Shell tools for building AIs, including a recursive LLM CLI. Of bash, by bash, for bash; it's shells all the way down.

Harbor is a framework for running agent evaluations and creating and using RL environments.

A benchmark for LLMs on complicated tasks in the terminal

Code behind Arxiv Papers

Arcade AI NodeJS Client

Official Arcade Python Client

MCP Server Framework and Tool Development library for building custom capabilities into agents.

headless terminal - wrap any binary with a terminal interface for easy programmatic access.

The pretty much "official" DSPy framework for Typescript

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

A fast inference library for running LLMs locally on modern consumer-class GPUs

The official API server for Exllama. OAI compatible, lightweight, and fast.

Structured Outputs

A lightweight coding agent for open models like Deepseek, Kimi, and Qwen

Immutable persistent data collections for Javascript which increase efficiency and simplicity.

a Hassle-Free Python Experience

The agent engineering platform.

This AutoHotKey script gets you all the MacOS keyboard shortcuts you love, in Windows!

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).

The Python Component System (PCS) is an API and CLI for building, running, and sharing Python code. AgentOS is a set of libraries built on top of PCS that make it easy to build, run, and share agen…

Making large AI models cheaper, faster and more accessible

A compiler and scenario generator for the Scenic scenario description language.

Training and serving large-scale neural networks with auto parallelization.

Move fast from data science prototype to pipeline. Capture, analyze, and transform messy notebooks into data pipelines with just two lines of code.

Intuitive concurrent programming in any language

An offline deep reinforcement learning library