convez.ai
MCP ServerAutomaçãoIntermediário
synapseorch-ai

Synapse AI — Orquestração Multi-Agent

synapseorch-ai/synapse-ai

Orquestrador de agentes IA sem lock-in de framework

Ver no GitHub
BomPluginScore · de 0 a 100

Plataforma open-source para criar, conectar e orquestrar agentes de IA alimentados por qualquer LLM (local, cloud ou CLIs). Permite construir workflows determinísticos conectando agentes, ferramentas e modelos sem lock-in de framework, com suporte nativo a MCP servers, webhooks e scripts Python.

Instalação

$npx convez-ai synapseorch-ai/synapse-ai

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
343
Forks
63
Acompanhando
1
Saúde
62%
Último commit
há 1 dia
Versão
v2.1.0
Issues abertas
5
Contribuidores
4

Casos de uso

  • Automação de workflows complexos com múltiplos agentes
  • Integração de LLMs locais e cloud em pipelines determinísticos
  • Exposição de ferramentas e integrações via MCP servers

Veredito

Synapse é uma solução madura e bem-estruturada para orquestração de agentes IA. Recomendado para quem precisa de workflows complexos com múltiplos agentes sem ficar preso a um framework específico; exige conhecimento técnico sólido em Python e arquitetura de sistemas.

README

A tradução para o português deste README ainda está na fila.

Synapse AI — Multi-Agent Orchestration Platform

Build AI workflows that actually ship.

Wire agents, tools, and LLMs into deterministic pipelines — without the framework lock-in. Synapse is an open-source platform for creating, connecting, and orchestrating AI agents powered by any LLM — local or cloud. Agents use real tools: browsing the web, querying databases, executing code, reading files, managing emails, and anything else you can expose through an MCP server, a webhook, or a Python script.


Install

Quick Setup Script (recommended)

macOS / Linux:

curl -sSL https://raw.githubusercontent.com/synapseorch-ai/synapse-ai/main/setup.sh | bash

Windows (PowerShell):

irm https://raw.githubusercontent.com/synapseorch-ai/synapse-ai/main/setup.ps1 | iex

npm

npm install -g synapse-orch-ai
synapse

pip

pip install synapse-orch-ai
synapse

Docker

docker run -d \
  -p 3000:3000 \
  -v synapse-data:/data \
  -v /var/run/docker.sock:/var/run/docker.sock \
  synapseorchai/synapse-ai:latest

Then open http://localhost:3000. See the Docker guide in the docs for custom ports and environment variable configuration.

Upgrading

Install methodUpgrade command
Bash / PowerShell installer (recommended)synapse upgrade
pippip install --upgrade synapse-orch-ai
npmnpm update -g synapse-orch-ai
Dockerdocker pull synapseorchai/synapse-ai:latest

Scale Mode

Run unlimited agents and orchestrations concurrently. When you need to go beyond a single process, the distributed scale layer handles the load:

  • Redis Cluster — job queue, SSE event streams, pub/sub cancellation signals, auto-failover
  • ARQ worker fleet — 1 to 100+ independent workers, each running up to 20 concurrent orchestrations; autoscale with KEDA on queue depth
  • PgBouncer — multiplexes hundreds of worker connections into a small, stable Postgres pool
  • S3 artifact storage — stream large file outputs directly to AWS S3, Cloudflare R2, or MinIO
  • Multi-tenant quotas — per-team or per-customer concurrent run limits with HTTP 429 enforcement
  • Per-step checkpoint recovery — worker crashes don't lose jobs; the next worker resumes from the last completed step

Three Docker images — pull only what you need:

docker pull synapseorchai/synapse-ai:latest             # full app (standalone mode)
docker pull synapseorchai/synapse-ai-api-server:latest  # stateless API server (scale mode)
docker pull synapseorchai/synapse-ai-worker:latest      # worker process (scale mode, run as many as needed)

The docker-compose.yml in the repo spins up the full stack. Production K8s manifests are in infra/k8s/.

