#2828th of 52 in Agent platforms
openbot
Self-hosted team assistant where each bot gets its own browser and audited actions
- Stars
- 9.3k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
2,423 on 22 Aug 20269,282 on 31 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
OpenBot is a clonable template for a company-run, ChatGPT-style assistant. Any AG-UI agent endpoint becomes a Bot with its own container, Chromium profile and workspace. Every browser, file, shell and MCP action passes a gateway that applies a CEL policy and writes an audit row first. Data is stored in PostgreSQL, and threads go through CopilotKit Intelligence. The README labels it alpha.
Who it is for: Teams building a governed in-house AI coworker platform
Strengths
- Per-Bot container with own browser profile and workspace volume, optional gVisor (runsc) runtime
- Single gateway applies CEL deny/allow policy and logs every action; refusals name the rule
- Works with any AG-UI endpoint: LangGraph, Mastra, CrewAI, Pydantic AI, Google ADK or custom
- SAML/OIDC, Google, Microsoft and Okta sign-in, plus admin pages for people, audit and credentials
Weaknesses
- Marked alpha; README warns of rough edges and changing behavior
- Requires a CopilotKit Intelligence project and license for threads and memory
- Template to clone and customize, not a published package or hosted product
- Local setup defaults to single-user mode with no sign-in until configured
What it needs
- no GPU
- Docker + Compose
- Needs Docker, PostgreSQL, Bun 1.3+, CopilotKit Intelligence, LLM API key
- Models: OpenAI, Anthropic, Google, any AG-UI agent endpoint
- port 3010
Quick answers
Is openbot open source?
Yes. Its code is on GitHub under the MIT license.
Can you run openbot with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does openbot need a GPU?
No, it runs without one.
Also in Agent platforms
See all 52| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 94 out of 100 |
| 2 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 93 out of 100 |
| 3 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 93 out of 100 |
| #4 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |
| #5 | open-designDesign workspace that drives your coding agent to build prototypes, decks and video | 92 out of 100 |