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.
🌐 Website · 📖 Documentation · 💬 Discord
macOS / Linux:
curl -sSL https://raw.githubusercontent.com/synapseorch-ai/synapse-ai/main/setup.sh | bashWindows (PowerShell):
irm https://raw.githubusercontent.com/synapseorch-ai/synapse-ai/main/setup.ps1 | iexnpm install -g synapse-orch-ai
synapsepip install synapse-orch-ai
synapsedocker run -d \
-p 3000:3000 \
-v synapse-data:/data \
-v /var/run/docker.sock:/var/run/docker.sock \
synapseorchai/synapse-ai:latestThen open http://localhost:3000. See the Docker guide in the docs for custom ports and environment variable configuration.
| Install method | Upgrade command |
|---|---|
| Bash / PowerShell installer (recommended) | synapse upgrade |
| pip | pip install --upgrade synapse-orch-ai |
| npm | npm update -g synapse-orch-ai |
| Docker | docker pull synapseorchai/synapse-ai:latest |
- 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.
- 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.
synapse-ai-ui.mov
Multi-agent pipeline that researches a topic, drafts content in a Google Doc, and returns the shared link. (Video is 2x speed)
orchestration-demo.mp4
Multi-agent system with human-in-the-loop that writes code and generates pull requests autonomously.
code-orchestration.mp4
Chat with the AI builder — describe what you want, and it creates the orchestration DAG for you.
orch-builder.mp4
| Concept | Summary |
|---|---|
| Agents | Independent ReAct loops with their own system prompt, tools, model, and repos. Docs → |
| Orchestrations | DAGs of steps — wire agents together with routing, parallelism, loops, and human gates. Docs → |
| Tool Ecosystem | 10+ native tool servers, built-in MCP servers, remote MCP via OAuth/PAT, and custom HTTP/Python tools. Docs → |
| AI Builder | A meta-agent that designs and materializes orchestrations from natural language. Docs → |
| Schedules | Cron/interval automation with messaging notifications. Docs → |
| Messaging | Slack, Discord, Telegram, Teams, WhatsApp — with multi-agent mode. Docs → |
| REST API | Trigger agents and orchestrations programmatically from any application. Docs → |
| Vault | Persistent file storage shared across agents and sessions. Docs → |
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- 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.
See CONTRIBUTING.md for dev setup, architecture details, how to add MCP tool servers, and the PR checklist.
Synapse AI is licensed under AGPL v3 — see LICENSE