Lists (3)
Stars
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Scan for secrets in files you plan to share
"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.5, GPT-OSS, Llama, and more!
Lightpanda: the headless browser designed for AI and automation
Skills for AI Evals to compliment the course: AI Evals For Engineers & PMs
A list of recent papers about adversarial learning
Inference-time scaling for LLMs-as-a-judge.
Source code for the website geminibyexample.com which provides simple Python code examples for the Gemini SDK
Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.
Plug-and-play document AI with zero-shot models.
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents.
The pretty much "official" DSPy framework for Typescript
Training Sparse Autoencoders on Language Models
Code accompanying "How I learned to start worrying about prompt formatting".
An agentic retrieval augmented generated (RAG) application to help foodies in Charlotte satisfy their culinary cravings.
Build production-ready AI agents in both Python and Typescript.
Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.
A playbook for effectively prompting post-trained LLMs