FLUJO
Multi-Agent + Automation Harness: Graph-based Workflows, MCP, Self-Improving Agents. NextJs+React
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
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/mario-andreschak/FLUJO 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/mario-andreschak/FLUJO'
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
Markdown
[](/listings/mario-andreschak--flujo)HTML
<a href="/listings/mario-andreschak--flujo"><img src="/api/listings/mario-andreschak--flujo/badge.svg" alt="findsafeskills safety rating" /></a>Install
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.
The installer sets up everything FLUJO needs (Git, Node.js, Python, uv, ripgrep), clones FLUJO, builds it, and creates a global `flujo` command. This is the recommended way to run FLUJO — MCP servers get all their runtimes too.
**Windows installer (recommended)** — click below to download the latest `flujo-setup.exe`:
**Windows PowerShell** — alternatively, press Start, type powershell, press Enter, copy & paste the command below and press Enter again:
irm https://raw.githubusercontent.com/mario-andreschak/FLUJO/main/scripts/install.ps1 | iex
**Linux / macOS** — paste into a terminal:
curl -fsSL https://raw.githubusercontent.com/mario-andreschak/FLUJO/main/scripts/install.sh | bash
**Already have Node.js?** You can also skip installation entirely and run a prebuilt FLUJO straight from npm — fastest start, but MCP servers may still need `git` / `python` / `uv` on your PATH (see [Run via npx](#run-via-npx-npm-package)):
npx flujo-ai
Prefer to set it up manually? See [Getting Started](#-getting-started). To remove FLUJO later, see [Uninstalling](#uninstalling-windows).
> [!TIP] > Stuck on MCP installation, the app, or anything else? [Open a GitHub issue](https://github.com/mario-andreschak/FLUJO/issues) or [join the Discord](https://discord.gg/KPyrjTSSat). I read every message and will do my best to get back to you within a day.
<p align="center"><em>The FLUJO home screen: connect once, then use your private AI workspace.</em></p>
FLUJO is powered by the [PocketFlow Framework](https://the-pocket-world.github.io/Pocket-Flow-Framework/) and built with Cline, Claude Code, and a lot of love.
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 · 352 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.
- <div align="center">
- # FLUJO
- ### Build private AI agents visually. Run them your way.
- **Connect your AIs and apps, build an agent, then talk to it, automate it, or call it from other software.**
- **Simple + visual builders** · **MCP-native connections** · **Multi-model** · **Built-in debugger** · **Automation**
- [**Install FLUJO ↓**](#-quick-install-recommended) · [**Explore features ↓**](#-key-features) · [**Watch the walkthrough →**](https://flujo.com.co/film/) · [**Website →**](https://flujo.com.co/) · [**Online demo →**](https://try.flujo.com.co/)
- [](LICENSE)
- [](package.json)
- </div>
- FLUJO is an open-source, local-first AI workspace. Save your model and app connections once, build reusable agents as plain-language steps or visual flows, and inspect what happens when they run. Combine models, tools and other agents; branch, loop and hand off work; use the same setup in chat, background automations and external applications.
- Your workspace is stored on your computer. Cloud models and connected services receive the requests you send them. [Privacy and workspace controls](#privacy-and-workspace-controls).
- [](githubpages/film/media/walkthrough/act1-dashboard.png)
- *Connect your AI, create an agent, then use it. Walkthrough screenshots show real FLUJO 3.46.2 screens; select an image to view it at full size.*
- > FLUJO feels complicated, you're missing a feature, or you're stuck? [Join Discord](https://discord.gg/KPyrjTSSat) or [open a GitHub issue](https://github.com/mario-andreschak/FLUJO/issues). **We can only improve if we know what's wrong.**
- [AI Setup](#ai-setup) · [Connected Apps](#connected-apps-mcp) · [Agent Builder](#agent-builder) · [Talk & debugging](#talk-and-debugging) · [Automations](#automations) · [Meetings](#meetings--experimental) · [Personas](#personas-and-roles--experimental) · [Integrations](#external-tool-integration) · [Project vision](#project-vision--soontm)
- <a id="-quick-install-recommended"></a>
- ## Quick install
- The installers set up FLUJO and useful tool runtimes such as Git, Node.js, Python, uv and ripgrep. They download dependencies and need an internet connection.
