Skip to content
Back to search

synapse-ai

Build AI agents that actually do things. Synapse is an open-source platform for creating, connecting, and orchestrating AI agents powered by any LLM — local, cloud or CLIs.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/synapseorch-ai/synapse-ai with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/synapseorch-ai/synapse-ai'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/synapseorch-ai--synapse-ai/badge.svg)](/listings/synapseorch-ai--synapse-ai)

HTML

<a href="/listings/synapseorch-ai--synapse-ai"><img src="/api/listings/synapseorch-ai--synapse-ai/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

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](https://docs.synapseorch.com/getting-started/installation#docker) in the docs for custom ports and environment variable configuration.

> **Security:** publish only the frontend port `3000` — the backend (`8765`) serves an internal API and should not be exposed on `0.0.0.0` (docker-compose binds it to `127.0.0.1`). The container auto-generates a shared internal token so that surface is authenticated by default. For any network-reachable deployment, enable **login** (Settings → Security) and/or set `allow_stdio_mcp=false`, since registering a stdio MCP server launches local commands.

Upgrading

| 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` |

> **Upgrade note (security hardening):** the backend now auto-generates a shared internal token and, under docker-compose, binds its port to `127.0.0.1` by default. The UI and its API are unaffected (the frontend proxies the backend internally). If you previously called the **backend directly** on `:8765` (e.g. external API clients), either point them at the frontend instead — `http://host:3000/api/v1|v2/...` — or set `SYNAPSE_BACKEND_BIND=0.0.0.0` in `.env` to keep publishing `:8765`.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 276 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <p align="center">
  2. <a href="https://synapseorch.com">
  3. <img src="https://raw.githubusercontent.com/synapseorch-ai/synapse-ai/master/.github/assets/readme/banner.png" alt="SynapseOrch — AI automation you can read, approve and rely on" width="100%" />
  4. </a>
  5. </p>
  6. <p align="center">
  7. <a href="LICENSE"><img src="https://img.shields.io/badge/license-AGPL--3.0-0f71b0" alt="License: AGPL-3.0"></a>
  8. <a href="https://pypi.org/project/synapse-orch-ai/"><img src="https://img.shields.io/pypi/v/synapse-orch-ai?label=pypi&color=0f71b0" alt="PyPI version"></a>
  9. <a href="https://discord.gg/9UN45qyGh8"><img src="https://img.shields.io/badge/Discord-join-5865F2?logo=discord&logoColor=white" alt="Discord"></a>
  10. </p>
  11. **[SynapseOrch](https://synapseorch.com/) builds and runs AI workflows that take a fixed path.** Describe a job in plain words and it shows you a
  12. plan: the steps, the model for each, what a run should cost, and where a person signs off. Nothing is built until you
  13. approve it, and every run then follows that path. Models do the work inside the steps; they don't decide which step
  14. comes next.
  15. **It's for** developers and automation builders, working for their own team or for clients, who need an AI workflow
  16. to behave the same on its fiftieth run as on its first. Self-hosted, any model, AGPL-3.0: no account, no licence
  17. check, no telemetry.
  18. ## Install
  19. ```bash
  20. curl -LsSf https://synapseorch.com/install.sh | bash # macOS, Linux
  21. ```
  22. ```powershell
  23. irm https://synapseorch.com/install.ps1 | iex # Windows (PowerShell)
  24. ```
  25. It brings its own Python (and Node.js, if yours is missing or older than 20.9), needs no sudo, keeps everything in
  26. `~/.synapse`, and ends with a link to open. [pip, npm and Docker ↓](#more-ways-to-install)
  27. ## Your first workflow, without an account
  28. 1. **Choose a model when the installer asks "Which AI should Synapse use?"** Synapse AI, the assistant that builds
  29. workflows from a description, needs a capable model: paste a key for Anthropic, OpenAI, Gemini, Groq, OpenRouter,
  30. DeepSeek, Mistral or another provider. No key yet? A free Gemini key from
  31. [Google AI Studio](https://aistudio.google.com/apikey) takes a few minutes (your prompts go to Google).
  32. 2. **Open the link it prints.** Synapse AI's chat opens. Describe a job, for example: *"Every weekday at 9, read the
  33. Hacker News front page, pick the three stories about AI agents, summarise each in two lines, and ask me before
  34. saving the summary to the vault."*
  35. 3. **Read the plan, approve it, then run the workflow.** The run stops at your sign-off: answer it under **Needs
  36. you** on Home, or from the terminal with `synapse runs answer`.
