# Renor

Keeps agent decisions and context in local Markdown files. Lets fresh sessions in Claude Code or Codex pick up past notes without starting over.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 11
- Author: renorai
- License: AGPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/renorai/renor-engine
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/mcp/renor

## What it does

Renor gives coding assistants persistent memory stored directly in your filesystem. When an agent logs a choice during a session, the next agent can look it up immediately. The server appends facts to `System/Memory Events Ledger.md` and saves daily notes under `Memory/Daily`.

Search relies on a local SQLite index. Out of the box, queries match exact words rather than conceptual meaning. Semantic search kicks in only after you configure `EMBEDDING_PROVIDER` with `openai` or a local model. No text leaves the machine unless these external providers are active.

Building the self-hosted engine requires Node 22 or newer. On older runtimes, the local engine simply refuses to run. If you want to bypass local builds, connect directly to the hosted HTTP endpoint at `https://mcp.renor.cloud/mcp`.

## Requirements
- Remote server: `https://mcp.renor.cloud/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http renor https://mcp.renor.cloud/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add renor --url https://mcp.renor.cloud/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "renor": {
            "url": "https://mcp.renor.cloud/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "renor": {
            "type": "http",
            "url": "https://mcp.renor.cloud/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http renor https://mcp.renor.cloud/mcp
```

## When to use it
- persist technical decisions across separate agent sessions
- share remembered facts between Claude Code, Codex and Cursor
- keep notes in accessible Markdown files instead of closed databases
- recall project rules without re-explaining them in every prompt

## Example prompts
- Remember that our API routes always return timestamps in UTC
- Recall why we chose Redis over Memcached for caching user tokens
- Save the current rollout plan to daily memory

## Similar
- [Palinode](https://affpapa.org/en/nevibecode/mcp/palinode.md) — MCP server · ★ 46
- [context-mem](https://affpapa.org/en/nevibecode/mcp/context-mem.md) — MCP server · ★ 19
- [Global Agent Memory](https://affpapa.org/en/nevibecode/mcp/global-agent-memory.md) — MCP server · ★ 14
- [sqlite-graph-memory](https://affpapa.org/en/nevibecode/mcp/sqlite-graph-memory.md) — MCP server · ★ 12
- [open-memex](https://affpapa.org/en/nevibecode/mcp/open-memex.md) — MCP server · ★ 6
- [mem](https://affpapa.org/en/nevibecode/skills/mem.md) — skill · 2400 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