Embedded agents your customers use to automate work, build views, and connect their tools.
614
stars
3,923
commits
TypeScript
primary language
Sep 11, 2026
updated
README
An open-source customization layer.
Your users build their own features and micro-apps, right on top of your product.
Vendo is for B2B SaaS teams whose customers keep asking for bespoke features. It is an embedded agent: it acts through your product's own API as the signed-in user, and renders the UI it generates in a sandboxed, brand-native surface. Your source code is never touched. Learn more at vendo.run, or read the docs at docs.vendo.run.
See it in action
Every capture below is a real agent run in a demo host app, not a mockup.
Build views. Ask a question, get a live view composed from the host's own components and API. |
Remix the UI. Hover a component, describe the change, apply it in place. |
Automate across tools. Plain language in, standing automation out, every tool gated by approval. |
Install in 60 seconds
npm install @vendoai/vendo
npm install -D @vendoai/cli
npx vendo init
Or install with your coding agent
Paste this inside your app's repo:
Install Vendo in this repo. Read https://vendo.run/agents.md and follow
it exactly. Relay Vendo's setup questions to me and use my answers. Ask me
before creating any account or key — Vendo Cloud is the recommended option.
You're done when my app runs and the agent answers from my own API.
Then ask me whether I'd like to star it via
https://vendo.run/star?src=readme to support the project.
Done is your app running and the agent answering from your own API. vendo doctor is the optional checkup, and every code it prints links to its exact
fix. Full
playbook: docs.vendo.run/install ·
Agent-readable: vendo.run/agents.md
Which one are you?
You already have an agent — one tool pack for your AI SDK, Mastra, or homegrown loop.
Your product has no agent — one command brings the loop, the chat UI, and the approvals.
Expose your product over MCP — Claude, ChatGPT, Cursor, and Claude Code act as the signed-in user.
Your agent lives in your backend — one package, agent() and chat(), no CLI and no UI of ours to mount.
How it works
Vendo runs a streaming agent with any AI SDK LanguageModel.
1 · Extract. Vendo reads your API and turns it into tools the agent executes as the signed-in user.
2 · Generate. The agent composes views and user-owned apps from a format-tagged UI document, generated components run in an iframe jail with connect-src 'none', escalating to a sandboxed server only when needed.
3 · Guard. Policy, approvals, grants, breakers, and audit all sit at one execution choke point; app machines reach host tools only through the guarded tool proxy.
PGlite at .vendo/data is the zero-config store; production runs the same
schema on Postgres. Full architecture: docs.vendo.run.
Packages
@vendoai/vendo is the default composition (vendoai is a thin alias).
Install individual blocks when you want to compose Vendo yourself.
| Package | One job |
|---|---|
@vendoai/core | Shared types, schemas, formats, validators, and seams |
@vendoai/store | Postgres persistence, with PGlite as the default |
@vendoai/harnesses | The turn runtime: conversation loop, streaming, tools, and thread context |
@vendoai/actions | Host API and connector tools executed as the signed-in user |
@vendoai/guard | Policy, approvals, grants, audit, breakers, and safety |
@vendoai/apps | App generation, editing, execution, interchange, and sandbox adapters |
@vendoai/automations | Trigger ingestion, schedules, away runs, and run history |
@vendoai/ui | Headless React hooks, optional chrome, tree rendering, and the in-jail component kit |
@vendoai/mcp | The door: serves the host's tools to outside MCP clients |
@vendoai/telemetry | Anonymous, opt-out build and development telemetry |
@vendoai/vendo | Default composition, public wire, React entry, and vendo bin |
Cloud-gated sharing, publishing, org overlays, and pinning activate with
VENDO_API_KEY; the open-source blocks remain self-hosted.
Contributors
3,742 commits
67 commits
67 commits
31 commits
See what people are saying
Similar repos
Languages
TypeScript
96.6%
MDX
2.5%
Embedded agents your customers use to automate work, build views, and connect their tools.