📖 Scale Mode docs →


What Makes Synapse Different

  • Multi-Model Orchestrations — Run a different LLM at every step. Use a fast model for routing, a powerful one for analysis. You control where the compute goes.
  • Deterministic DAG Execution — Orchestrations follow the exact path you designed. No hallucinated detours.
  • Turn Anything Into a Tool — Python scripts, REST APIs, webhooks, MCP servers, or entire orchestrations — all become agent-callable tools.
  • Human-in-the-Loop — Pause workflows for human review. Resumable across restarts. Connect via UI, Slack, Telegram, or any messaging channel.
  • Scales to Millions of Requests — The distributed scale layer separates API servers, Redis job queues, and independent worker processes so you can run any number of agents or orchestrations concurrently. Start on one machine, grow to a Kubernetes cluster — the V2 API never changes.
  • Local-First, No Lock-In — Full local operation with Ollama. Mix local and cloud models freely. Your data stays yours.
  • Built-In Scheduling & Messaging — Cron-based automation with results pushed to Slack, Discord, Telegram, Teams, or WhatsApp.
  • 14+ LLM Providers — Cloud, local, and CLI providers including Ollama, OpenAI, Anthropic, Gemini, xAI, DeepSeek, AWS Bedrock, and more.

📖 Learn more →


Synapse UI

https://github.com/user-attachments/assets/7a5ab42c-5fae-4f13-876c-13aa9b5a0366

Demos

Content Writing Orchestration

Multi-agent pipeline that researches a topic, drafts content in a Google Doc, and returns the shared link. (Video is 2x speed)

https://github.com/user-attachments/assets/4eec5db8-70d0-47b6-8608-f52b1f7b7d68

Autonomous Code Development & PR Creation

Multi-agent system with human-in-the-loop that writes code and generates pull requests autonomously.

https://github.com/user-attachments/assets/95a511e1-e3e9-4812-b9ca-f7f4c28ef80f

Native Orchestration Builder

Chat with the AI builder — describe what you want, and it creates the orchestration DAG for you.

https://github.com/user-attachments/assets/282cc99d-cdea-4ad0-b648-f22112c6e295


Key Concepts

ConceptSummary
AgentsIndependent ReAct loops with their own system prompt, tools, model, and repos. Docs →
OrchestrationsDAGs of steps — wire agents together with routing, parallelism, loops, and human gates. Docs →
Tool Ecosystem10+ native tool servers, built-in MCP servers, remote MCP via OAuth/PAT, and custom HTTP/Python tools. Docs →
AI BuilderA meta-agent that designs and materializes orchestrations from natural language. Docs →
SchedulesCron/interval automation with messaging notifications. Docs →
MessagingSlack, Discord, Telegram, Teams, WhatsApp — with multi-agent mode. Docs →
Scale ModeDistributed execution layer: Redis job queue, independent worker fleet, per-step Postgres checkpoints, S3 artifact storage, and multi-tenant quotas. Docs →
V2 APIStable versioned REST API for building products on top of Synapse — enqueue, stream, cancel, webhooks. Docs →
VaultPersistent file storage shared across agents and sessions. Docs →

CLI

synapse start     # start backend + frontend, open browser
synapse stop      # stop background processes
synapse upgrade   # upgrade to the latest version
synapse uninstall # remove Synapse, wipe ~/.synapse, and uninstall the package

Roadmap

  • Spawn Sub-Agent Tool — Agents natively spawn and delegate tasks to temporary sub-agents mid-execution.
  • Compact Conversations — Automatic message history compression for large contexts.
  • Global Variables — Dynamic variables injectable into prompts, orchestrations, tools, and MCP environments.

Star History

Star History Chart


Contributing

See CONTRIBUTING.md for dev setup, architecture details, how to add MCP tool servers, and the PR checklist.

License

Synapse AI is licensed under AGPL v3 — see LICENSE

Ver o original no GitHub

Bom para

Relacionados