3,431 of the 290,197 public repositories in the corpus declare a dependency on LiteLLM. That is 86.7% of the Model Routers and Gateways category, where it ranks 1 of 4.
Repos are counted by creation quarter, so recent quarters keep growing as the corpus is re-observed. This is adoption among repos we have scanned, not the whole of GitHub.
| LiteLLM | 3,431 |
| OpenRouter | 480 |
| Azure AI Foundry (also shown on the Model Providers page) | 172 |
| Portkey | 44 |
| Helicone | 1 |
| infiniflow/ragflow | 90,719 | agent |
| headroomlabs-ai/headroom | 72,224 | mcp_server |
| mem0ai/mem0 | 65,312 | framework |
| ZhuLinsen/daily_stock_analysis | 65,077 | ai_enabled |
| usestrix/strix | 62,545 | framework |
| pathwaycom/pathway | 62,283 | framework |
| sansan0/TrendRadar | 62,268 | template |
| Aider-AI/aider | 48,476 | agent_adjacent |
| bojieli/ai-agent-book | 47,312 | ai_enabled |
| stanfordnlp/dspy | 38,033 | framework |
Detected from declared dependencies in package.json, pyproject.toml and requirements.txt. A project using LiteLLM without declaring it is not counted, so this is a floor. How this is measured ยท Browse all repos