- **Windows installer:** [Download the latest flujo-setup.exe](https://github.com/mario-andreschak/FLUJO/releases/latest/download/flujo-setup.exe).
- **Windows PowerShell:**
- ```powershell
- irm https://raw.githubusercontent.com/mario-andreschak/FLUJO/main/scripts/install.ps1 | iex
- ```
- **Linux / macOS:**
- ```bash
- curl -fsSL https://raw.githubusercontent.com/mario-andreschak/FLUJO/main/scripts/install.sh | bash
- ```
- **Already have Node.js 22.23.4+ within 22.x, or 24.22.1+ within 24.x?** Run the published package:
- ```bash
- npx flujo-ai@latest
- ```
- Open [localhost:4200](http://localhost:4200) and keep the FLUJO server running. Some connected tools need additional runtimes or credentials. Shell installers follow the development branch by default; check the release notes for a Windows installer's version and channel.
- [All installation choices](docs/start-here/install.md) · [Windows](docs/start-here/windows.md) · [Linux/macOS](docs/start-here/unix.md) · [npm](docs/start-here/npm.md) · [Docker](docs/start-here/docker.md) · [Build from source](docs/start-here/source.md)
- <a id="-key-features"></a>
- ## Key features
- ### AI Setup
- - **Choose your provider:** OpenAI, Azure OpenAI, Anthropic, Google Gemini, X.ai, OpenRouter, supported subscription connections, or local models through Ollama.
- - **Guided or expert setup:** use a gentle walkthrough, a faster guided path or the complete configuration form. Test the saved connection before using it.
- - **Subscription and CLI options:** Claude Subscription uses the Claude Agent SDK; Codex and the bundled Antigravity CLI have their own login and host requirements. Provider access and allowance still apply.
- - **Reuse and organize:** keep connections in folders, mark favorites and select different models for different AI steps.
- - **Fallback policies:** try ordered backup connections for selected limits or outages, before output or tool activity begins.
- [](githubpages/film/media/walkthrough/act1-model-test-success.png)
- [Model connections and supported logins](docs/features/models/connecting.md) · [Model settings](docs/features/models/settings.md) · [Fallback behavior](docs/features/model-fallback-policies.md)
- ### Connected Apps (MCP)
- Give agents access to files, browsers, APIs and other services through the **Model Context Protocol**.
- - **Connect your way:** curated apps, the [MCP Registry](https://registry.modelcontextprotocol.io), a remote URL, a GitHub repository or a local command. AI-assisted setup can help configure the connection.
- - **More than tools:** browse tools, resources and reusable prompts; configure roots and opt-in model sampling where supported.
- - **Inspect before attaching:** call tools and inspect resources from the connected server's detail view. A saved connection and a successful operation are separate checks.
- - **Interactive MCP Apps:** compatible tools can return an interface inside chat. Enable Apps for the connection; support depends on the server's declared capabilities.
- - **Reuse outside FLUJO:** explicitly expose a configured server through FLUJO's local MCP proxy for another compatible client.
- [](githubpages/film/media/walkthrough/act2-desktop-commander-connected.png)
- <details>
- <summary>GitHub setup and the tool inspector</summary>
- Import a repository, install and build its server, configure its run command, then test and save the connection.
- [](githubpages/film/media/walkthrough/act2-github-parsed.png)
- The tool inspector lets you browse and call a connected server's capabilities directly:
- 
- </details>
- [Connected Apps guide](docs/features/mcp/overview.md) · [GitHub setup](docs/features/mcp/github-servers.md) · [Interactive Apps and limits](docs/features/mcp/apps.md)
- ### Agent Builder
- Start simple, then add the structure your task needs.
- - **Easy mode:** build an agent like a recipe, one plain-language step at a time.
- - **Expert visual mode:** connect Start, AI, connected-app, Static, Subflow and Finish nodes in a graph.
- - **Branching and handoff:** let a model choose the next specialist or path based on the conversation.
- - **Loops:** return to an earlier step for another pass.
