Web search and content extraction extension for Pi coding agent

Codebase for the LiT Benchmark from "Round-Trip Translation Reveals What Frontier Multilingual Benchmarks Miss"

Intelligent Mixture-of-Models Router for Efficient Heterogeneous LLMs Inference

OpenWiki is a CLI that writes and maintains agent documentation for your codebase.

KJob: Tool for CLI-loving ML researchers

Kubernetes-native Job Queueing

a Jax quantization library

Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at your tasks.

State-of-the-art web crawler 🔱

Get web data for AI agents and LLMs

A scalable, mature and versatile web crawler based on Apache Storm

OpenTela is a decentralized compute fabric for running machine learning applications.

Marin coding standards as an installable kit: pre-commit linter, lint-review catalog, agent guidelines, and portable skills

A tiny single-header tensor library in C

The open agent skills tool - npx skills

We release Open Meditron, a fully open, clinician-audited medical training corpus and evaluation protocol that closes the open-vs-closed gap on open-ended clinical evaluation.

JaxPP is a library for JAX that enables flexible MPMD pipeline parallelism for large-scale LLM training

An Open-source Drug Discovery Engine

Fast, streaming indexing, query, and agentic LLM applications in Rust

High-performance AI coding agent CLI written in Rust with zero unsafe code

⚙️🦀 Build modular and scalable LLM Applications in Rust

A Python port of Pi’s minimalist coding agent.

Everything I know about running LLMs locally

Issue tracking for AI coding agents

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Evaluate PithTrain, Megatron-LM, TorchTitan on agent-task efficiency.

Compact and Agent-Native MoE Training System

Official repository for MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models [NeurIPS 2024]