Directory

Enterprise-focused model provider with Command generation, Embed and Rerank retrieval models, Aya multilingual research models, the North agent platform and private or dedicated deployment options

Open-source node-based interface and inference engine for diffusion and other generative models (image, video, audio, 3D), runnable locally with desktop apps or as a hosted cloud

Nonprofit open repository of petabyte-scale web crawl data since 2008, published as WARC, WAT and WET files on AWS Open Data with URL and columnar indexes

Visual literature-exploration tool that builds a similarity graph of papers around a seed paper, with prior and derivative works lists

AI search engine over peer-reviewed literature that synthesizes answers, shows a Consensus Meter for yes/no questions and summarizes studies

Block-based document and notes app with native Apple, Windows and web clients, structured pages, collections and shareable published documents

Open-source crawling and scraping library for Node.js/TypeScript and Python that unifies HTTP and headless-browser crawlers with queues, proxies, fingerprints and storage

Open-source Python framework for role-based multi-agent crews and event-driven flows, with a commercial enterprise console for deploying, monitoring and triggering automations

Membership organization that registers DOIs for scholarly content and exposes the metadata through a free public REST API, content negotiation and the paid Metadata Plus service

Open-source behavior-based intrusion prevention engine whose detections feed a crowd-sourced IP reputation network, with remediation components for firewalls, proxies and CDNs

AI-native code editor from Anysphere, forked from VS Code, with inline edits, codebase-aware chat and agent mode that can run multi-step changes

End-to-end and component testing framework that runs tests inside the browser with an interactive runner, paired with the commercial Cypress Cloud

Asset-oriented Python orchestrator that models pipelines as software-defined data assets with lineage, checks and a hosted Dagster+ option

Python library for parallel and distributed computing that scales pandas, NumPy and custom task graphs from a laptop to a cluster

Open table format with a transaction log over Parquet files, created by Databricks and hosted by the Linux Foundation, with Spark, Rust and Python implementations

Secure-by-default JavaScript and TypeScript runtime from Deno Land with web-standard APIs, built-in tooling and an optional hosted Deploy service

Community chat platform with servers, text and voice channels, video, forums and a bot API, free to use with optional Nitro subscriptions

React-based static site generator from Meta for documentation sites with MDX content, versioning, localization and a plugin architecture

Québec's shared open-data portal where provincial ministries and municipalities publish datasets under a Creative Commons Attribution licence

TypeScript ORM with SQL-like query builder, schema defined in code, migrations through Drizzle Kit, and support for PostgreSQL, MySQL and SQLite drivers

Hosted voice AI platform: text-to-speech and speech-to-text models, voice cloning, dubbing, music and sound effects, a voice-agent builder and a REST API with Python and TypeScript SDKs

AI research assistant that finds papers, extracts structured data from them into tables and runs systematic-review style workflows and reports

Pluggable static analysis tool for JavaScript and TypeScript that finds problems in code through configurable rules and can fix many automatically

Ethereum block explorer and multichain REST API exposing balances, transactions, token transfers, verified contract source, logs and gas data