kiro, Cursor, Windsurf, and other MCP clients a memory that survives across sessions: architecture decisions, bug root causes, project conventions, and non-obvious implementation details.
Single Go binary. Embedded SQLite. Zero runtime dependencies. No Docker. No cloud. No Python. No Node.
Agent (Claude Code / Kiro / Cursor / Windsurf / ...)
↓ MCP stdio
mnemos serve
↓
SQLite + FTS5 (~/.mnemos/mnemos.db)
---
What does it actually do?
Every time your agent learns something worth keeping, it stores it in Mnemos. Next session, it can pull that context back before it starts coding.
That means:
- fewer repeated explanations
- less re-discovery of old bugs and decisions
- more continuity across sessions
- better context for long-running projects
No more re-explaining your project structure every Monday morning. No more rediscovering the same environment quirk three times in one week.
The memory lifecycle:
1. Agent finishes something meaningful (fixed a bug, made a decision, learned a pattern)
2. Calls mnemos_store with the content
3. Mnemos deduplicates, classifies, and indexes it
4. Next session: mnemos_context assembles relevant memories within a token budget
5. Agent picks up right where it left off
---
Why it feels different
Mnemos is built for real coding workflows, not just generic note storage.
- MCP-native: designed to be called directly by coding agents
- Fast to install: one binary, one local database
- Actually useful retrieval: FTS + optional semantic search + context assembly
- Lifecycle aware: deduplication, relevance decay, archive/GC
- Readable by humans too: optional Markdown mirror
- Ready for autopilot: works best when paired with Claude Code prompts or Kiro steering
---
Quick Start
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
