# SlashML (/ ml) Persistent Agent Memory, Redaction & Code Localization

SlashML (/ ml) Persistent Agent Memory, Redaction & Code Localization is an MCP server for Claude Code that keeps memory and searches code by behavior. It ranks likely files behind an error or stack trace.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1 repo stars
- Author: slashml-ai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/slashml-ai/ml-memory
- Updated: 2026-11-14
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/slashml-ml-persistent-agent-memory-redaction-code-localization

## What it does

The server stores architectural decisions, preferences, and standing project rules for later sessions. Agents can add, retrieve, search, and remove memories, find functions by their runtime or architectural behavior, and rank files that may explain a symptom or stack trace.

It can mask sensitive text and set read-only or read-write access for individual agents. Lifecycle hooks capture new standing instructions and compare tool calls with active rules. A SlashML API key is required.

## Requirements
- Remote server: `https://api.slashml.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http ml-memory https://api.slashml.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add slashml-ml-persistent-agent-memory-redaction-code-localization --url https://api.slashml.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "slashml-ml-persistent-agent-memory-redaction-code-localization": {
            "url": "https://api.slashml.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "slashml-ml-persistent-agent-memory-redaction-code-localization": {
            "type": "http",
            "url": "https://api.slashml.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http slashml-ml-persistent-agent-memory-redaction-code-localization https://api.slashml.ai/mcp
```

## When to use it
- carry project rules across sessions
- find functions from a description of their behavior
- rank files related to a stack trace
- mask sensitive text in stored memories
- set different access modes for agents

## Example prompts
- Save this project rule: new API routes must require authentication.
- Find the function that retries a request after it fails.
- Use this stack trace to rank files that may contain the bug.

## Similar
- [Cathedral — Persistent Memory for AI Agents](https://affpapa.org/en/nevibecode/mcp/cathedral-persistent-memory-for-ai-agents.md) — MCP server · ★ 11 repo stars
- [SlashML (/ ml) Embodied Robotics Trajectory Memory](https://affpapa.org/en/nevibecode/mcp/slashml-ml-embodied-robotics-trajectory-memory.md) — MCP server · ★ 1 repo stars
- [agentdb-persistent-memory-patterns](https://affpapa.org/en/nevibecode/skills/agentdb-persistent-memory-patterns.md) — skill · 1 install
- [agent-memory](https://affpapa.org/en/nevibecode/mcp/xchucx-agent-memory.md) — MCP server · ★ 15 repo stars
- [memory-engineering](https://affpapa.org/en/nevibecode/skills/memory-engineering.md) — skill · 29 installs
- [cursor-memory-curator](https://affpapa.org/en/nevibecode/skills/cursor-memory-curator.md) — skill · 2700 installs

---
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
