Enables AI agents to offload mechanical, high-token work to local Ollama models through MCP, with role-based model discovery, batch processing, and file-aware inputs.
Enables natural language filesystem operations (create, list, delete directories/files) via Ollama local LLM and MCP protocol within allowed directories.
Enables delegating complete coding tasks to a local OpenAI-compatible model through MCP, using bounded Git worktrees and compact receipts so conversation history is not carried.
Enables local interaction with Ollama models through a ChatGPT-style web interface and MCP tools, including chat, generation, embedding, web search, webpage extraction, and safe utility functions.