LangChainhttps://www.langchain.comLLM app framework + LangGraph. vLLM (lib)https://docs.vllm.aiHigh-throughput serving library. Embedchainhttps://embedchain.aiData-to-answer RAG for any source. LlamaIndexhttps://www.llamaindex.aiRAG + agent data framework. llama-cpp-pythonhttps://llama-cpp-python.readthedocs.iollama.cpp's Python bindings. anthropic-sdk-pythonhttps://github.com/anthropics/anthropic-sdk-pythonOfficial Anthropic Python SDK. Arize Phoenixhttps://phoenix.arize.comLLM tracing + eval observability. axolotlhttps://github.com/axolotl-ai-cloud/axolotlLLM fine-tuning toolkit. BERTopichttps://maartengr.github.io/BERTopicNeural topic modeling. Candlehttps://github.com/huggingface/candleHF's Rust ML framework. Chromahttps://www.trychroma.comEmbedded vector database. Cognitahttps://github.com/truefoundry/cognitaTrueFoundry's RAG framework + UI. DeepEvalhttps://deepeval.comLLM evaluation framework. Doclinghttps://docling-project.github.io/doclingIBM's document-to-AI parser. DSPyhttps://dspy.aiProgrammatic LM pipelines + optimizers. Einohttps://github.com/cloudwego/einoCloudWeGo's LLM app framework. ExLlamaV2https://github.com/turboderp-org/exllamav2Fast local inference kernels. FAISShttps://github.com/facebookresearch/faissMeta's similarity-search library. FastEmbedhttps://qdrant.github.io/fastembedFast quantized embeddings (Qdrant). Genkithttps://genkit.devGoogle's AI app framework. GraphRAGhttps://microsoft.github.io/graphragMicrosoft's graph-based RAG. Guardrails AIhttps://www.guardrailsai.comLLM output validation + rails. guidancehttps://github.com/guidance-ai/guidanceMicrosoft's structured generation. Haystackhttps://haystack.deepset.aideepset's RAG pipeline framework. Heliconehttps://helicone.aiLLM observability proxy. Instructorhttps://jxnl.github.io/instructorStructured LLM outputs (Pydantic). Jina Embeddingshttps://jina.ai/embeddingsLong-context embedding models. Kalosmhttps://github.com/floneum/kalosmRust local AI (embed, transcribe, generate). kotaemonhttps://github.com/Cinnamon/kotaemonClean RAG UI + framework. LanceDBhttps://lancedb.comServerless embedded vector DB. LangChain.jshttps://js.langchain.comLangChain for TypeScript. LangChain.rbhttps://github.com/patterns-ai-core/langchainrbLangChain for Ruby. LangChain4jhttps://github.com/langchain4j/langchain4jLangChain for Java. langchaingohttps://github.com/tmc/langchaingoLangChain for Go. Langfusehttps://langfuse.comLLM observability + tracing. LangSmithhttps://smith.langchain.comLangChain's observability platform. LightRAGhttps://github.com/HKUDS/LightRAGGraph-augmented RAG. LiteLLMhttps://litellm.aiOne SDK for 100+ providers. llm-chainhttps://github.com/sobelio/llm-chainRust LLM chains. Marqohttps://marqo.aiTensor search engine. Mastrahttps://mastra.aiTS agent framework. Meilisearchhttps://meilisearch.comInstant search engine + vector store. Milvushttps://milvus.ioDistributed vector DB. mistral.rshttps://github.com/EricLBuehler/mistral.rsRust local LLM inference. MLXhttps://ml-explore.github.io/mlxApple-silicon ML array framework. openai-nodehttps://github.com/openai/openai-nodeOfficial OpenAI TS SDK. openai-phphttps://github.com/openai-php/clientOpenAI PHP client. openai-pythonhttps://github.com/openai/openai-pythonOfficial OpenAI Python SDK. Outlineshttps://outlines-dev.github.io/outlinesStructured generation control. pgvectorhttps://github.com/pgvector/pgvectorVector search inside Postgres. Pineconehttps://pinecone.ioManaged vector database. PostgresMLhttps://postgresml.orgML inside Postgres (embed + infer). promptfoohttps://promptfoo.devLLM eval + red-team toolkit. Pydantic AIhttps://ai.pydantic.devType-safe agent framework. Qdranthttps://qdrant.techVector database (Rust). qdrant-clienthttps://github.com/qdrant/qdrant-clientQdrant's Python client. Ragashttps://docs.ragas.ioRAG evaluation metrics. RAGFlowhttps://ragflow.ioOpen RAG engine with deep document understanding. Redis vector setshttps://redis.ioVector search inside Redis. rigginghttps://github.com/0xPlaygrounds/rigRust LLM app framework. Semantic Kernelhttps://github.com/microsoft/semantic-kernelMicrosoft's AI orchestration SDK. Semantic Kernel Javahttps://github.com/microsoft/semantic-kernel-javaSK for Java. Semantic Kernel Pythonhttps://github.com/microsoft/semantic-kernelSK for Python. Sentence Transformershttps://sbert.netSentence/paragraph embeddings. Spring AIhttps://spring.io/projects/spring-aiAI applications on Spring. sqlite-vechttps://github.com/asg017/sqlite-vecVector search inside SQLite. TensorRT-LLMhttps://github.com/NVIDIA/TensorRT-LLMNVIDIA's optimized LLM inference. Transformershttps://huggingface.co/transformersHF's model library. TRLhttps://github.com/huggingface/trlHF RL fine-tuning (SFT, DPO, PPO). turbopufferhttps://turbopuffer.comServerless vector search. txtaihttps://neuml.github.io/txtaiEmbeddings + RAG workflows. Typesensehttps://typesense.orgFast typo-tolerant + vector search. unslothhttps://unsloth.ai2× faster fine-tuning. Unstructuredhttps://unstructured.ioDocument ETL for RAG. Valkeyhttps://valkey.ioRedis-forked cache + vector sets. Vercel AI SDKhttps://sdk.vercel.aiThe AI app SDK for TS. Vespahttps://vespa.aiBig-data serving + vector search. VoltAgenthttps://voltagent.devTS multi-agent framework. Weaviatehttps://weaviate.ioOpen-source vector DB. zvechttps://github.com/zvec-ai/zvecEmbedded vector DB (Zilliz).