For personal projects
OpenBot
Free
Personal development and experimentation on your laptop.
- Run on your laptop with Docker
- Bring your agents, models, and tools
- Customize your personal workspace
Your model provider charges separately for usage.
OpenBot™: AI coworkers on your terms.
A fully customizable agent application for your employees, running on infrastructure you own. Bring your choice of models and custom agents built on your stack, with company knowledge, permissions, and computer use in one place. Customize it yourself, or have our engineers do it with you and hand it over.
OpenBot
Start a new channel
Ask anything
Goes to General Assistant. Type @ to reach somebody else.
Explore agents
General AssistantHelp with everyday work using clear, concise, and accurate answers.
ResearchGathers context from documents, drafts from it.
KnowledgeAnswers from company documents, with sources.
MetricsReads the warehouse and draws the answer.
Channels
Message agents like teammates
Every agent gets its own channel, the way a colleague gets their own thread. Ask for something, watch the work happen, and come back to it later with the whole history intact.
- One thread per agent
- Context stays where the work happened instead of scrolling away in a single shared window.
- Skills on a slash
- Each agent exposes only the skills it has been granted, and they are discoverable from the composer.
Knowledge
Answers from your company's documents
Connect Google Drive and your agents answer from what your company already wrote down — with the sources attached, so an answer can be checked rather than trusted.
- Permissions are fail-closed
- An agent only ever sees files the person asking is already allowed to open. When permissions are unclear, it returns nothing rather than guessing.
- Cited, not asserted
- Every answer names the documents behind it, so the reader can go and read them.
Computer use
Agents that use your tools
When there is no API worth using, an agent signs in and drives the interface the way a person would. You can watch the screen while it works, and take the wheel whenever you want to.
- Watch it work
- The screen opens beside the conversation, so the work is visible rather than something you are told about afterwards.
- Take the wheel
- Step in mid-task without losing the thread, then hand it back.
- A computer per agent
- Each agent can be given a container of its own, with its own files and its own signed-in browser, so a login one agent holds is not one the next agent can pick up. The boundary is drawn per agent rather than per person.
Roles
Give each agent a job
An agent is a role, not a chatbot. Publish the ones your company needs, grant each only the skills and sources its job requires, and let people talk to them by name.
Company knowledge
Answers policy and process questions from the documents your company already wrote, and names its sources.
Warehouse analyst
Queries the analytics warehouse and draws the answer rather than describing it. Read-only by construction.
Desk research
Gathers context from the open web and drafts from it, keeping contradictory sources rather than quietly picking one.
Tool operator
Signs in and works inside the tools that have no API worth using, with the screen open so you can watch.
Inbox triage
Reads what arrived, drafts the replies that are obvious, and leaves the ones that are not for you.
Onboarding buddy
Answers the questions a new starter asks in week one, from the handbook rather than from memory.
Built on AG-UI
From the team behind the protocol
AG-UI is the Agent–User Interaction Protocol: the open, event-based standard for how an agent talks to the application a person is actually looking at. We wrote it, we maintain it, and we ship the reference implementation.
Adopted by
MCP is context
How an agent pulls in tools and external knowledge.
A2A is coordination
How agents hand work to one another.
AG-UI is interaction
How the work becomes something a person can watch, question and interrupt. It is the leg the other two do not cover.
For you this means no bet on a single framework. Any agent that speaks AG-UI — LangGraph, Mastra, PydanticAI, or one your team writes — is registered as an endpoint and gets a channel.
Ownership
Runs on your infrastructure
The reason most AI pilots stall is not the model. It is that nobody can say where the data went. OpenBot runs where your other internal systems run, and the answers below are the ones your security review will ask for.
- One deployment, one company
- Each company gets its own deployment. Docker Compose stands up a demo; Helm is the supported path to production.
- Your content never leaves
- Documents, vectors, permissions and conversations live in your Postgres. Nothing is sent anywhere you did not configure.
- Your models, your keys
- Admins hold the provider credentials. Keys are encrypted at rest with your key-encryption key, never returned, never logged, and revocable.
- No bundled model
- The built-in agent stays unavailable until an admin configures a provider. Nothing silently falls back to somebody else's LLM.
- Retrieval fails closed
- Permissions from the source normalise to allow and deny principals, deny wins, and a document with an ambiguous mapping is not returned at all.
- Tool calls are gated
- Sensitive MCP calls go through a gateway with an explicit per-tool allowlist, and every call and outcome is recorded.
Pricing
Personal projects. Company-wide work.
Free for personal projects. OpenBot for Business™ starts at $29 per user per month.
OpenBot for Business™
Pay as you go
Starts at$29 / user / month
- A per-user rate that falls as your team grows
- Credit card billing, monthly, with no commitment
- Standard support included
- Self-hosted by default, or hosted by us in early access
Self-hosted or hosted, the same plan price.
OpenBot for Business™
Annual
Custom pricing
- SSO and role-based access control
- Offline and air-gapped deployment
- Custom contract terms
- 24/7 production support
- Invoicing and purchase orders
- AWS Marketplace private offers
Self-hosted, hosted, or offline and air-gapped.
Pay as you go
What would it cost your team?
Pay for the people who use it. Unlimited Bots, with no per-bot, per-agent, or per-interaction charge.
1 user10K+ users
One interaction in the month makes someone active. Each person counts once.
Estimated monthly plan price
$725/ month
$29.00 per active user per month
For 25 active users. Model provider usage and your own infrastructure costs are separate.
Model usage
Your models. Your provider bill.
You pay your model providers directly. We do not resell inference or mark up tokens.
A 5% charge on model spend above $5,000 per month, per organization, applies to both pay as you go and Annual. Billing begins when spend metering is available.
For example, $4,000 in monthly model spend adds no usage charge. At $10,000, the usage charge would be $250, calculated on the $5,000 above the threshold.
FAQs
Questions
See it running inside your company
The source is open, so you can read exactly how permissions, tool gating and the channel model work before you talk to anybody. When you want it standing up on your own infrastructure, or customized into something that looks like your own product and handed back to you to keep changing, that is the conversation to have with us.
