explaingit

catowabisabi/heso-ai-orchestrator

18HTMLAudience · developerLicenseSetup · moderate

TLDR

A two-agent system that automatically reviews and improves your codebase in a continuous loop, one agent thinks and plans, the other does the work, sending you Telegram updates without needing to babysit a terminal.

Mindmap

mindmap
  root((HESO))
    Agents
      Hermes reviewer
      Sisyphus worker
      Strict role split
    How it runs
      Cron schedule
      tmux terminal
      800-1000 cycles per day
    Memory
      Project intention file
      SQLite database
      Keyword pool
    Monitoring
      Telegram messages
      No local ML model
      Plain-language updates
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Things people build with this

USE CASE 1

Set up a fully automated coding loop that reviews and improves your project overnight with no manual intervention.

USE CASE 2

Monitor an AI-driven code improvement agent via Telegram messages without watching a terminal.

USE CASE 3

Run continuous AI-assisted refactoring on a codebase using only ordinary hardware and a SQLite file, no GPU or vector database needed.

USE CASE 4

Use the reviewer-worker separation pattern to avoid the common failure mode where a single AI agent reviews its own output and misses everything.

Tech stack

PythonSQLitetmuxcronTelegram API

Getting it running

Difficulty · moderate Time to first run · 1h+

Requires a Telegram bot token for notifications and cron + tmux on the host, no GPU or external vector database needed.

In plain English

HESO is a system for running two AI agents together in a continuous loop to automatically review and improve a software codebase without human involvement in each cycle. The name stands for Hermes, Sisyphus, and Orchestrator, referring to the two agents and the overall coordination layer. The core idea is a strict separation of roles. Hermes acts as the thinking half: it reviews the codebase, checks whether the previous task was completed correctly, generates ideas for improvements, and decides what to work on next. Sisyphus acts as the working half: it receives a single clearly defined task from Hermes and executes it, then reports back. Sisyphus never decides what to do, never reviews its own output, and never sets priorities. The README argues that most automated code review loops fail because a single agent reviews its own work and reliably finds nothing wrong. Keeping the reviewer and the worker separate is the central design choice. The loop runs on a schedule, using standard cron and the tmux terminal multiplexer rather than any specialized infrastructure. There is no vector database or machine learning model running locally, all state is stored in a plain SQLite file. The README states the design targets 800 to 1,000 cycles per day on ordinary hardware. Each cycle ends with a short plain-language message sent to you via Telegram, so you can monitor progress without watching a terminal. The system has three memory layers: a file that holds your stated intention for the project (written once and not changed without asking you), a set of database tables tracking ideas, user experience notes, and pain points, and a keyword pool used to introduce variety into the brainstorming step. The full database schema, prompt templates, and task format are documented in a SPEC.md file in the repository. The project is in alpha. It is released under the MIT License.

Copy-paste prompts

Prompt 1
Walk me through setting up HESO to automatically improve my Python project overnight using the Hermes and Sisyphus agents.
Prompt 2
How do I write the project intention file for HESO so the agents focus on the right goals for my codebase?
Prompt 3
Set up Telegram notifications for a HESO loop running on my Linux server so I get a summary after each cycle.
Prompt 4
Help me adapt the HESO SPEC.md prompt templates to work with a TypeScript project instead of Python.
Prompt 5
How does HESO store memory across cycles, and how do I inspect the SQLite database to see what the agents have done?
Open on GitHub → Explain another repo

← catowabisabi on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.