The Toolchain
The ultimate directory of tools, databases, orchestration layers, and infrastructure required to build modern AI applications.
Vercel AI SDK
The AI Toolkit for React, Svelte, and Vue. Build AI-powered applications with streaming text and UI.
LangChain
Building applications with LLMs through composability. Connect models to your own data sources.
Pinecone
The vector database for building AI applications. Fast, scalable, and easy to use.
Ollama
Get up and running with large language models locally. Run Llama 3, Phi 3, and more.
Supabase Vector
Postgres with pgvector. Store embeddings and perform vector similarity search.
Hugging Face Inference
Deploy models as production-ready APIs with a few clicks.
LlamaIndex
Data framework for your LLM application. Connect custom data sources to LLMs.
Replicate
Run AI models with an API. Run open-source models with one line of code.
vLLM
High-throughput and memory-efficient LLM serving engine.
Weaviate
AI-native open source vector database. Built to scale seamlessly.
Together AI
Fastest cloud platform for building and running generative AI.
Milvus
Open-source vector database built to power embedding similarity search and AI applications.
DSPy
Framework for programming—not prompting—foundation models.
Gradio
Build and share delightful machine learning apps, all in Python.
Modal
Run custom Python code and AI models in the cloud in seconds.
Qdrant
Vector similarity search engine and vector database.
Baseten
Fast, scalable, and secure infrastructure for ML models.
Chroma
The AI-native open-source embedding database.
LM Studio
Discover, download, and run local LLMs on your machine.
LiteLLM
Call all LLM APIs using the OpenAI format. Bedrock, Azure, OpenAI, Cohere, Anthropic.
Streamlit
A faster way to build and share data apps. Turn Python scripts into interactive web apps.
Weights & Biases
The developer-first MLOps platform. Build better models faster with experiment tracking.
Anyscale
The Ray-based platform to build, deploy, and manage scalable AI and Python applications.
Haystack
An open source framework for building NLP pipelines with LLMs, Transformer models, and vector databases.
Neo4j
Graph database that integrates with vector search to build advanced RAG applications.
RunPod
Rent cloud GPUs for AI workloads. Scale serverless GPU inference globally.
Semantic Kernel
Microsoft's open-source SDK for integrating LLMs into C#, Python, and Java applications.
ExLlamaV2
Fast inference library for running local LLMs on modern consumer GPUs.
OpenAI Cookbook
Example code and guides for accomplishing common tasks with the OpenAI API.
Flowise
Drag & drop UI to build your customized LLM flow using LangchainJS.