“Turns unreliable LLM text output into validated Pydantic objects with a few lines of code, removing an entire category of prompt-parsing bugs.”
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.
23 repositories • Page 2 of 2
“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.”
“Purpose-built web crawler for feeding LLMs - it strips a page down to clean markdown instead of leaving you to parse raw HTML yourself.”
“An open-source Copilot alternative that lets you plug in any model - genuinely useful if you want AI-assisted coding without being locked into a single provider.”
“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.”
“A lighter-weight take on multi-agent orchestration - agents get explicit roles and goals, which reads more naturally than raw chain composition.”
“A drag-and-drop builder for LLM workflows - genuinely useful for prototyping an idea in minutes before committing to a hand-written implementation.”
“One of the earliest serious multi-agent orchestration frameworks - useful once a single agent/chain isn't enough for the problem.”
“Handles the messy part of RAG most tutorials skip - deep document understanding for PDFs, tables, and scanned files - not just chunking clean text.”
“Gives Claude the ability to actually watch a video - extracting frames and transcript together - instead of guessing from a title or an incomplete transcript.”
“A TypeScript-first agent framework with built-in observability - genuinely useful for teams who need to see exactly why an agent made a decision, not just that it did.”
Jump straight to the category you care about
123
Curated Repositories
64
Hidden Gems