$ loading_
Route LLM tasks locally first to keep sensitive data private and controlled.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "llm-localfirst" yet — see the docs or source repo.
Design a routing policy for llm-localfirst: prompts containing internal code or customer data must go to local models first, while only low-sensitivity general Q&A may be sent to cloud models. Provide example rules and calling recommendations.
A clear routing policy showing which requests stay local, which may go to cloud models, and how to call them.
Use llm-localfirst to handle a summarization task containing confidential business terms, and ensure the content is processed only by local models with no automatic fallback to external services. Output a secure calling plan.
A secure local-only completion plan with fail-closed behavior and no external data leakage.
Explain how to implement a manager-worker pattern with llm-localfirst: one model decomposes tasks and selects routes, while another local model performs the actual generation. Provide a workflow suitable for MCP client integration.
An MCP-friendly delegation workflow covering task breakdown, routing decisions, local execution, and result return.
Route LLM requests across providers and orchestrate MCP tools with local privacy.
Route prompts across LLM providers with policy-based orchestration and verification.
Delegate summarization, classification, extraction, and drafting tasks to a local LLM.
Manage local model runtimes with unified discovery, checks, lifecycle control, and inference.
Route coding tasks across local and remote LLMs with benchmarking and code search.
Unify multiple LLM providers, routing, and model collaboration in one local gateway.