A hand-curated library of 123+ repositories — AI agents, developer productivity, system design, security, mobile, and more — picked by editors for lasting value, not a 24-hour trending snapshot.
14 repositories • Page 1 of 2
“Unifies dozens of LLM providers behind a single API, making model switching almost effortless in production.”
“The standard library for working with open-weight models - thousands of pretrained models are one line of code away.”
“The most widely adopted framework for chaining LLM calls, tools, and retrieval into real applications - a near-default starting point for RAG and agent projects.”
“The reference collection of Model Context Protocol servers - worth knowing now, since MCP is quickly becoming the standard way agents connect to real tools and data.”
“Brings the Pydantic team's own type-safety philosophy to agent development - if you already trust Pydantic for data validation, this is the natural way to build agents.”
“Gives an LLM agent real control of a browser instead of just reading its HTML, which is the difference between an agent that can describe a task and one that can finish it.”
“The interface that makes self-hosted LLMs actually pleasant to use day to day - it's what turns a local Ollama install into something that feels like a real product.”
“One of the most capable open autonomous coding agents available - it can plan, write, and actually execute code to verify its own work, not just suggest snippets.”
“The official, minimal-overhead client for OpenAI's API - the right starting point before reaching for a bigger framework.”
“Turns unreliable LLM text output into validated Pydantic objects with a few lines of code, removing an entire category of prompt-parsing bugs.”
The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents
“The cleanest way to wire streaming LLM responses into a React/Next.js UI - handles the hard parts (streaming, tool calls, edge runtimes) so you don't have to.”
“Adds a proper long-term memory layer to LLM apps, so an assistant can recall what it learned about a user last week instead of starting from zero every session.”
Jump straight to the category you care about
123
Curated Repositories
64
Hidden Gems