- - **Subflows:** reuse another flow as a step, with configurable input context and output handling.
- - **Per-step scope:** choose each AI step's model, instructions, tools and resources. Review AI-generated flows before running them.
- [](githubpages/film/media/walkthrough/act3-agent-saved.png)
- *Easy and Expert are views of the same agent. This recording uses a Website Builder as one example.*
- [](githubpages/film/media/walkthrough/act3-expert-graph.png)
- #### Branching, loops and orchestration
- Connect one node to several successors, then describe when its handoff tools should choose each path. Connect a node back to an earlier step to create a loop. Combine these patterns to coordinate several specialists.
- 
- <details>
- <summary>Handoff tools, loops and orchestration examples</summary>
- 
- 
- 
- </details>
- <a id="orchestration--subflows"></a>
- #### Reusable subflows
- Drop in a **Subflow** node to call another flow. Choose what context it receives and how its output appears in the parent run.
- 
- [Node reference](docs/features/flows/README.md) · [Context and output modes](docs/features/README.md#process-node-vs-subflow-node-inputoutput-modes)
- ### Talk and debugging
- - **One place for every agent:** select a saved agent in **Talk**, then start or resume a conversation.
- - **Live execution view:** follow steps and tool results, with model usage and a context-window meter.
- - **Visual debugger:** set breakpoints, step through nodes, and inspect state before and after execution.
- - **Optional tool approvals:** review tool calls before they run. Approvals control actions; they do not sandbox local programs.
- - **Files, audio and revisions:** attach supported files or audio, edit a message, or branch the conversation to try a different direction.
- 
- 
- [Run and debug agents](docs/features/flows/running-flows.md) · [Chat commands and dynamic references](docs/features/dynamic-references.md)
- ### Automations
- Run a saved agent on a schedule or when something happens. **The FLUJO server must stay running; the browser tab can be closed.**
- | Trigger | Example |
- | --- | --- |
- | Schedule | Prepare a daily report or run on a custom cron schedule |
- | Webhook | Start work from an authenticated call by another service |
- | File changes | Process a file when it appears or changes in a watched folder |
- | Watch a tool | Poll an MCP tool and react to changed results or new items |
- | Website changes | React when fetched page content changes |
- | Another flow finishes | Chain work after a flow completes or fails |
- [](githubpages/film/media/walkthrough/act5-trigger-options.png)
- *Choose what starts the work. Each saved trigger has its own run history and results.*
- <details>
- <summary>Run history and the WhatsApp example</summary>
- 
- Combine a **Watch a tool** trigger with a WhatsApp MCP server to build an auto-responder. Its operation depends on the connected server, account access and agent configuration.
- 
- </details>
- Failed tools, provider limits and approvals can need attention. Schedule catch-up can admit one missed occurrence; it does not replay every missed run. The Triggers page retains saved schedules during refresh errors and offers **Try again**. Pause changes wait for confirmation, failed deletions remain retryable, and stalled requests release the controls after 30 seconds.
- [Automation setup and recovery](docs/start-here/using-flujo.md#schedule-work-after-a-manual-run-succeeds) · [Scheduled occurrence accounting](docs/features/scheduled-occurrences.md)
- ### Meetings — experimental
- Bring multiple agents into a shared conversation around a topic. Choose participants and facilitation in **More → Meetings**.
- [](githubpages/film/media/walkthrough/act5-meeting-setup.png)
- *The walkthrough previews this setup without creating or running a meeting.*
- <details>
- <summary>Earlier multi-agent meeting example</summary>
- 
- </details>
- ### Personas and Roles — experimental
- A Persona is an ongoing helper with a name, a Role, memories, conversations and goals. Review its work and memories, adjust its setup, and pause or stop ongoing goals. Enable experimental features in **Settings** to explore Personas.
- [](githubpages/film/media/walkthrough/act5-maya-desk.png)
- [Follow Maya's workshop example](docs/journeys/persona.md). Its three “days” are compressed demonstration sessions, with operator review and corrections; they do not establish unattended reliability over elapsed days.
