LegitShow is the trusted source on every newly launched software product: what it does, who it’s for, how it actually holds up, and whether the AI engines are already reading it. Built to be what AI cites.

Web apps, SaaS, AI tools, MCP servers and developer tools. How we measure →


Legit.Show benchmarks every launched service it lists — measured deterministically from the public surface. See the methodology →

Cross-links · Directory · Reports · Insights · What AI reads · Methodology · About

Privacy · Terms · @Legit_Show on X · GitHub · operated by Madeflo Inc., a Delaware corporation. Benchmark engine powered by commit.show.

AI & Agents

OpenBot

Source: CopilotKit/OpenBot · ★ 1901 · TypeScript

Last updated 2026-08-21 · benchmark measured 2026-08-21 — deterministic & reproducible

CopilotKit pricing plans for building agentic UI and AI copilot products.

OpenBot at a glance

OpenBot is a customizable AI agent application from CopilotKit that companies run on their own infrastructure, giving employees dedicated chat channels to work with agents that can read company documents and use software tools.

Good for

  • Organizations that want to self-host AI agents instead of using a shared cloud tenant
  • Companies with sensitive data that need documents, permissions, and conversations to stay in their own database
  • Development and enterprise teams building agentic applications with frontend SDKs and backend connections

Pricing

Developer: free. Pro: $39/month. Team: $100/seat/month (up to 5 seats). Enterprise: custom pricing.

Questions people ask

What is OpenBot and what does it cost?
OpenBot is a customizable agent application that runs on infrastructure the company owns. CopilotKit's plans for building this kind of product are Developer (free), Pro ($39/month), Team ($100/seat/month, up to 5 seats), and Enterprise (custom pricing).

Can an agent see documents I'm not allowed to see?
No. Permissions are fail-closed, meaning an agent only sees files the person asking is already allowed to open, and it returns nothing rather than guessing when permissions are unclear.

Which systems can OpenBot connect to?
It can connect to Google Drive and OneDrive for company documents, and to Slack or Teams for channels. For tools without an API, an agent can sign in and use the interface directly through computer use, with the screen visible during the task.

Where does the data live, and who controls the AI models used?
OpenBot runs on the company's own infrastructure, with documents, vectors, permissions, and conversations stored in the company's own Postgres database. Admins hold the model provider credentials, which are encrypted at rest and never logged.

Can we bring our own agents instead of using the built-in ones?
Yes. Any agent that speaks the AG-UI protocol, including ones built with LangGraph, Mastra, PydanticAI, or a team's own framework, can be registered as an endpoint and given its own channel.

Written by Legit.Show from copilotkit.ai on 2026-09-30. It does not change the score.

74/100
5/7 frames
Top 66% of 17,496 measured
Legit Benchmark — the simple average of 5 measured frames. Frames we could not measure are left out of the average, never counted as zero. Every frame is shown below with its evidence.
Checked 2026-08-21 · scores move as sites change

Are you the maker of OpenBot? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.

Launched something? Add your product, free.

To cite this score: legit.show/s/gh-copilotkit-openbot/2026-08-21. That address never changes; this page moves with every re-measure.

Legit.Show scored OpenBot 74/100 on 2026-08-21, measured across 5 of 7 frames from its public surface. legit.show/s/gh-copilotkit-openbot/2026-08-21

Is OpenBot production-ready?

Legit.Show scores OpenBot 74 out of 100 — the simple average of its 5 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on OpenBot (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Discoverability; its weakest is Security. 5 of the seven frames returned a score; Performance and Accessibility were not measurable on this service and are recorded as null — not as zero. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

What we measured

Who built it

Atai Barkai · product account @CopilotKit

Who it's for

Enterprise teams · Development teams · Organizations needing self-hosted agents · Companies with sensitive data

Pricing

Free (Developer plan); $39/month (Pro); $100/seat/month (Team); Custom pricing (Enterprise)

Sources and updates

Description
Taken from copilotkit.ai's own website on 2026-08-21.
Operator
Tawkit, Inc., as named in copilotkit.ai's terms, privacy page or footer.
Code
github.com/CopilotKit/OpenBot.
Benchmark
Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-08-21.

Put together from public information, without OpenBot's involvement. If anything here is wrong, tell us and a person will check it.

Visit OpenBot → · Alternatives to OpenBot → · How this was measured →

Other tested AI & Agents products