explaingit

pauloberezini/hermes-synapse

Analysis updated 2026-05-18

24PythonAudience · developerComplexity · 4/5LicenseSetup · moderate

TLDR

A self-hosted, visual framework for building teams of AI agents that plan dynamically and coordinate through a strict, cycle-safe graph.

Mindmap

mindmap
  root((repo))
    What it does
      Visual agent canvas
      DAG based coordination
      Dynamic planning loop
    Tech stack
      Python and FastAPI
      React and Vite
      Docker and Qdrant
    Use cases
      Multi agent orchestration
      Tool permission control
      Self hosted assistant
    Audience
      Developers
      Self hosters

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

What do people build with it?

USE CASE 1

Build a hierarchical team of AI agents that plan their own steps instead of following a fixed hardcoded workflow.

USE CASE 2

Wire agents together visually on a canvas instead of writing orchestration code by hand.

USE CASE 3

Give agents specific tools, like web search or a code sandbox, while limiting what child agents can access.

USE CASE 4

Run a self-hosted multi-agent assistant that connects to Telegram, Google Calendar, or Todoist.

What is it built with?

PythonFastAPIReactDockerQdrant

How does it compare?

pauloberezini/hermes-synapse0311119/free_registertool18597990650-lab/multi-agent-game
Stars242424
LanguagePythonPythonPython
Setup difficultymoderatehardmoderate
Complexity4/54/53/5
Audiencedeveloperdeveloperdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires Docker Compose and at least one LLM API key, such as OpenRouter.

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

In plain English

Hermes is a visual framework for building networks of AI agents that plan their own steps and coordinate through a strict directed graph, structured so a task branches into sub tasks but never loops back on itself, avoiding the runaway back and forth that some other agent frameworks fall into. Users wire agents together on a drag and drop canvas rather than writing code by hand, and a root orchestrator called Jarvis sits at the entry point, deciding how to route each incoming request down through sub orchestrators and sub agents. Each agent can be given a set of skills, which are pluggable tools such as web search, a Python code sandbox, weather lookups, a calendar integration, or a local memory system backed by the Qdrant vector database. The project ships with a set of ready made agents out of the box: a search agent, a code engineer that can self correct its own scripts, a data analyst that builds charts, a scheduler, a market monitor for stocks and crypto, a daily planner that connects to Google Calendar and Todoist, a system operations agent, and a football analyst. Agents missing a required API key still start, they just report plainly what needs to be configured. Security is enforced through what the project calls Permission Intersection: a child agent can only use the tools that both it and its parent were given, so a sub agent cannot gain access to something like shell execution just because it happens to be configured with that skill, if its parent lacks it too. This is meant to stop one agent from quietly escalating its own privileges as tasks move down the chain. The backend is a FastAPI Python server with a React and Vite dashboard, and it can connect to any OpenAI compatible language model provider, including OpenRouter's hosted models or a locally run model through Ollama. Setup is done through Docker Compose, using a single environment file for configuration, and the project supports SQLite by default or PostgreSQL for production use. The code is released under the MIT license.

Copy-paste prompts

Prompt 1
Set up hermes-synapse with Docker Compose and connect it to OpenRouter using my API key.
Prompt 2
Explain how hermes-synapse's Permission Intersection stops a sub-agent from gaining tools its parent doesn't have.
Prompt 3
Show me how to add a new custom skill to one of the built-in agents in hermes-synapse.
Prompt 4
Configure hermes-synapse to use a local Ollama model instead of OpenRouter.

Frequently asked questions

What is hermes-synapse?

A self-hosted, visual framework for building teams of AI agents that plan dynamically and coordinate through a strict, cycle-safe graph.

What language is hermes-synapse written in?

Mainly Python. The stack also includes Python, FastAPI, React.

What license does hermes-synapse use?

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

How hard is hermes-synapse to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is hermes-synapse for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.