AI-powered resume evaluator that scores candidates with GitHub signals.
The open-source LLM evaluation framework for unit testing AI applications
Reusable computer vision toolkit for building AI vision applications with any model
Official Python SDK for building AI agents with Claude Code
Open-source AgentOS for building and orchestrating multi-agent AI systems
Generate full-length novels with AI — auto-coherent chapters, foreshadowing, and world-building.
Extract structured data from unstructured text using LLMs with precise source grounding
Production-grade AI agent framework built the Pydantic way — type-safe, model-agnostic, FastAPI-inspired.
AI-powered adaptive web scraping framework for modern crawling
Make websites accessible for AI agents - automate browser tasks with LLMs
Unofficial Python API & Agentic Skill for Google NotebookLM
Build your own Claude Code-like AI agent harness from scratch
Open-source Python framework for building, evaluating, and deploying sophisticated AI agents
