Directory
The AI builder's toolkit
Frameworks, models, platforms, and tools we use and recommend for building production AI agents and LLM applications.
20 resources
Framework for building LLM-powered applications with chains, agents, and memory.
Build stateful, multi-actor agentic applications with graph-based orchestration.
Data framework for LLM applications, specializing in ingestion, indexing, and retrieval.
Framework for orchestrating multi-agent AI systems with role-playing agents.
Microsoft's framework for multi-agent conversation and task completion.
Anthropic's family of AI models — Claude 3.5 Sonnet and Opus offer state-of-the-art reasoning and instruction following.
OpenAI's multimodal flagship model with vision, audio, and text capabilities.
Meta's open-weight large language models, suitable for fine-tuning and local deployment.
Google's multimodal AI model family with strong coding and reasoning capabilities.
Managed vector database for production-grade semantic search and RAG applications.
Open-source vector database with hybrid search, multi-tenancy, and built-in ML modules.
High-performance vector similarity search engine written in Rust, with filtering support.
TypeScript SDK for building AI-powered applications with streaming, tool calling, and multi-provider support.
Observability and evaluation platform for LLM applications. Trace, debug, and test agents.
Run LLMs locally on your machine. Supports Llama, Mistral, Gemma, and more.
Open-source LLM testing and red-teaming tool. Evaluate prompts, compare models, catch regressions.
LLM observability platform with one-line integration — logging, monitoring, and caching.
Structured outputs from LLMs using Pydantic. Makes LLMs return validated, typed Python objects.
Microsoft's SDK for integrating LLMs into .NET, Python, and Java applications.