High-performance Toolkit for WebGL-based Data Visualization

Large Language Models for GNU Octave

Simple HTML5 Charts using the <canvas> tag

software vulnerability detection

Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.

Python Library and CLI for the LanguageTool JSON API

Fast word vectors with little memory usage in Python

SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.

Community-maintained fastText fork for modern Python and portable native builds.

Access to the latest 'Janelia FlyEM' datasets

The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Open source vulnerability DB and triage service.

OSS-Fuzz vulnerabilities for OSV.

LLM powered fuzzing via OSS-Fuzz.

OSS-Fuzz - continuous fuzzing for open source software.

ExploitBench measures how far AI agents climb, from reaching vulnerable code, to triggering the bug, to building exploit primitives, to arbitrary code execution.

CyberGym-E2E is a large-scale benchmark built from real-world vulnerabilities in widely used open-source projects to evaluate AI agents' end-to-end cybersecurity capabilities, from discovering vuln…

CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on real-world vulnerability analysis tasks.

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.

FoundationDB - the open source, distributed, transactional key-value store

Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.

Event-driven network application framework for high performance protocol servers & clients, non-blocking.

Minimal metadata schemas for science software and code, in JSON-LD

Measuring Cross-Modal Synergy: A Game-Theoretic Benchmark for VLM Explainability (NeurIPS 2026)