METR Time Horizons metr.org ↗

A personal AI agent framework that can run locally with local or cloud models.

A framework for running agent evaluation task suites.

A site benchmarking and comparing AI models on quality, price and speed.

An open-source tool for automatically removing refusal behavior from language models.

Models from Liquid AI trained specifically to produce decisions with calibrated confidence.

A line of research where one neural network generates the weights of another, popularized by Google Brain in 2016.

An open-source, self-hostable context and memory system for AI agents made by ByteDance.

Vercel's gateway service for calling multiple AI model providers through one API.

A marketplace that routes API requests to many LLM inference providers.

A family of large language models offered via a low-cost API.

A C/C++ engine for running LLMs locally.

An open-weights large language model family from Zhipu AI.

Alibaba's family of open-weight large language models.

A low-cost DeepSeek language model available via API.

A site benchmarking and comparing AI models on quality, price and speed.

Anthropic's AI model and command-line assistant.

A Qwen open-weight model that can be run locally.

An open-source project for running large MoE models on small-VRAM GPUs with system RAM.

A subscription plan for accessing models through the OpenCode coding tool.

A service that uses a trained model to detect AI-generated text.