Snowflake ArcticSnowflake Arctic is a truly open-source LLM built for enterprise AI. Discover breakthrough efficiency, top-tier performance, and seamless Snowflake Data Cloud integration.(0)0
AnythingLLMAnythingLLM lets you chat with any document using any LLM, fully locally and privately. Open source, no technical setup required. Supports PDFs, Word, CSV, codebases, and more.(0)0
Arize Phoenix AIArize Phoenix is an open-source LLM observability platform built on OpenTelemetry. Instrument, trace, evaluate, and optimize AI applications in real time—framework-agnostic and vendor-lock-in free.(0)0
FeatureformFeatureform turns your existing infrastructure into a feature store. Define, manage, version, and serve ML features, labels, and training sets with built-in lineage, monitoring, and governance.(0)0
Flowise AI BuilderFlowise is an open-source platform for building AI agents, multi-agent workflows, and LLM-powered chatbots with a visual drag-and-drop interface. Supports RAG, HITL, and enterprise deployment.(0)0
Gorilla LLMGorilla is an open-source LLM from UC Berkeley that connects with massive APIs, enabling state-of-the-art function calling across Python, Java, JavaScript, and REST APIs. Includes BFCL benchmarking, RAFT fine-tuning, and the GoEX execution engine.(0)0
Open WebUI AI ChatRun AI on your own terms with Open WebUI. Connect to Ollama, OpenAI, Anthropic, or any model. Self-host locally or in the cloud with full data privacy, Python extensibility, and enterprise-grade controls.(0)0
LiteLLM ProxyLiteLLM Proxy is an open-source LLM gateway that provides a single OpenAI-compatible API to manage authentication, load balancing, and spend tracking across 100+ LLM providers.(0)0
PrivateGPTPrivateGPT is a free, open-source AI framework for querying your documents with local LLMs. 100% private, works offline, no data leaves your environment.(0)0
Milvus AI Vector DBMilvus is an open-source vector database built for GenAI applications. Perform high-speed similarity searches and scale to tens of billions of vectors with minimal performance loss.(0)0