toddllm/luanti-voyager

AI Summary: The task involves creating comprehensive installation instructions for running the Luanti Voyager project on Windows using the Windows Subsystem for Linux (WSL). This includes testing the setup on WSL2 with Ubuntu, documenting the process, addressing potential WSL-specific issues like file paths, network configuration, and web UI access from the Windows host, and adding performance considerations. The instructions should be added to the project's INSTALL.md file.

AI Summary: The task involves creating detailed installation instructions for the Luanti Voyager project on Ubuntu Linux systems. This includes testing the installation process on Ubuntu 22.04 and 24.04, documenting necessary package dependencies (Luanti/Minetest), verifying Python setup steps, testing Craftium mod installation paths, documenting any Linux-specific configurations, and adding a troubleshooting section. The final deliverable is an updated INSTALL.md file with clear, step-by-step instructions for Ubuntu users.

AI Summary: The task involves creating a monitoring dashboard for AI development workflows within the Luanti Voyager project. This dashboard should integrate various monitoring tools and techniques (process monitoring, resource usage, API activity, progress tracking, and log aggregation) into a single, easily accessible terminal interface. The goal is to provide real-time visibility into the AI's performance and resource consumption during development and debugging.

AI Summary: Implement a logging system for Ollama API interactions in the Luanti Voyager project. This involves creating a logger class to record prompts, responses, metadata (including timing and token counts), and integrating it into the existing batch processing, testing, and development workflows. Analysis tools and reporting features are also required to facilitate debugging, performance optimization, and cost tracking.

AI Summary: The task is to design and implement a system for creating, managing, and evaluating community challenges and competitions within the Luanti Voyager project. This involves developing features for challenge creation, submission handling, performance evaluation (including automated scoring and community voting), leaderboard maintenance, and a showcase gallery. The system should support various challenge types (building, survival, innovation, educational) and foster community engagement.

AI Summary: Develop an automated benchmarking suite for evaluating the performance of AI agents within a voxel-based game environment. The suite should track metrics such as survival time, resource gathering, distance traveled, crafting success, and task completion, across various scenarios (survival, building, exploration). The results should be saved in a structured format and visualized for easy comparison and analysis.

AI Summary: Implement a skill-sharing system for AI agents in a voxel world simulation. This involves creating a centralized repository where agents can upload and download learned strategies (skills), including defining a skill metadata format, building a local repository with search functionality, adding upload/download commands, implementing skill validation and sandboxing, and creating a simple CLI or web interface for managing skills.

AI Summary: Implement a function calling interface for the Luanti Voyager project, allowing AI agents to interact with external tools and APIs (like weather APIs, calculators, or knowledge bases) using a framework similar to OpenAI's function calling or LangChain tools. This involves creating a tool interface, a tool registry, integrating function calling into LLM prompts, ensuring safe execution, and returning results to the agent's decision loop. At least three example tools should be implemented, and the functionality should be thoroughly tested.

AI Summary: The task involves enhancing the existing Luanti Voyager web interface to include a dashboard for monitoring the health and status of multiple agents in real-time. This requires extending the WebSocket protocol to transmit agent metrics, creating a new dashboard UI with agent cards and real-time charts, and integrating this with the existing 3D viewer. The dashboard should display agent health, inventory, task progress, communication, and performance metrics.

AI Summary: Implement a system for defining agent personalities in JSON format, allowing for varied agent behaviors, goals, and communication styles within the Luanti Voyager project. This involves creating a JSON schema, loading profiles during agent initialization, modifying decision-making to incorporate personality traits, and updating the multi-agent coordinator to utilize role information. At least four distinct agent profiles should be created, and testing should verify functionality.

AI Summary: Implement a Retrieval-Augmented Generation (RAG) system for the Luanti Voyager project to improve agent skill memory and retrieval. This involves integrating a lightweight vector database (like Chroma or Qdrant), creating embeddings for skill descriptions and code, implementing semantic search, and integrating this with the existing memory system. The goal is to enable agents to find relevant past experiences, share knowledge, and build upon previous learnings more effectively.

AI Summary: Implement adaptive learning mechanisms for AI agents in a voxel-based game environment. This involves analyzing failures, optimizing successes, dynamically selecting strategies, and potentially incorporating meta-learning techniques to improve the agents' ability to learn and adapt over time. The agents should learn from their mistakes and improve their performance in various scenarios, such as survival and resource management.

AI Summary: Implement a system for multiple AI agents in a voxel world to share learned skills and collaborate on tasks. This involves creating a shared memory system for skills, mechanisms for agents to communicate and share knowledge, and strategies for conflict resolution and resource management. The implementation should allow for multiple agents to run concurrently, share skills automatically, coordinate to avoid conflicts, and be well-documented.

AI Summary: Enhance the AI agents in the Luanti Voyager project by improving their decision-making capabilities through advanced LLM integration. This involves implementing multi-step reasoning, context awareness, advanced prompting techniques, and model optimization to enable more sophisticated behaviors and error handling. The goal is to create agents capable of complex planning and adaptation within the voxel world.

AI Summary: The task requires finding or creating a Luanti world with pre-generated terrain for use in the Luanti Voyager project. This is necessary because the current methods of terrain generation within the project are failing. Solutions involve finding an existing suitable world, manually creating terrain using a Lua script, investigating alternative games, or establishing a community system for sharing compatible worlds.

AI Summary: The task requires debugging a Luanti server's terrain generation. The server, using the `devtest` game, is failing to generate terrain correctly, producing only 'ignore' blocks instead of the expected diverse terrain (stone, dirt, grass, etc.). The solution involves investigating the server configuration, game compatibility, map generation parameters, and potentially switching to a different base game. This is blocking further development of AI agent exploration and 3D visualization features.

AI Summary: The task requires fixing a Lua command in a Luanti mod to enable terrain generation for an AI agent within a voxel world. This involves debugging the command parsing and registration within the mod's Lua code, ensuring the `generate` command correctly calls the existing terrain generation function. Success would allow the AI agent to explore dynamically generated terrain in real-time.