#107 trending · +2319 stars today
NVIDIA-NeMo/Switchyard
Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.
12-month star history
NVIDIA-NeMo/Switchyard gained 2319 stars since today's 00:00 UTC snapshot and currently sits at #107 in the trending feed. An engagement is the star gain since a snapshot; on this page that history spans the last 12 months. More Python repos →
Similar projects
Open-source framework for the research and development of foundation models.
OpenRouter for agent tools. Join community here: https://discord.gg/6mQYYfFMAn
Long-horizon agent control plane for durable, governed work across Codex, Claude Code, and other harnesses.
Community plugin marketplace for Claude Cowork and Claude Code. Read-only mirror — submit plugins at clau.de/plugin-directory-submission.
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.