Directory

Hosted observability and evaluation platform for AI agents with tracing, experiments, pattern detection, a CLI, MCP access and an AI assistant (Loop) that analyzes traces and builds evals

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

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

Web data API that scrapes, crawls, maps and searches websites and returns clean Markdown or structured JSON for LLM pipelines, with an AGPL-licensed self-hostable core

Hosting platform for open models, datasets and Spaces demo apps built on git repositories and Xet storage, with Inference Providers, Endpoints, Jobs and an open-source Python client and CLI

Prefix-style API from Jina AI that converts any public URL into LLM-ready Markdown (r.jina.ai) or returns web search results with content (s.jina.ai), with open-source server code

Open-source Python SDK and self-hosted AI gateway that calls 100+ LLM providers in the OpenAI format, with routing, fallbacks, virtual keys, budgets, spend tracking and logging callbacks

French model provider offering open-weight and proprietary models through the Studio API, OCR and speech models, the Vibe agent for productivity and coding, and self-deployment options

OpenAI's coding agent: an open-source Rust terminal CLI plus IDE extension, desktop app and cloud agent, signed in with a ChatGPT plan or an API key

Open-source, local-first CLI and library for evaluating prompts, models, RAG pipelines and agents, with automated red teaming and CI integration

ML experiment tracking, sweeps, artifacts and model registry plus Weave for LLM tracing and evaluation, now sold by CoreWeave within its Forge platform with a free academic tier