Agent runtimeWorkflow automation
atom
Self-host multi-agent workflows for conversational business automation.
- Stars
- 787
- Forks
- 81
- Updated
- Updated Jul 14, 2026
AGPL-3.0
Self-host multi-agent workflows for conversational business automation.
Atom is a self-hosted platform for running business workflows from text or voice requests. Specialized agents plan and execute work across connected services, while visual workflows, memory, and governance levels help operators control how tasks progress. Workflow data, agent state, and memory remain on infrastructure controlled by the operator. Prompts still go to a configured cloud model when bring-your-own API keys are used, unless local models such as Ollama or Llama.cpp are selected. Deployment requires operating the backend, frontend, database, and model configuration.
Resource types
Use cases
Runtime
Give each AI agent an always-on computer, memory, and chat channels.
Build, deploy, and monitor continuously running agents with visual blocks.
Protocols & integrations
Capabilities
Public GitHub facts last synced Jul 14, 2026.
Automate real browser pages for AI agents through a fast command-line interface.
Find, install, use, and manage agent skills across many coding assistants.