# Pensyve

Stores persistent episodic, semantic, and procedural agent memory locally in SQLite. Useful when an assistant needs to recall user preferences across chats.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 97
- Author: major7apps
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/major7apps/pensyve
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/mcp/pensyve

## What it does

Pensyve acts as an external memory runtime for AI assistants, keeping facts, conversation history, and task outcomes inside SQLite. Its Rust core processes text using local embedding weights to match entries by meaning. The server gives clients tools such as `pensyve_remember`, `pensyve_recall`, `pensyve_observe`, and `pensyve_inspect`.

Local setups require no cloud accounts or API keys. Pensyve Cloud shut down on October 1, 2026, so the repository remains in maintenance mode for security patches. Because embedding models download upon first run, offline environments fail unless cache files are prepared in advance.

## Requirements
- Needs: Docker

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add pensyve -- docker run -i --rm ghcr.io/major7apps/pensyve-mcp:5.0.0
```

### Codex

**Platform CLI**
```bash
codex mcp add pensyve -- docker run -i --rm ghcr.io/major7apps/pensyve-mcp:5.0.0
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "pensyve": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/major7apps/pensyve-mcp:5.0.0"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "pensyve": {
            "type": "stdio",
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/major7apps/pensyve-mcp:5.0.0"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add pensyve docker run -i --rm ghcr.io/major7apps/pensyve-mcp:5.0.0
```

## When to use it
- persist user preferences and habits across fresh agent sessions
- retrieve previous facts using local semantic vector search
- record task outcomes to evaluate successful procedures
- maintain local agent state in SQLite without external cloud dependencies

## Example prompts
- Remember using pensyve that this project uses Python 3.10 and pytest
- Recall my preferred editor keybindings and theme from memory
- Inspect recorded observations for the current workspace namespace

## 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