$ loading_
Delegate low-risk tasks to a cheaper model with main-agent review.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "cn-llm-mcp" yet — see the docs or source repo.
Use cn-llm-mcp to send this long document to a low-cost model for summarization. Return five key points and one risk note, then review and correct any obvious mistakes yourself.
A concise summary reviewed by the main agent, including key points and a confidence or risk note.
Through cn-llm-mcp, have a low-cost model generate a minimal patch based on this error and code. Then review it for side effects and provide the final recommendation.
A reviewable patch draft plus the main agent’s assessment of risks and suitability.
Use cn-llm-mcp to batch-process these low-risk tasks: clean up meeting notes, extract action items, and format the output consistently. Then consolidate the results and flag anything needing human confirmation.
A consolidated structured result with action items and flags for items needing further confirmation.
Delegate summarization, classification, extraction, and drafting tasks to a local LLM.
Route LLM requests across providers and orchestrate MCP tools with local privacy.
Offload non-critical LLM tasks to your own model and save premium quota.
Offload non-critical LLM tasks to your own model to save premium quota.
Build, debug, and manage software tasks with natural language across LLMs.
Run local multi-model deliberation and synthesis on Mac for AI coding workflows.