Launch HN: LlamaFarm (YC W22) – Open-source framework for distributed AI
6 hours ago
- #open-source
- #RAG
- #AI-framework
- LlamaFarm is an open-source framework for building retrieval-augmented and agentic AI applications.
- It offers a local-first developer experience with a single CLI (`lf`) for managing projects, datasets, and chat sessions.
- Features include composable RAG pipelines configurable via YAML, extendable components (runtimes, embedders, databases, etc.), and a production-ready architecture.
- Prerequisites include installing the CLI, adjusting Ollama's context window, and initializing/running a project.
- Commands are provided for interactive chats, one-off messages, dataset creation/upload/processing, and semantic queries.
- LlamaFarm provides a comprehensive REST API compatible with OpenAI's format for integration.
- Configuration is managed via `llamafarm.yaml`, which enforces schema-based settings for projects.
- Extensibility is a key feature, allowing users to swap runtimes, add vector stores, parsers, or extend the CLI.
- Examples and testing instructions are included for practical application and development.
- Community engagement is encouraged through Discord, GitHub Issues, and Discussions, with contributions welcome under the Apache 2.0 License.