LiteLLM
LiteLLM is an open-source AI gateway that allows to call over 100 large language models in OpenAI format over a single standard interface. Both can be directly integrated as Python SDK and can be hosted as a central proxy server for teams. Virtual keys have features for the production environment, such as spending tracking, security limits, and load balancing.
LiteLLM
60BerriAI · MLOps & AI Infrastructure
Common commercial products in this category: Weights & Biases, Amazon SageMaker, Databricks
- You call the large language model over the face of different providers through a single unified interface.
- Using Python SDK you provide direct library integration or distribute the proxy server as a central service.
- By creating virtual keys, you perform an audit through the spending tracking and management panel.
- • High number of open issues (5,582)
- • No published release
- • NeutralHacker News
Compromised LiteLLM 1.107.0 on PyPI Installs a Credential Stealer and Backdoor
“> Was `cook.pth` a dependency that got automatically downloaded from PyPI on install and then the build system put it into dependencies? This isn't the name of an entire package, but just a single file included in the package. .pth files are part of Python's import system. At…”
- • NeutralHacker News
Compromised LiteLLM 1.107.0 on PyPI Installs a Credential Stealer and Backdoor
“If Claude's custom solution is less secure than LiteLLM there will be no news report informing you of a vulnerability.”
Verified against README · Oct 26, 2026 · source
My note
Alternative pages
More in: MLOps & AI Infrastructure
- keras★ 64,400 · today
- Ray★ 44,168 · today
- Langfuse★ 36,776 · today
- MLflow★ 28,602 · today
- Label Studio★ 28,595 · today
- pytorch_geometric★ 24,130 · 9 days ago