Skip to main content

Open Source Managed Agents for AI Native Apps

Embed deep agents directly in your products. Built in Rust.

Prompt your coding agent
Read distri.dev/SKILL.md to set up my agent
Claude Code · Codex · Cursor
import { DistriProvider, Chat } from '@distri/react';
export function Assistant() {
return (
<DistriProvider config={{
baseUrl: 'https://api.distri.dev/v1',
clientId: 'dpc_…',
workspaceId: '…',
}}>
<Chat
agentId="shop_assistant"
externalTools={[addToCart]} // your own function
/>
</DistriProvider>
);
}
webReact Native previewscript tagEmbedded agents →

See it work

Four products, each operated by an agent through the product’s own functions.

Open the gallery
  • 3D studio

    Builds a model part by part in WebGL, refinishes it, then drops 40 rigid bodies on it.

  • Design canvas

    Lays out two mobile screens on an HTML canvas, then restyles them on request.

  • KYC / KYB

    Reads two documents and fills a whole onboarding form in one structured call.

  • Checkout

    Turns one sentence into a cart, a discount and a ready-to-pay checkout sheet.

Features

Embed AI experiences in your product.

The parts every team ends up building around an agent, ready on the first day. For agents inside your product and the ones your team runs.

refund-requestWaits for you
  • fetch_orderapi_call · 412ms
  • fetch_customerapi_call · 380ms
  • assessagent_run · returns_agent
  • approvewait_for_input · waits for you
  • refundapi_call

Durable runs

Each conversation keeps its thread and memory. A workflow can stop for a person’s approval, wait a day, and pick up at the same step.

Sandboxesopensandbox · gVisor
  • thread 7f3a…running
  • thread 2c91…paused · volume kept
$ ls /workspace
report.csv  notes.md  venv/

Sandboxes on any runtime

Each conversation gets its own Linux machine and a /workspace that outlives pauses. We run OpenSandbox on Kubernetes. Bring E2B, Daytona or your own VMs instead.

Cancel order 4821, I ordered it twice
cancel_orderruns in your app
{ "orderId": "4821" }
ApproveDecline

Tools that run in your app

Give the agent the functions your product already has. They run in the user’s session, and the risky ones ask the user first.

Usage · by end user7 days
  • usr_maya$0.065
  • usr_dan$0.050no limit
  • usr_omar$0.010

429 usr_omar’s daily limit is used up. It resets at 00:00 UTC.

Cost and limits per end user

Every model call is priced against the person who made it. Cap an end user, an agent, an API key or a tag, and the next call over the cap never reaches the provider.

# agents/returns_agent.md
[model_settings]
model = "zai/glm-5.2"

# agents/product_finder.md
[model_settings]
model = "gpt-4.1-mini"
OpenAIAnthropicGeminiBedrockAzureVertexZ.ai+6

Any model, your keys

Start on our key, then add yours for any of 13 providers. Set one default model and override it per agent.

  • Telegram@acme_support_bot
  • WhatsAppshared number
  • Webhook/workflows/webhook/acme-refund
  • Schedule0 0 9 * * MON
  • MCPgithub · linear

Channels and integrations

The same agent answers on Telegram and WhatsApp, runs from a webhook or a cron schedule, and reaches your other tools through MCP.

Embedded agents

The agent runs on Distri. Its tools run in your app.

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.

Read more

Architecture

Distri runs the agent. Your product stays yours.

Most agent platforms ask you to move the work to them. Distri sits next to the product you have, and nothing gets rebuilt for the agent.

Distri runs

  • The agent loopThreads, memory, skills and multi-step plans, from a markdown file.
  • The AI gatewayEvery provider, with traces, attribution and limits on each call.
  • Channels and workflowsBots, webhooks and schedules for the same agents.
  • SandboxesIsolated code execution, switched on per agent.
  • TracesEvery turn, tool call and token, to debug and to bill.

Your product keeps

  • Screens and stateClient-side tools call your own functions; the UI updates as it does on a click.
  • Auth and permissionsTools run in the user’s session, so the agent can do what the user can do.
  • APIs and dataYour backend, and the MCP servers you already expose.
  • Provider accountsBring your own LLM keys; the account stays yours.

Where your users are

Embedded in your appin the user’s session
  • auth handshake
  • client-side tools
  • approve in your UI
Managed agent runtimerunning
  • durable runs
  • workflows
  • sub-agents
  • schedules
  • A2A
  • MCP
Your provider keysOpenAIAnthropicOpen models

Comparison

Managed-platform speed, without handing over the platform.

Building it yourself takes months. Managed agent platforms get you live fast, then decide your models, your cloud, your data and your bill.

Build it yourselfManaged agent platformsDistri
Time to productionMonthsFastDays. An agent is a markdown file and one push
Who runs itYour platform teamThe vendorUs on Distri Cloud, us in your cloud, or you
ModelsAnyOne vendor’sAny provider on your keys, a different one per agent
Where users reach itWhat you buildThe vendor’s chat or APIInside your web and mobile app, over the API, on Telegram, WhatsApp, Slack and Discord
ToolsWhat you buildThe vendor’s sandboxYour app’s own functions, your MCP servers, a sandbox per conversation
LLM trafficYou build the metering and tracingOne bill per accountEvery call traced, attributed to the end user and capped before it runs, across providers
Your dataYoursHeld by the vendorYours
PricingSalaries and infrastructureSet by the vendorFree to start. No fee to self-host
Source codeYours to maintainClosedOpen source, built in Rust
Bots / acme_ops_bot
Live
Platform
TelegramWhatsAppDiscord
Bot token
7421963:AAF••••••••••••
Runs
refund_order workflow
Trigger
MessageScheduleWebhook

/start/stop/reset/status/help

Channels, workflows and bots

The same agent, wherever the work continues.

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.

  • Slack, Telegram, WhatsApp and Discord

    The agent answers where your team and your customers already talk. Pick the agent and connect the channel; there is no server to deploy.

  • Email, CRMs and internal tools, through workflows

    A workflow starts on a schedule or a webhook, calls your APIs, and can wait for a person before it goes on.

  • Anything else, through the API

    Every agent answers over a streaming API, so your backend, a cron job or another agent can run it.

Built-in AI gateway

Understand, manage and optimise your LLM traffic.

Every model call your agents make goes through Distri’s gateway: traced end to end, attributed to the agent and the end user, held to your limits, on whichever providers you use.

UsageLast 30 days
Sample data
Cost
$212.40
Tokens
18.4M
Model calls
41,280
AgentCallsTokensCost
support_agentv0.4.121,4009.6M$118.20
form_fillerv0.2.012,3004.1M$38.90
refund_orderworkflow5,1802.9M$34.10
weekly_digestv0.1.32,4001.8M$21.20
  • End-to-end observability

    Every agent run is a trace: agent, model and tool spans with timings, tokens and cost.

  • Usage attribution

    Every model call is counted against the agent, end user, API key, use case and model.

  • Limits before the call

    Cap tokens or USD per workspace, agent, end user or API key. Over the cap, the call never reaches the model.

  • Multiple providers, your keys

    OpenAI, Anthropic, Gemini, Bedrock, Azure and more, a model per agent. The provider accounts stay yours.

Built on Distri

Start with one agent, in one flow your users already know.

Free to self-host. Distri Cloud has a free tier. See pricing →