  37. **Only local models?** The installer finds [Ollama](https://ollama.com/download) and its models, and workflow steps
  38. run well on them, with your prompts staying on your machine. Building with Synapse AI on a small local model doesn't
  39. work well yet, so draw the workflow in the editor, or give Synapse AI a hosted model in Settings → Models and keep
  40. the steps local. [Models and providers →](https://docs.synapseorch.com/llm-providers/overview)
  41. <!-- DEMO VIDEO: a shorter MP4 can replace the GIF: drag demo.mp4 into a GitHub comment box, and paste the user-attachments link it gives on its own line here, so it plays inline. -->
  42. <p align="center">
  43. <img src="https://raw.githubusercontent.com/synapseorch-ai/synapse-ai/master/.github/assets/readme/demo.gif" alt="One sentence to Synapse AI: it asks where the notes live, shows a plan with its cost, and builds the workflow; then the workflow runs, waits for you to approve the summary and the save, and finishes with what each step cost" width="100%" />
  44. <br />
  45. <sub>A real session on a hosted Claude model, the model’s waits sped up: one sentence to a built workflow, then a run that waits for a sign-off.</sub>
  46. </p>
  47. <p align="center">
  48. <a href="https://docs.synapseorch.com"><strong>Documentation</strong></a> ·
  49. <a href="#how-it-compares"><strong>How it compares</strong></a> ·
  50. <a href="https://discord.gg/9UN45qyGh8"><strong>Discord</strong></a> ·
  51. <a href="https://synapseorch.com/cloud/"><strong>SynapseOrch Cloud</strong></a>
  52. </p>
  53. ---
  54. ## Describe it. Approve it. Rely on it.
  55. - **Describe it.** Tell **Synapse AI** the job. It writes the steps, picks a model for each and marks where you sign
  56. off, then shows you the plan before anything is built.
  57. - **Approve it.** Read every step. When a run reaches yours, it waits for your yes — in the app, or in Slack,
  58. Telegram or another chat channel.
  59. - **Rely on it.** It runs on schedule exactly as you approved, and shows what each step did and what it cost. A run
  60. stops once it reaches the spending limit you set.
  61. <table>
  62. <tr>
  63. <td width="38%" valign="top"><img src="https://raw.githubusercontent.com/synapseorch-ai/synapse-ai/master/.github/assets/readme/plan-card.png" alt="Synapse AI's plan: the steps, the schedule, what a run costs, and what it asks you first" width="100%" /><br /><sub><b>Describe it.</b> Synapse AI shows the plan, what a run costs and what it will ask you — before it builds anything.</sub></td>
  64. <td width="62%" valign="top"><picture>
  65. <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/synapseorch-ai/synapse-ai/master/.github/assets/readme/home-dark.png" />
  66. <img src="https://raw.githubusercontent.com/synapseorch-ai/synapse-ai/master/.github/assets/readme/home-light.png" alt="Home: one run waiting on you, with this week's feedback summary to approve" width="100%" />
  67. </picture><br /><sub><b>Approve it.</b> When a run reaches your step, it waits on Home for your yes.</sub></td>
  68. </tr>
  69. </table>
  70. <picture>
  71. <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/synapseorch-ai/synapse-ai/master/.github/assets/readme/result-dark.png" />
  72. <img src="https://raw.githubusercontent.com/synapseorch-ai/synapse-ai/master/.github/assets/readme/result-light.png" alt="A finished run: completed in 37 s, 12 steps, the time it waited on you, and what each step cost" width="100%" />
  73. </picture>
  74. <p align="center"><sub><b>Rely on it.</b> Every run shows the path it took, how long it waited on you, and what each step cost.</sub></p>
  75. ## What's inside
  76. | | |
  77. |---|---|
  78. | **Synapse AI** | An assistant that builds and changes agents and workflows from a sentence, and answers questions about your workspace. |
  79. | **Workflows** | Steps you can read on a canvas: agents, models, tools, code, branches, loops, parallel paths, sign-offs and other workflows. Runs follow the path you drew. |
  80. | **Agents and teams** | Agents with their own model, tools, skills and memory. A team agent splits work among its members; any agent can start short-lived helpers. |
  81. | **Sign-offs** | A step that waits for a person — answered in the app or in a chat channel. Approvals for risky tool calls, too. |
  82. | **Knowledge** | Your files and web pages, indexed; answers cite the passage they used. *(Optional part — see below.)* |
  83. | **Boards** | A shared to-do board for people and agents, with each card's history. *(Off until you turn it on in Settings.)* |
  84. | **Apps and tools** | MCP servers (local or remote, OAuth included), REST and OpenAPI, Python functions, SQL databases, web fetch and scraping. |
