Give Claude Code eyes 👁️ — a camera skill so it can SEE real hardware, displays and wiring: verify a rendered panel, check wiring before power-on, and catch bugs that live on the glass, not the logs.

Language model tokenization at GB/s

The self-improving SRE agent

The HTML5 Creation Engine: Create beautiful digital content with the fastest, most flexible 2D WebGL renderer.

Qwen-AgentWorld: Language World Models for General Agents

YC Bench: a Live Benchmark for Forecasting Startup Outperformance in Y Combinator Batches arXiv:2604.02378

Open-source benchmark for evaluating LLMs on 220 real professional tasks across 9 sectors and 44 occupations. Reproducible experiments, artifact validation, grading, and a live evidence dashboard.

Frontier Models playing the board game Diplomacy.

DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference

Official repository for "Craw4LLM: Efficient Web Crawling for LLM Pretraining"

Preferred Generation Benchmark

An agent benchmark with tasks in a simulated software company.

Official repository for "DynaSaur: Large Language Agents Beyond Predefined Actions"

👩‍⚖️ Agent-as-a-Judge: The Magic for Open-Endedness

SWE-bench: Can Language Models Resolve Real-world Github Issues?

An SRE agent benchmark inspired by SWE-bench, focused on real-world Site Reliability Engineering tasks: incident response, infra changes, observability triage, and reliability improvements across K…

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation

SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

[NeurIPS 2025 Spotlight] Scaling Computer-Use Grounding via UI Decomposition and Synthesis

[ACL'26] Official Code for "ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning"

Cargo subcommand `release`: everything about releasing a rust crate.

📦 shippable application packaging

A batteries-included framework for building web apps

The elegant bundler for libraries powered by Rolldown

Easily export your Rust types to other languages

Completely typesafe Tauri commands

A fully-featured team and group chat application that you can easily selfhost.