The open-source desktop AI app
for agents, research, writing, slides, apps and workflows.agents
Use your own API keys or local models, and ask across your own files. Give a workflow an agent that runs commands and edits files in a folder you choose, asking before it acts, and track what you spend each day.
- Free and open source (AGPL-3.0)
- No account, no subscription
- Windows, macOS, and Linux
A release candidate: installers aren't OS code-signed yet, so expect a SmartScreen or Gatekeeper prompt on first launch. Details
What it does
What you can do with it
Agents
Agents that work on your computer, and ask before they act
Give a workflow an agent and it does the job itself. It reads your files, uses your connectors and, if you turn it on, runs commands and edits files in a folder you choose.
- Every command asks first, unless your rule covers it
- Every file change shows its diff first
- Off until you turn it on, per workflow
Workflows
Routines that run on a schedule or when something new arrives, and ask first
Describe a routine in your own words, or start from a ready-made one. Run it now, on a schedule, or when a feed or folder gets something new.
- Fetch, search, research, summarise and save
- Lists what it may do alone, for you to approve
- Anything waiting on you lands in one Inbox
Research
Every claim backed by a real quote
Approve a short brief, then Conduit searches, reads the full pages and writes a report with numbered sources.
- Each claim quoted from its source, and checked
- Weak sources are marked
- Quick, Standard or Deep: 8 to 50 searches
Writing
Better blog posts, docs and reports
Agree the outline first, then the draft fills in section by section. Ask for a change and only that part moves. Your own sentences stay word for word.
- Cites the pages, documents and reports it used
- Marks a missing fact as a TODO
- Export Markdown or print-ready HTML
Slides
A deck you edit by asking, not a file you regenerate
Approve a storyline, then get one live deck. Ask for a change and it edits that slide instead of making a new file.
- Charts drawn from your numbers
- Presenter window with notes and a timer
- Export one HTML file, or a PDF on Windows
Apps
Keep what it builds, and open it any time
Save a page the assistant built as a personal app. Open it from Apps whenever you need it, even after the chat is gone.
- Eight starter apps built in
- Each app declares the sites it can reach
- Asking your AI model needs your OK first
Connectors
Plug in any MCP server, on your own terms
Install a server from the official MCP registry in one click, and its tools work in every chat.
- Read-only tools just run. Others ask first
- OAuth, with tokens in your OS keychain
- Approvals you can review and revoke
White-label
Make it your own
Put your name, logo and colours on Conduit with one brand.md file. It's configuration, not a fork, so it updates with Conduit.
- Rebrand any install in Settings
- Light and dark palettes, contrast-checked
- Branded installers in early access
Every feature, with its limits
Try it on your own keys
Free and open source, on Windows, macOS and Linux. Bring a key, or point it at a model you already run.
Models
The models you already pay for
Seventeen providers built in. Paste a key and pick from the list the provider returns, or skip the key and run a model on your own machine.
Model labs
Your own key, at the lab's own price.
- Anthropic Claude
- OpenAI GPT
- Google Gemini Gemini
- xAI Grok
- DeepSeek
- Mistral
- Z.ai GLM
- Moonshot AI Kimi
- Qwen
Gateways and fast inference
One key for hundreds of models, or the quickest hosts for open-weight ones.
- OpenRouter
- OpenCode Zen
- Groq
- Together AI
- Fireworks AI
On your machine
No key and no cost. With local-only mode on, no internet either.
- Ollama
- LM Studio
- Any OpenAI-compatible endpoint
MiniMax, and whatever shipped this week, comes through OpenRouter, OpenCode Zen, or any OpenAI-compatible endpoint.
Cost
Know what you spend
Requests go from your machine straight to the provider you picked, at that provider's own price. Conduit adds nothing on top and resells no tokens.
Settings charts your estimated cost per day and per model. Prices come from your own overrides first, then the provider's live listing, then a bundled price table, and a model with no known price says so instead of showing $0.
- Your provider's per-token price, with no markup
- Set any model's price yourself
- An optional alert when a day's estimated spend passes your amount
- Local models through Ollama or LM Studio cost nothing
Get Conduit
Download Conduit
The latest release is the current build — installers for Windows, macOS (Apple silicon and Intel), and Linux. It is a release candidate rather than a 1.0: expect rough edges, and read the note on installers below before you run it.