  85. | **Channels** | Your agents on Slack, Discord, Telegram, Microsoft Teams, WhatsApp, a website chat widget, or a phone number (Twilio). |
  86. | **Any model** | Your own keys for 23+ providers, any OpenAI-compatible endpoint, local models through Ollama, or the Claude Code, Codex, Gemini and Copilot CLIs you already use. A different model at every step. |
  87. | **Costs you can read** | An estimate before a run, what each step cost after it, and a spending cap per run, checked before each step. |
  88. | **Use it from anywhere** | A command line, a versioned REST API, an MCP server for Claude, ChatGPT and Cursor, and an OpenAI-compatible endpoint where every agent answers as a model. |
  89. | **Scale mode** | Redis queue, a worker fleet, Postgres checkpoints and S3 storage, for when one process is not enough. |
  90. ## How it compares
  91. | | What it is | You build it by | Licence |
  92. |---|---|---|---|
  93. | **SynapseOrch** | An app that builds and runs AI workflows, with a UI, REST API, CLI and MCP server | Describing it (Synapse AI drafts a plan you approve) or drawing it | AGPL-3.0 |
  94. | n8n | A workflow automation app with 500+ integrations | Drawing it, code nodes, or its Assistant (in preview) | Sustainable Use License (source-available) |
  95. | Dify | An LLM app platform with a visual workflow canvas | Drawing it | Apache 2.0 with added conditions |
  96. | LangGraph | A library for agent graphs in Python and JavaScript | Writing code | MIT |
  97. | CrewAI | A Python framework for teams of agents | Writing code | MIT |
  98. | Temporal | A durable-execution engine for workflows written in code | Writing code | MIT |
  99. If you need hundreds of ready integrations, n8n has far more than we do. If an engineer will own the agent in code,
  100. a library is the better fit, and your code can still start SynapseOrch runs through the API. Where each one is the
  101. better choice: [synapseorch.com/compare](https://synapseorch.com/compare/).
  102. ---
  103. ## More ways to install
  104. The one-line installer above asks which AI to use (and whether to start on login) while it installs; add `--yes`
  105. (`curl … | bash -s -- --yes`) to take every default. The short addresses redirect to the scripts on the latest GitHub
  106. release: [setup.sh](https://github.com/synapseorch-ai/synapse-ai/releases/latest/download/setup.sh) and
  107. [setup.ps1](https://github.com/synapseorch-ai/synapse-ai/releases/latest/download/setup.ps1).
  108. **npm, pip or Docker**
  109. ```bash
  110. npm install -g synapse-orch-ai && synapse # the first run uses the same installer
  111. pip install synapse-orch-ai && synapse # Python 3.11–3.14 and Node.js 20.9+
  112. ```
  113. ```bash
  114. docker run -d --name synapse -p 3000:3000 -p 127.0.0.1:8765:8765 \
  115. -v synapse-data:/data \
  116. -v /var/run/docker.sock:/var/run/docker.sock \
  117. synapseorchai/synapse-ai:latest
  118. ```
  119. Then open `http://localhost:3000`. The backend's port (`8765`) is published on this machine only: it serves an
  120. internal API, so never publish it on `0.0.0.0`.
  121. **Optional parts.** Knowledge brings Docling and a CPU build of PyTorch, so it is added only when you ask:
  122. ```bash
  123. synapse upgrade --with knowledge # an existing install
  124. curl -LsSf …/setup.sh | bash -s -- --with knowledge # a new one
  125. ```
  126. Then turn it on in Settings → General. Every later upgrade keeps it.
  127. ## Upgrading
  128. ```bash
  129. synapse upgrade
  130. ```
  131. It backs up the database, installs the newest version, updates the database and starts Synapse again if it was running.
  132. An npm install is upgraded with `npm install -g synapse-orch-ai@latest`; Docker by pulling the new image and running
  133. the same command.
  134. **Coming from 1.x?** Run the install command above, or `synapse upgrade`. Your agents, workflows, chats, schedules,
  135. settings, API keys and vault files move into 2.0's store. Before anything changes, the upgrade backs up your 1.x data
  136. folder, logs and `.env` to `~/.synapse/backups/synapse-1.x-<date>.tar.gz`, with a `manifest.json` that lists where each
  137. part came from; the old install's folder is removed once 2.0 is running. To go back, reinstall 1.9.3 and put each part
  138. of the backup back where `manifest.json` says. Don't run 2.0's `synapse uninstall` first: it removes `~/.synapse`,
  139. backups included, unless you add `--keep-data`. Docker imports a 1.x `/data` volume on its first start. See
  140. [Upgrading to 2.0](https://docs.synapseorch.com/getting-started/upgrading-to-2).
  141. ---
  142. ## The command line
  143. One `synapse` command runs SynapseOrch on this machine, and drives any SynapseOrch — this one, one on your servers, or
