# bytebot-ai/bytebot

Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerized Linux desktop environment.

Repository: https://github.com/bytebot-ai/bytebot
Canonical: https://ross.abutalabs.com/products/bytebot
Homepage: https://www.bytebot.ai/
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: ai-agents, anthropic, computer-use, docker, llm, agentic-ai, agents, ai-tools, cua, gemini, openai, bytebot, automation, desktop-automation, agent, ai, desktop, mcp, computer-use-agent
Archived: true
Last push: 2025-09-12T19:35:46+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 41, release rhythm 35, longevity 41
- inputs: {"age_days": 576, "days_push": 355, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 11089, forks 1504 (observed 2026-08-28T04:10:46.085030+00:00)

## What it is
Bytebot is a self-hosted, open-source AI desktop agent that operates a full containerized Linux desktop, using screen vision, mouse, and keyboard to complete tasks described in natural language. It supports multiple LLM providers (OpenAI, Anthropic, Gemini) and exposes an MCP interface, running entirely on your own infrastructure via Docker.

## Use cases
- automate downloading invoices from vendor portals
- fill out web forms and data entry automatically
- process PDFs and spreadsheets with AI
- run multi-app workflows without scripting
- self-hosted alternative to RPA tools like UiPath
- give an AI agent its own computer to complete tasks

## When to choose
- you need task automation across arbitrary desktop apps and websites without writing scripts
- privacy matters and tasks must stay on your own infrastructure
- UI changes frequently and brittle RPA scripts break
- you want to use your own LLM API keys with no usage limits

## When to avoid
- you need simple API-to-API integration where a script is cheaper and faster
- you cannot run Docker or spare container resources
- tasks require guaranteed deterministic outcomes that LLM-driven agents can't assure
- you need a fully managed cloud service rather than self-hosting

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, computer-vision, workflow-automation, mcp, llm-inference, self-hosted
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: self-hosted
- tags: computer-use, desktop-automation, agentic-ai, rpa, containerized-desktop, natural-language-automation, ai-agents, automation, docker, linux, web-server, typescript

## Member repositories
- bytebot-ai/bytebot (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:46.085030+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:16:48.480941+00:00, confidence not recorded.
  - readme: https://github.com/bytebot-ai/bytebot (fetched 2026-08-28T04:10:46.085030+00:00, sha 6b70308e9938)
  - homepage: https://www.bytebot.ai/ (fetched 2026-08-29T08:15:50.509258+00:00, sha bf7b6b1aabcd)
  - site_page: https://docs.bytebot.ai (fetched 2026-08-29T08:15:50.513136+00:00, sha 40545375b0b6)
- Data as of 2026-08-30T08:39:29.467469+00:00.