FellouAI/eko
Eko
Eko is a framework for designing and deploying agentic workflows, featuring an LLM agent workflow orchestrator and a browser automation engine. It provides a server-side process manager for executing system-level operations and managing local files, alongside a human-in-the-loop agent controller for manual oversight and direction during automated decision processes.
The system coordinates multi-agent collaboration through role-based partitioning and workflow orchestration, dividing complex tasks into distinct roles and managing execution handoffs. It integrates the Model Context Protocol to standardize connections between agents and external tools or data sources.
The platform includes capabilities for headless browser automation, web scraping, and repetitive task automation using loop-based event listening. It also features execution plan streaming to visualize an agent's internal planning process in real-time.
Features
- Agentic Workflow Orchestration - Provides a core orchestrator for executing complex processes by delegating and coordinating multi-step tasks across autonomous AI agents.
- Role-Based Agent Orchestration - Coordinates multi-agent collaboration by partitioning complex tasks into distinct roles and managing execution handoffs.
- Human-in-the-Loop Oversight - Includes a human-in-the-loop agent controller for manual oversight and directional overrides during automated decision processes.
- Headless Browser Automation - Provides a headless browser automation engine for web scraping and automated interactions with web applications.
- Browser Automation - Provides capabilities for controlling web browsers to perform scraping, handle login flows, and manage UI actions.
- Browser Automation Engines - Ships an engine for performing web scraping and GUI interactions to automate complex tasks across web applications.
- Server-Side Process Management - Enables agents to control local files and execute system-level processes within a server-side environment.
- AI Agent Process Runtimes - Provides a server-side process manager that allows AI agents to execute operating system processes and manage local files.
- Web Scraping and Automation - Uses AI to control web browsers and graphical interfaces for web scraping and application interaction.
- Model Context Protocol - Integrates the Model Context Protocol to standardize connections between agents and external tools or data sources.
- MCP Protocol Integrations - Standardizes external tool and data connections using the Model Context Protocol to extend agent capabilities.
- Model Context Protocol Integrations - Implements standardized interfaces for linking AI models to external data sources via the Model Context Protocol.
- Agent Planning Visualizations - Features execution plan streaming to visualize an agent's internal planning process in real-time.
- Agent-Driven Task Automation - Uses AI agents and event-driven triggers to automate repetitive digital workflows and recurring actions.
- Event-Driven Agent Loops - Implements loop-based event listening to execute recurring tasks and trigger automated agent responses.
Star history
How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
