# Honcho

Honcho stores conversation history and events, then gives an agent context or natural-language answers. Use it to add persistent memory to a coding agent.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed · ★ 7776
- Author: plastic-labs
- License: AGPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/plastic-labs/honcho
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/mcp/honcho

## What it does

Honcho stores messages and events in sessions and associates them with users, agents, groups, and projects. It processes data in the background to update peer representations. An agent can then request session context, search results, or an answer to a natural-language question, and pass the result to a model.

The MCP server connects over HTTP. In Claude Code, add it with `claude mcp add --transport http honcho https://mcp.honcho.dev`. Honcho also supports Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, and Zed. Message processing is asynchronous, so updated peer context may take time to appear.

## Requirements
- Remote server: `https://mcp.honcho.dev`

## Install

### Claude Code (native platform)

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

### Codex

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

### Cursor

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

### GitHub Copilot

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

### Gemini CLI

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

## When to use it
- retain conversation history across agent sessions
- retrieve user context before replying
- search messages and events for relevant details
- pass session context to a model

## Example prompts
- Save this conversation to Honcho memory for use in later sessions.
- Find what the user has told Honcho about their preferences.
- Prepare Honcho session context for answering my question.

## Similar
- [session-history](https://affpapa.org/en/nevibecode/skills/session-history.md) — skill · 13900 installs
- [recap](https://affpapa.org/en/nevibecode/skills/recap.md) — skill · 13700 installs
- [memory-engineering](https://affpapa.org/en/nevibecode/skills/memory-engineering.md) — skill · 29 installs
- [memory-management](https://affpapa.org/en/nevibecode/skills/aaron-he-zhu-memory-management.md) — skill · 4900 installs
- [ontology](https://affpapa.org/en/nevibecode/skills/ontology.md) — skill · 3700 installs
- [cursor-memory-curator](https://affpapa.org/en/nevibecode/skills/cursor-memory-curator.md) — skill · 2700 installs

From the same set: [plastic-labs/honcho](https://affpapa.org/en/nevibecode/by/plastic-labs/honcho.md) — 3 cards

---
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