Post

Honcho

Honcho is an open-source memory server for building stateful AI agents. Apps store the messages of users and agents through a REST API or the Python and TypeScript SDKs, and an LLM derives conclusions about each peer that agents can then query in natural language.

Honcho
In Development
This script is currently in active development and may be unstable or incomplete. Use in production environments is not recommended.

Installation

Default install:

1
bash -c "$(curl -fsSL https://raw.githubusercontent.com/community-scripts/DevScripts/main/ct/honcho.sh)"
CPU: 2 cores RAM: 2048 MB Disk: 6 GB OS: Debian 13

Notes

Honcho needs an API key for OpenAI, Anthropic or Gemini, or an OpenAI-compatible endpoint such as Ollama. Without one the install leaves it stopped.
There is no web interface. Every API request needs a key sent as Authorization: Bearer <key>; the install prints an admin key.
Port 8000 is plain HTTP, and /docs and /health answer without a key. Put a reverse proxy with TLS in front before exposing Honcho beyond your LAN.

Web Interface

Port: 8000

Source code
Loading...