This repository allows reproduction of Poetiq's record-breaking submission to the ARC-AGI-1 and ARC-AGI-2 benchmarks.

LLM Council works together to answer your hardest questions

A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.

Streaming replication for SQLite.

Renderer for the harmony response format to be used with gpt-oss

Genome modeling and design across all domains of life

The leading data integration platform for ETL / ELT data pipelines from APIs, databases & files to data warehouses, data lakes & data lakehouses. Both self-hosted and Cloud-hosted.

Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message…

A lightweight, powerful framework for multi-agent workflows and voice agents

The most comprehensive authentication framework for TypeScript

World's smallest storage controller

Cloud-Native distributed storage built on and for Kubernetes

Barman - Backup and Recovery Manager for PostgreSQL

CloudNativePG is a comprehensive platform designed to seamlessly manage PostgreSQL databases within Kubernetes environments, covering the entire operational lifecycle from initial deployment to ong…

🌈 React for interactive command-line apps

An extremely fast Python package and project manager, written in Rust.

This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"

CodeAct Agent SDK with an AST-based code execution engine, enabling stop/start workflows, tool-level state management, and enhanced observability.

📄 PDF extraction and rendering across all JavaScript runtimes

Build cross-browser extensions with native HMR and zero-config setup

AlphaFold 3 inference pipeline.

An async ORM for Rust (incubating)

Command-line sampling profiler for macOS, Linux, and Windows

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

Test and benchmark suite for sort implementations.

An extensible, state of the art columnar file format. Formerly at @spiraldb, now an Incubation Stage project at LFAI&Data, part of the Linux Foundation.

Rust Bindings for the Skia Graphics Library

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Code for the paper "Evaluating Large Language Models Trained on Code"

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning