A AI2 (Allen Institute for AI)Ai2 is a nonprofit AI research institute offering fully open LLMs, multimodal models, and AI platforms for science, environment, and robotics. Explore OLMo, Molmo, Semantic Scholar, and more.(0)0
K KaskadaKaskada is an open-source streaming engine that connects AI models to real-time and historical data. Build real-time AI features with Python, no infrastructure required.(0)0
M MemGPT AgentLetta (MemGPT) is an open-source platform for building stateful AI agents with advanced memory that learns and self-improves over time.(0)0
R Ray ServeRay Serve is an open-source, scalable model serving framework built on Ray for deploying ML models, LLMs, and multi-model pipelines in production.(0)0
P Petals AIPetals is an open-source framework for distributed LLM inference. Run Llama 3.1 (405B), Mixtral, Falcon, and BLOOM collaboratively across a peer-to-peer GPU network using a consumer GPU or Google Colab.(0)0
v vLLMvLLM is an open-source high-throughput LLM inference library supporting GPU, CPU, and TPU backends with an OpenAI-compatible API, PagedAttention, and production deployment tools.(0)0
T TrulensTruLens is an open-source framework for evaluating and tracing AI agents and LLM apps. Measure groundedness, context relevance, and more to ship production-ready AI faster.(0)0
G 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
Q Qwen AIQwen is Alibaba's open-source family of foundation models covering LLMs, image generation, translation, and AI safety. Available on Hugging Face, GitHub, ModelScope, and via API.(0)0
O OmniParserOmniParser by Microsoft is an open-source tool that parses UI screenshots into structured elements, enabling accurate vision-based GUI automation agents powered by GPT-4V and other VLMs.(0)0