Free
$0free while in beta
- 1 workspace
- Embedded agents, bots and the AI gateway
- Usage and cost per agent and end user
- Bring your own model keys
Distri runs the agent. Its tools are functions your app already has, and they run in the user’s session, behind your auth, on your own screens. Nothing gets rebuilt for the agent.
curl -fsSL https://distri.dev/install.sh | shWhere your users are
See it work
Four products, each operated by an agent through the product’s own functions.
Open the gallery



Quick start
An agent is a markdown file. Install the CLI, sign in, and push the folder to your workspace.
---name = "shop_assistant"description = "Helps shoppers check out"
[tools]external = ["add_to_cart"]
[model_settings]model = "gpt-4.1-mini"---
# ROLEYou help shoppers on our store.curl -fsSL https://distri.dev/install.sh | shdistri logindistri pushThe agent is in your workspace, ready to be called from your product.
Pass the functions the agent may call as client-side tools and render the chat. The handlers run in the browser.
// npm install @distri/react @distri/coreconst addToCart: DistriFnTool = { name: 'add_to_cart', description: 'Add a product to the cart', type: 'function', parameters: { type: 'object', properties: { sku: { type: 'string' } }, }, autoExecute: true, handler: async ({ sku }) => { await cart.add(sku); // your code return { ok: true, items: cart.count }; },};
<DistriProvider config={{ baseUrl, clientId }}> <Chat agentId="shop_assistant" externalTools={[addToCart]} /></DistriProvider>Not on React? The same tool works from React Native or a script tag.
A streaming chat renders inside your app. How client-side tools work
Open your app and type. The agent calls your function, and your UI changes the way it does for a click.
Add two oat milks to my cart
add_to_cartran in your app{ ok: true, items: 3 }
Added 2 × Oat milk 1 L. Your cart has 3 items.
Each run is recorded with its tokens and cost. Usage · Traces
You need a model provider key, for example OPENAI_API_KEY. Prefer your own machine? Run it locally, or follow the full guide.
01 · Embedded agents
Your product already knows how to do the work. Hand the agent the same functions, and when it calls one, your handler runs in the user’s browser or on their phone.
Give the agent a name, a JSON Schema and a handler. It can fill your form, add to your cart or move your router.
In the browser or on the phone, in the user’s session and behind your auth. There is no second API to build for the agent.
Drop-in chat components, a React Native package in preview, or one script tag with no build step.
Add two oat milks to my cart
add_to_cart({ sku: "oat-milk-1l", qty: 2 })await cart.add("oat-milk-1l", 2)No endpoint was built for the agent, and no credential left your app. Distri saw a tool name, its arguments and what your function returned.
Your stack stays
Most agent platforms ask you to move the work to them: a sandbox, a new chat surface, a second set of APIs. Distri works through the product you have.
/start/stop/reset/status/help
Refund order 4821, the lamp arrived broken
Order #4821
Ceramic lamp · $64.00
Paid by card on 12 Nov
Refund the full amount?
refund_order · resumed after wait_for_input
Done. $64.00 is on its way back to the card ending 4242, and the customer has been emailed.
02 · Channels, workflows and bots
Not every step happens on your screens. The agent you embedded can answer in a chat thread, run on a schedule, or wait for an approval from your team.
The agent answers where your team and your customers already talk. Pick the agent and connect the channel; there is no server to deploy.
A workflow starts on a schedule or a webhook, calls your APIs, and can wait for a person before it goes on.
Every agent answers over a streaming API, so your backend, a cron job or another agent can run it.
03 · Cost per end user
An agent in front of your customers spends money on their behalf. The gateway records every model call against the agent and the end user, and stops a user at their limit before the call is made.
support_agentv0.4.121,4009.6M$118.20form_fillerv0.2.012,3004.1M$38.90refund_orderworkflow5,1802.9M$34.10weekly_digestv0.1.32,4001.8M$21.20Every call is recorded with its tokens and cost against the agent, end user, API key, model and source.
Per workspace, agent, end user or API key, in tokens or USD. Over the limit, the API answers 429.
Bring your own LLM keys. Distri meters the calls; the provider account stays yours.
Built on Distri
Pricing
Start on Distri Cloud for free. Enterprise runs in our cloud, in yours (BYOC) or self-hosted, with SLAs.
$0free while in beta
Contact Us
Custom
FAQ
curl -fsSL https://distri.dev/install.sh | sh, write a markdown file with a TOML front matter block (name, [tools], [model_settings]) and a system prompt, then run it with distri run --task "..." --agent NAME. Local runs need no account, only a model provider key.distri login, then sync your agents to Distri Cloud with distri agents push agents/ --all. Skills, prompts and workflows push the same way (distri skills push, distri workflows push).Free to self-host. Distri Cloud has a free tier.