Yuga Planner acts as an intelligent project assistant that takes the guesswork out of scheduling. By simply describing a project—such as "building a new website"—this tool automatically breaks the big goal down into smaller, manageable tasks and finds the perfect spots for them on a calendar. It can even read existing appointments from a calendar file to ensure there are no overlaps, making sure new work fits seamlessly into a busy day without manual planning. Under the hood, this system uses a neuro-symbolic approach to solve complex organizational problems. It leverages LLamaIndex and Nebius AI to perform task decomposition and estimation, transforming natural language descriptions into actionable structured data. Once tasks are identified, the Timefold optimization engine takes over, applying advanced constraints such as business hours, weekend prevention, and skill matching. This ensures that every task is not just scheduled, but assigned to the right resources at the most efficient time while respecting sequential dependencies. For developers building AI agents, Yuga Planner provides a robust Model Context Protocol (MCP) interface that simplifies the integration of sophisticated scheduling logic into larger AI workflows. The architecture includes a specialized tool-call assembler to handle streaming data from LLMs and built-in JSON repair to maintain reliability during real-time interactions. By exposing these capabilities as a standardized MCP tool, it allows agents to handle complex project management and personal productivity tasks with professional-grade constraint satisfaction and reasoning.
Category: Communication & Messaging
Tags: calendar, optimization, productivity, scheduling, task-management
bash git clone https://github.com/blackopsrepl/yuga-planner.git cd yuga-planner 2. Create a virtual environment: bash make venv 3. Install dependencies: bash make install 4. Run the application: bash make run Docker Setup: 1. Build the image: bash docker build -t yuga-planner . 2. Run the container: bash docker run -p 7860:7860 yuga-plannerbash make setup-secrets 2. Edit the generated file tests/secrets/cred.py to add your actual API credentials. MCP Settings: The provided content does not include a specific mcpServers JSON configuration block for standard MCP clients (like Claude Desktop or Cursor). However, it notes that the application provides an MCP endpoint for agent workflow integration and a Chat Interface with MCP via its Gradio UI..ics file attachments to parse existing commitments. * Capabilities: Performs task decomposition, estimation, and constraint-based scheduling (respecting business hours 09:00-18:00 and preventing weekend assignments).text use yuga-planner mcp tool Task Description: [Your task description] [Attach calendar.ics file].ics calendar file. It identifies the gaps in the user’s existing schedule, enforces business hours (9:00–18:00) and lunch breaks, and automatically pins the project tasks into the available free time. Example: A developer uploads their work calendar and asks, "Schedule the implementation of a new payment gateway." Yuga Planner breaks the project into sub-tasks like "API research," "Stripe integration," and "Unit testing," then slots them into the 2-hour windows between their existing Zoom meetings.Part of MCP Servers
Yuga Planner is a neuro-symbolic scheduling tool that combines LlamaIndex task decomposition with the Timefold constraint optimization solver. It accepts natural language project descriptions, breaks them down into sub-tasks with dependencies, and schedules them against calendar commitments provided in iCalendar format while respecting predefined constraints like working hours and employee skills.
To install Yuga Planner locally, clone the GitHub repository and run make venv followed by make install using Python 3.10 and Java 17. Configure your Nebius credentials using make setup-secrets, then launch the service with make run. Alternatively, you can build and run the Docker container on port 7860.
Yuga Planner enforces multiple operational constraints during schedule optimization. It pins existing events from uploaded calendar files, limits work strictly to standard business hours from 09:00 to 18:00, excludes designated lunch hours, and blocks weekend scheduling. It also validates task dependencies to ensure prerequisite steps finish before dependent work begins.
Yes, Yuga Planner is open source software. The project is distributed under the Apache 2.0 license, and the complete source code, Docker build configurations, and test suites are publicly accessible on GitHub. Users are permitted to inspect, modify, and deploy the application for personal use or integrate it into agent workflows.
Yuga Planner works with any MCP-compatible platform, chatbot, or agent environment capable of consuming Model Context Protocol tools. It also features a built-in Gradio chat interface that includes streaming tool-call assembly and JSON repair to process natural language scheduling requests alongside attached calendar files directly.