- ### Waves — experimental
- See flows and their relationships in one place, or explore planned timing in the Day view. The overview is read-only; forecasts are distinct from execution results.
- [](githubpages/film/media/walkthrough/act5-waves-overview.png)
- ### External tool integration
- Reuse FLUJO from Cline, Roo Code, Cursor, an OpenAI SDK client or another compatible MCP client.
- | Surface | Use |
- | --- | --- |
- | `http://localhost:4200/v1` | Select a `flow-<your-flow-name>` model to run an agent through the OpenAI-compatible API |
- | `http://localhost:4200/mcp-flows` | Access flows through FLUJO's MCP transport |
- | `http://localhost:4200/mcp-proxy/<server-name>` | Reuse an explicitly exposed MCP server's tools and resources; the proxy is currently localhost-only |
- The default local profile accepts a compatibility API-key value; that value is not authentication. An explicitly enabled owner policy requires an issued, scoped bearer. These interfaces have exposure and workspace-access rules; see the [API reference](docs/api-reference/README.md).
- FLUJO connects **to Ollama** as a model provider. It does not expose an Ollama-compatible server endpoint.
- #### Built-in API documentation
- Open **/docs** in the running app for searchable HTTP documentation with examples for chat, conversations, models, flows, MCP, automations and administration. The reference is curated; the [route inventory](docs/api-reference/routes.md) covers the source handlers.
- 
- [Developer and integration guide](docs/start-here/developers.md)
- <a id="-getting-started"></a>
- ## Getting started and examples
- 1. Install FLUJO and open **AI Setup → Connect AI**. Save and test a model connection.
- 2. Add any tools your task needs under **Connected Apps**; test an operation before attaching them.
- 3. Open **Agents → Start simple**, describe the steps, bind their models and tools, name the agent and **Save**.
- 4. Choose **Try it** to talk to the agent. Return to its editor to change instructions or use the Expert graph.
- 5. After a manual run succeeds, add an automation or connect an external client if your task needs it.
- Choose an example:
- | Guide | What it demonstrates |
- | --- | --- |
- | [First AI-only conversation](docs/getting-started/README.md) | The shortest path from a model connection to a reply |
- | [Coffee-reading helper](docs/journeys/first-agent.md) | Install a web-reading tool from GitHub, use it in chat and check the answer against its source |
- | [Website Builder](docs/journeys/website-builder.md) | Reuse a general agent for a site brief, then review and revise its local output |
- | [Plan with Maya](docs/journeys/persona.md) | Continuing context, memory and goals across resumed demonstration sessions |
- [Everyday use and recovery](docs/start-here/using-flujo.md) · [Compare working styles with Claude, Goose, Dify, n8n, OpenClaw and Hermes](docs/start-here/compare.md) · [Full documentation](docs/README.md)
- <details>
- <summary>Installation, updates and maintenance</summary>
- The detailed instructions remain available for each setup:
- - [Windows installer, PowerShell options and updates](docs/start-here/windows.md)
- - [Linux/macOS installation and updates](docs/start-here/unix.md)
- - [Run the published npm package](docs/start-here/npm.md), including data paths and embedded launcher settings
- - [Build from source](docs/start-here/source.md), with supported Node versions and manual setup
- - [Docker](docs/start-here/docker.md), including persistent volumes, rebuilds, tool runtimes and Apps ports
- - [Corporate proxies, custom certificates and browser-download recovery](docs/start-here/proxy.md)
- - [Windows uninstall and backup guidance](docs/start-here/uninstall.md)
- </details>
- ## Privacy and workspace controls
- - **Local workspace storage:** models, agents, chats and settings live on your computer. Cloud providers and remote tools receive the data required for their requests and may charge separately.
- - **Credential protection:** set your own encryption password. The public default is obfuscation, not a private vault; historical plaintext records need explicit repair. [Encryption and migration](src/utils/encryption/README.md).
- - **Shared values:** store a credential or value once in **Settings → Global variables**, then bind it into model and app configurations.
- - **Workspaces and backups:** organize projects separately, back up and restore them. Backups and portable-worker snapshots can contain credentials. [Workspaces](docs/features/workspaces.md) · [Transfer rules](docs/features/hot-clone-workspace.md).