Or build from source
# clone, install, run
git clone REPO_URL conduit
cd conduit
pnpm install
pnpm devYou'll need Node 20, pnpm 10.34.4, and a stable Rust toolchain — plus Visual Studio 2022 Build Tools on Windows. Full instructions, including how to add your first provider, are in the documentation.
More about Conduit: use cases · how it compares · every network flow · white-label
FAQ
Questions, answered plainly
Is Conduit free?
Yes, and it's open source. You pay your model provider directly — Conduit never proxies your requests or resells tokens, so there is nothing to subscribe to.
Do I need an API key?
For hosted providers, yes — you bring your own. If you'd rather not use one, run Ollama or LM Studio locally and Conduit will talk to them with no key and no cost.
What will it cost me to run?
Whatever your provider charges, and nothing on top — Conduit takes no cut, adds no subscription, and sends you no bill at all. What you actually spend depends on which model you pick and how hard you use it, which is why the app charts your cost and tokens per day from your own usage rather than leaving you to find out on a statement. Running Ollama or LM Studio locally costs nothing.
Which models does Conduit support?
The ones people actually use — GPT, Claude, Gemini, Grok, GLM, DeepSeek, Kimi, Qwen, MiniMax — and anything else your provider lists. Seventeen providers are built in, including dedicated ones for xAI, Z.ai, Moonshot AI, and Qwen. MiniMax, and whatever shipped this week, comes through OpenRouter, OpenCode Zen, or any OpenAI-compatible endpoint. A model you already run in Ollama or LM Studio needs no key at all.
Where does my data go?
Your conversations, attachments, documents, and artifacts stay in a local SQLite database and blob store on your machine. What leaves it is what a feature needs, sent from your machine straight to the service you picked — your messages to your chat provider, including the text of a document you attach to a message (or the PDF itself, for models that read PDFs), a document's text to the embedding provider when you add it to a collection, and a search query when you turn web search on. The privacy page lists every one of those flows and its default.
Can I chat with my own documents?
Yes. Add text, Markdown, CSV, Word, or PDF files to a collection under Documents, attach it to a chat, and the reply names the files it drew on — click one to read the exact passage. Files are parsed on your machine and the index lives in your local database. To be searchable, a document's text is sent once to the embedding provider you choose (OpenAI, Gemini, or OpenRouter, after you agree to it); pick Ollama and it never leaves your machine. Scanned PDFs without a text layer can't be read into a collection. For a single file, attach it to your message instead, and the model gets its text, or the PDF itself if it reads PDFs, and that content goes to your chat provider with the message. How it works, step by step.
Does it phone home?
No. The app has no background telemetry, no analytics, and no usage reporting. Update checks are manual by default — nothing contacts the update server until you press Check now, and background checking is something you switch on yourself. Update payloads are signature-verified before anything is applied. (This website is separate and does use Google Analytics — see the privacy page.)
Will my system warn me when I install it?
Yes. The binaries aren't OS code-signed yet, so Windows SmartScreen and macOS Gatekeeper flag them on first launch. Building from source avoids this entirely.
Update payloads are separately signed and verified, so the update path is protected even while the installer isn't.
Can I run a completely local model?
Yes. Ollama and LM Studio are supported directly, as is any OpenAI-compatible server you host yourself. Combined with local-only mode, and with update checks switched off, Conduit will make no internet requests at all. Running models locally covers the setup.
Is there an open-source Claude Desktop alternative?
Conduit is one. It is AGPL-3.0 licensed, keeps conversations on your own machine, and talks to seventeen providers rather than one — but Claude Desktop is more mature and its installers are code-signed, which ours are not yet. The full comparison lists the rows each one wins.
What MCP clients run on Windows?
Several, including Claude Desktop, Cursor, and Conduit. Conduit runs on Windows 10 and 11 with no feature differences from macOS or Linux, and speaks MCP over both local stdio and remote streamable HTTP with OAuth. More on Conduit as an MCP client.
Can I white-label an AI chat client?
Partly, today. You can change the name, logo, and colours of a stock Conduit install from Settings → Branding; producing your own signed installer with your connectors pre-wired is not finished yet. The white-label page has the capability table and says plainly what is missing.
How is this different from a browser-based front end?
Conduit is a native desktop application, not a web app you host. That's what makes the OS keychain, a local database, supervised local tool processes, and true offline use possible — none of which a browser tab can do.