$ loading_
Routes coding tasks to local GPU models and tracks token cost savings.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "local-forge" yet — see the docs or source repo.
Use local-forge to route coding tasks suitable for local inference to a local GPU model, and explain the routing result.
A routing result showing which tasks go to the local model and why.
Use local-forge to track how much token-dollar cost is saved by sending these requests to a local GPU model.
Real-time or near real-time cost savings data.
Use local-forge's dynamic heuristic classifier to decide which AI tasks should go to local GPU models and which should stay elsewhere.
Task classification and routing recommendations.
Developers handling many code-related requests can route suitable tasks to local GPU models. This keeps the workflow automated while reducing token costs.
Teams that want to see which requests save the most after switching to local models can use it to track real-time savings. It fits cost visibility and routing decisions.
When an AI workflow includes both simple and complex tasks, a dynamic heuristic classifier can split them. It is useful when you need automatic selection between local GPU models and other models.
It is an MCP tool that helps AI coding agents route tasks to local GPU models and track real-time token-dollar savings.
It mainly automates routing of tasks suitable for local inference to reduce model usage costs. It also tracks the savings.
The provided material only says it routes to local GPU models; installation, configuration, and dependencies are not specified. See the source repository.
Offload bounded text tasks from coding agents to local or cheaper LLMs.
Provides local code intelligence and shared language services for AI coding agents.
Give AI coding agents persistent local memory across sessions.
Orchestrate multi-AI workflows with file locking, knowledge capture, and drift detection.
Give coding agents local structural memory for leaner, refactor-safe development.
Analyze local-first AI agent CLI usage patterns and invocation data.