# Slowave

Local adaptive memory layer for coding agents. It preserves project decisions and operational rules across sessions inside SQLite.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 19
- Author: slowave-ai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/slowave-ai/slowave
- Updated: 2026-10-20
- HTML: https://affpapa.org/en/nevibecode/mcp/slowave

## What it does

Slowave acts as shared storage across separate agent runs. It records architectural constraints, past bug fixes, and multi-step routines directly into a local SQLite database. Useful entries gain weight upon retrieval. Stale items gradually decay.

The workflow splits into task activation, context recall, notes persistence, and outcome recording. Background maintenance runs locally. You do not need an external LLM API key to manage or retrieve memories. You can inspect saved items in the browser using `slowave dashboard`.

Your system needs Python 3.11 or newer. Without it, `uvx` cannot start the server.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add slowave -- uvx slowave
```
uvx runs the command named after the package; if the README names another one, use uvx --from slowave <command>

### Codex

**Platform CLI**
```bash
codex mcp add slowave -- uvx slowave
```
uvx runs the command named after the package; if the README names another one, use uvx --from slowave <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "slowave": {
            "command": "uvx",
            "args": [
                "slowave"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from slowave <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "slowave": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "slowave"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from slowave <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add slowave uvx slowave
```
uvx runs the command named after the package; if the README names another one, use uvx --from slowave <command>

## When to use it
- retain architectural decisions across new agent runs
- share learned workflows between Claude Code and Codex
- store verified debugging procedures in local storage
- review stored context links through a local web dashboard

## Example prompts
- Remember that we avoid default exports across this TypeScript codebase
- Recall our previous procedure for configuring the staging database
- Commit this task outcome to Slowave and evaluate retrieved context

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md