flama
View on GitHubThe production framework for Predictive and Generative AI. Serve any model as an API in one line, with OpenAI/Anthropic/Ollama-compatible endpoints, a built-in chat UI, and native MCP.
Python framework for packaging and serving predictive models and LLMs as production APIs. Includes OpenAI-, Anthropic-, and Ollama-compatible endpoints, a built-in chat UI, and native MCP support.
Use Cases
Serve LLMs over HTTP APIsExpose model tools to AI agents over MCPPackage predictive models for portable deploymentProvide a streaming chat UI for served modelsRun inference locally or in production
Built With
- Language
- Python
- Frameworks
- vLLM · MLX · scikit-learn · TensorFlow · PyTorch
Tags
model serving · LLM inference · AI APIs · MCP · OpenAI-compatible · Anthropic-compatible · Ollama-compatible · chat UI · model packaging · predictive AI · generative AI