# zaxy

Auditable agent memory powered by Eventloom event sourcing and LadybugDB. Keeps session provenance intact with cited facts and replayable execution logs.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 17
- Author: syndicalt
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/syndicalt/zaxy
- Updated: 2026-08-10
- HTML: https://affpapa.org/en/nevibecode/mcp/zaxy

## What it does

Zaxy organizes agent activity into a verifiable project memory log. It records task missions, worker findings, and approval records directly into append-only JSONL files located in the `.eventloom` directory.

Local reasoning runs through an embedded LadybugDB graph projection without external services. Retrieval combines vector embeddings and graph traversal. The server exposes dedicated MCP tools such as `memory_append`, `memory_query`, `memory_feedback`, `memory_replay`, and `memory_invalidate`.

The standard setup operates entirely locally. External backends like Neo4j or Pathlight tracing remain strictly optional and require installing explicit package extras like `zaxy-memory[neo4j]` or `zaxy-memory[pathlight]`.

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

## Install

### Claude Code (native platform)

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

### Codex

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

### Cursor

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

### GitHub Copilot

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

### Gemini CLI

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

## When to use it
- track agent findings in an auditable append-only log
- isolate worker sessions before merging facts into main context
- query past decisions via hybrid vector search and graph traversal
- replay provenance steps behind model conclusions

## Example prompts
- Query Zaxy memory for recent architecture decisions using `memory_query`.
- Append verified validation rules to project history with `memory_append`.
- Replay past tool observations for the specified task session.

## 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