  144. Cloud — with an API key. Everything you can do in the app, you can do from a terminal or a script.
  145. **This machine**
  146. ```bash
  147. synapse start # open it (-d: in the background)
  148. synapse status # is it running? (--json for scripts)
  149. synapse logs -f # follow the backend's log (frontend, install)
  150. synapse upgrade # the newest version; data and settings stay
  151. synapse autostart on # start when you log in
  152. ```
  153. **Build, run and answer**
  154. ```bash
  155. synapse agents list # list, show, create, update, delete
  156. synapse workflows list # list, show, export, create, validate, deploy, delete
  157. synapse run NAME -m "…" # run a workflow and follow it to its answer
  158. synapse runs waiting # what waits on you: questions and held tool calls
  159. synapse runs answer RUN_ID --approve # answer a sign-off (or --reject, or reply with text)
  160. synapse chat --agent NAME -m "…" # one message to an agent (bare `synapse chat` to talk)
  161. synapse schedules create --workflow NAME --cron "0 9 * * MON"
  162. ```
  163. **Knowledge, Boards and the workspace**
  164. ```bash
  165. synapse knowledge upload --base Handbook ./policies/*.pdf --wait
  166. synapse knowledge search "refund window" --base Handbook
  167. synapse boards show BOARD # a board's open cards; `boards card` adds and comments
  168. synapse activity --days 7 # what ran, what failed, what waits
  169. synapse usage --by model # what the workspace spent, by day, agent or model
  170. ```
  171. **Every door a key has**
  172. ```bash
  173. synapse tools list # every product tool this key may call; `tools call NAME`
  174. synapse api GET /agents # call any route a key reaches, as `gh api` does
  175. synapse mcp # serve SynapseOrch to Claude, Cursor… over stdio
  176. synapse login --url https://api.synapseorch.com --api-key-stdin # drive another SynapseOrch
  177. ```
  178. For scripts, `--json` prints JSON (one event a line for a run) and `-q` lists ids only. Exit codes say what happened:
  179. `0` done · `3` waiting on a person · `4` run failed · `5` not found · `6` key refused · `7` busy or unreachable.
  180. `synapse --help` lists every command. [CLI reference →](https://docs.synapseorch.com/cli/commands)
  181. ## Use it from your own code and tools
  182. - **REST API** — start runs, stream their events, answer sign-offs, with an API key.
  183. [API →](https://docs.synapseorch.com/api/overview)
  184. - **MCP server** — build and run workflows from Claude, ChatGPT or Cursor.
  185. [MCP server →](https://docs.synapseorch.com/api/mcp-server)
  186. - **OpenAI-compatible endpoint** — every agent answers as a model to any OpenAI client, with its own tools.
  187. ## Scale mode
  188. When one process is not enough: a Redis job queue, 1 to 100+ workers, per-step Postgres checkpoints (a worker that dies
  189. loses nothing), S3-compatible storage and per-team run limits — behind the same API.
  190. ```bash
  191. docker pull synapseorchai/synapse-ai-api-server:latest # stateless API server
  192. docker pull synapseorchai/synapse-ai-worker:latest # workers, as many as needed
  193. ```
  194. `docker compose --profile scale up` runs the whole stack (with `REDIS_URL` set in `.env`); Kubernetes examples are in
  195. `infra/k8s/`.
  196. [Scale mode →](https://docs.synapseorch.com/scale/overview)
  197. ## Running it on a network
  198. Everything an agent can do runs on the machine Synapse runs on, so treat a shared instance like a server:
  199. - turn on **login** (Settings → General) on anything reachable beyond your own machine;
  200. - publish only the web port (`3000`) on the network, never the backend's (`8765`);
  201. - local MCP servers and custom Python tools run commands: turn them off with `allow_stdio_mcp` if you do not trust
  202. every user, and give agents the narrowest tools that do the job.
  203. Security issues: please report them privately — see [SECURITY.md](SECURITY.md).
  204. ---
  205. ## SynapseOrch Cloud
  206. The same product, run for you: no servers, managed models, plans with a hard monthly limit, and teams with roles.
  207. [synapseorch.com](https://synapseorch.com)
  208. ## Contributing
  209. See [CONTRIBUTING.md](CONTRIBUTING.md) for the development setup, how the pieces fit, and the PR checklist.
  210. Questions and ideas are welcome on [Discord](https://discord.gg/9UN45qyGh8).
  211. ## License
  212. SynapseOrch is licensed under the [GNU AGPL v3](LICENSE).
  213. [![Star History Chart](https://api.star-history.com/svg?repos=synapseorch-ai/synapse-ai&type=date&legend=top-left)](https://www.star-history.com/#synapseorch-ai/synapse-ai&type=date&legend=top-left)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.