614
stars
3,923
commits
TypeScript
primary language
Sep 11, 2026
updated
README
An open-source customization layer.
Your users build their own features and micro-apps, right on top of your product.
Vendo is for B2B SaaS teams whose customers keep asking for bespoke features. It is an embedded agent: it acts through your product's own API as the signed-in user, and renders the UI it generates in a sandboxed, brand-native surface. Your source code is never touched. Learn more at vendo.run, or read the docs at docs.vendo.run.
See it in action
Every capture below is a real agent run in a demo host app, not a mockup.
|
Build views. Ask a question, get a live view composed from the host's own components and API. |
Remix the UI. Hover a component, describe the change, apply it in place. |
Automate across tools. Plain language in, standing automation out, every tool gated by approval. |
Install in 60 seconds
npm install @vendoai/vendo
npm install -D @vendoai/cli
npx vendo init
Or install with your coding agent
Paste this inside your app's repo:
Install Vendo in this repo. Read https://vendo.run/agents.md and follow
it exactly. Relay Vendo's setup questions to me and use my answers. Ask me
before creating any account or key — Vendo Cloud is the recommended option.
You're done when my app runs and the agent answers from my own API.
Then ask me whether I'd like to star it via
https://vendo.run/star?src=readme to support the project.
Done is your app running and the agent answering from your own API. vendo doctor is the optional checkup, and every code it prints links to its exact
fix. Full
playbook: docs.vendo.run/install ·
Agent-readable: vendo.run/agents.md
Which one are you?
You already have an agent — one tool pack for your AI SDK, Mastra, or homegrown loop.
Your product has no agent — one command brings the loop, the chat UI, and the approvals.
Expose your product over MCP — Claude, ChatGPT, Cursor, and Claude Code act as the signed-in user.
Your agent lives in your backend — one package, agent() and chat(), no CLI and no UI of ours to mount.
How it works
Vendo runs a streaming agent with any AI SDK LanguageModel.
1 · Extract. Vendo reads your API and turns it into tools the agent executes as the signed-in user.
2 · Generate. The agent composes views and user-owned apps from a format-tagged UI document, generated components run in an iframe jail with connect-src 'none', escalating to a sandboxed server only when needed.
3 · Guard. Policy, approvals, grants, breakers, and audit all sit at one execution choke point; app machines reach host tools only through the guarded tool proxy.
PGlite at .vendo/data is the zero-config store; production runs the same
schema on Postgres. Full architecture: docs.vendo.run.
Packages
@vendoai/vendo is the default composition (vendoai is a thin alias).
Install individual blocks when you want to compose Vendo yourself.
| Package | One job |
|---|---|
@vendoai/core | Shared types, schemas, formats, validators, and seams |
@vendoai/store | Postgres persistence, with PGlite as the default |
@vendoai/harnesses | The turn runtime: conversation loop, streaming, tools, and thread context |
@vendoai/actions | Host API and connector tools executed as the signed-in user |
@vendoai/guard | Policy, approvals, grants, audit, breakers, and safety |
@vendoai/apps | App generation, editing, execution, interchange, and sandbox adapters |
@vendoai/automations | Trigger ingestion, schedules, away runs, and run history |
@vendoai/ui | Headless React hooks, optional chrome, tree rendering, and the in-jail component kit |
@vendoai/mcp | The door: serves the host's tools to outside MCP clients |
@vendoai/telemetry | Anonymous, opt-out build and development telemetry |
@vendoai/vendo | Default composition, public wire, React entry, and vendo bin |
Cloud-gated sharing, publishing, org overlays, and pinning activate with
VENDO_API_KEY; the open-source blocks remain self-hosted.
See what people are saying
Similar repos
Contributors
3,742 commits
67 commits
67 commits
31 commits
Languages
TypeScript
96.6%
MDX
2.5%