- - **Usage sharing:** an anonymous daily-active pulse is on by default. It contains version/platform/install metadata and a daily-changing identifier, not prompts, keys or conversation content. Control sharing and its notice in **Settings → Privacy & Usage**.
- <a id="network-exposure"></a>
- ### Network exposure
- The default installation is for one trusted operator on localhost, without a sign-in screen or separate user accounts. **Settings → Network access** controls exposure, not authentication. Deliberate LAN or public exposure needs appropriate authenticating controls; public/shared hosting acceptance remains open. Workspace selection does not provide user isolation.
- 
- [Network deployment guide](docs/start-here/network.md) · [Privacy and costs](docs/start-here/privacy.md) · [Security policy](SECURITY.md)
- ## Roadmap and maturity
- | Capability | Current scope |
- | --- | --- |
- | Model connections, chat and visual agents | Available, including branching, loops, subflows, debugging and tool approvals |
- | AI-assisted flow generation | Available; review the generated steps and tool access |
- | MCP connections and interactive Apps | Available within the server's capabilities and documented protocol limits |
- | Automation triggers | Available while the server runs; inspect results and recover failures |
- | Workspaces and portable workers | Available within their data, authentication and credential-transfer boundaries |
- | Meetings, Personas, Roles, persistent goals and Waves | Experimental; supervision and recovery can be needed |
- | MCP Skills, resumable subflow sessions and selected generators | Opt-in experiments; see their feature flags and guides |
- [Project status](docs/project-status.md) · [Release history](CHANGELOG.md) · [Persona acceptance criteria](docs/performance/persona-goal-endurance-acceptance.md)
- ### Project vision — Soon(tm)
- **World: one avatar, one voice, and work that happens in the background.** One virtual home to bring everything into one place.
- 
- **Swarms: bring FLUJO into the cloud.** One machine, ten machines, a hundred machines — with a long-term ambition of thousands of agents working together, using supported Claude/Codex subscription access and a copy of your local MCP configuration.
- 
- These are longer-term ambitions. Related directions include real-time voice, deeper roots/checkpoint support and builds suited to smaller devices. See the [current project status](docs/project-status.md) or [share a feature request](https://github.com/mario-andreschak/FLUJO/issues).
- ## Contributing and community
- Contributions, bug reports and ideas are welcome. [Read the contributor guide](docs/contributing/README.md), pick a [starter task](docs/contributing/starter-backlog.md), or open a pull request. Maintainers have a separate [release procedure](docs/npm-release.md).
- - [GitHub issues](https://github.com/mario-andreschak/FLUJO/issues) · [Discord](https://discord.gg/KPyrjTSSat)
- - Project author: [mario-andreschak](https://github.com/mario-andreschak) · [LinkedIn](https://www.linkedin.com/in/mario-andreschak-674033299/)
- - [Original product film and studio](https://flujo.com.co/short/) · [Guided walkthrough](https://flujo.com.co/film/)
- - [Developer notes, response formatting and debugging options](docs/start-here/developers.md#response-and-debugging-options)
- FLUJO is [MIT licensed](LICENSE), powered by [PocketFlow](https://the-pocket-world.github.io/Pocket-Flow-Framework/), and built with Cline, Claude Code and a lot of love.
- ### Bonus: “A sad song about MCP”
- [](https://www.youtube.com/watch?v=boOS9XHQdZc)
- ## Star History
- <a href="https://www.star-history.com/?repos=mario-andreschak%2Fflujo&type=date&legend=top-left">
- <picture>
- <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/chart?repos=mario-andreschak/flujo&type=date&theme=dark&legend=top-left" />
- <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/chart?repos=mario-andreschak/flujo&type=date&legend=top-left" />
- <img alt="Star History Chart" src="https://api.star-history.com/chart?repos=mario-andreschak/flujo&type=date&legend=top-left" />
- </picture>
- </a>
- ## Ecosystem
- [](https://mseep.ai/app/mario-andreschak-flujo)
- [](https://mseep.ai/app/3f62578d-605f-474c-9472-c5e40df60ee0)
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.