API Knowledge
API knowledge is the layer of indexes, descriptions, contexts, and signals that lets humans and agents reason about which APIs exist, what they do, who operates them, what they cost, how to call them, and how trustworthy they are. This topic repo catalogs the formats and platforms that publish API knowledge — APIs.json as a sitemap for an API project, APIs.guru as the community OpenAPI directory, RapidAPI Hub and the Postman Public API Network as commercial discovery surfaces, the OpenAPI Initiative as the spec authority, Jentic and Composio as agent-facing knowledge layers, llms.txt as a site-level guide for LLMs, schema.org/WebAPI as the structured-data vocabulary. Together they form a multi-source view of the API knowledge an AI agent needs to do real work against the API economy.
Resources
-
APIs.json
APIs.json is an open-source machine-readable format for indexing the surface area of an API project — its operations, OpenAPI files, JSON Schema, JSON-LD contexts, documentation, pricing, status page, and maintainer contacts. It functions…
-
APIs.guru OpenAPI Directory
APIs.guru is the community-driven directory of OpenAPI 2.0 and 3.x definitions for publicly available APIs. As reported on the api.apis.guru metrics endpoint, the directory currently indexes 2,529 APIs across 677 providers, with 3,992 spec…
-
RapidAPI Hub
RapidAPI Hub is a commercial API marketplace and developer portal that acts as a discovery, onboarding, and metering layer over thousands of third-party APIs. RapidAPI Hub fronts a single key, single billing relationship, and a normalized…
-
Postman Public API Network
The Postman Public API Network is Postman's public-facing index of API workspaces, collections, and environments. Postman's "Explore" surface organizes the network by category (App Security, Artificial Intelligence, Payments, etc.) and is…
-
OpenAPI Initiative
The OpenAPI Initiative (OAI) is the Linux Foundation working group that stewards the OpenAPI Specification — the de-facto contract format for HTTP APIs and the substrate underneath most API knowledge tooling. OpenAPI 3.2.0 was released on…
-
Jentic
Jentic is a governed execution layer that lets AI agents call enterprise APIs safely. It describes API workflows using the Arazzo open standard on top of OpenAPI, validates agent behavior in a sandbox, and converts successful interactions…
-
Composio
Composio is an agent integration platform that exposes 1,000+ third-party applications as agent-ready tools. Composio publishes a tool registry accessed through session.tools() and ships both an OpenAPI-based native tool representation and…
-
llms.txt
llms.txt is a community specification for a markdown file placed at the root path /llms.txt that gives LLMs a curated, link-rich entry point to a site's most important content. The spec is the lightest-weight form of API knowledge — it doe…
-
schema.org WebAPI
schema.org/WebAPI is the structured-data vocabulary for describing an "application programming interface accessible over Web/Internet technologies." It inherits from schema.org/Service and contributes properties like documentation, provide…
Links
Providers working in API Knowledge
Providers whose own tags share at least two of this topic's tags, most shared first — the top 30 of 118.
| Provider | About | Rating | APIs |
|---|---|---|---|
| WebCrawlerAPI | WebCrawlerAPI is a web crawling and scraping API from 103 Labs (Netherlands) that turns websites into clean, LLM-ready markdown, cleaned text, HTML or link lists for AI agents, support bots and RAG pipelines. It offers asynchronous multi-p… | strong | 2 |
| Cognee | Cognee is an open-source AI memory and knowledge graph platform that enables developers to build persistent, structured memory for AI agents and LLM applications. The platform provides a REST API and Python/TypeScript SDKs for ingesting do… | developing | 1 |
| H2O.ai | H2O.ai is an open-source artificial-intelligence and machine-learning company whose platform spans H2O-3 (a distributed, in-memory ML engine), H2O Driverless AI (automatic machine learning), H2O MLOps (model deployment, scoring and monitor… | developing | 2 |
| Zep | Zep is a context engineering and agent memory platform that assembles relevant context from chat history, business data, and user interactions for AI agents. It builds a temporal knowledge graph per user that evolves as new facts arrive, a… | developing | 1 |
| Julep | Julep is an open-source platform for building stateful AI agents that remember past interactions and execute long-running, multi-step tasks. Its cloud API and self-hostable server expose agents, sessions, tasks, executions, documents (RAG)… | thin | 1 |
| Docling | Docling is an open-source toolkit for parsing diverse document formats — PDF, DOCX, PPTX, XLSX, HTML, images, audio, LaTeX, plain text — into a unified, lossless DoclingDocument representation that downstream generative AI and RAG systems… | thin | 2 |
| Eder Labs | Eder Labs builds infrastructure for using personal data in safer, more human ways. Its current focus is Persona, an open-source (MIT) user-memory system for AI agents that turns a person's digital footprint into a Graph-Vector hybrid perso… | thin | 1 |
| Superduper | Superduper (formerly SuperDuperDB) is an open-source Python framework for building database-integrated AI agents and applications directly on top of existing databases - MongoDB, SQL databases, Snowflake, and Redis - without separate vecto… | emerging | 6 |
| Miriel | Miriel is the context engine and platform for AI-native development. It gives AI apps and agents the context they need in real time through a simple API: developers connect a data source with the learn operation and retrieve relevant conte… | emerging | 7 |
| RDF | The Resource Description Framework (RDF) is a W3C standard for representing information about resources on the web. RDF is the foundation for linked data and the semantic web, providing a graph-based data model where statements are express… | emerging | 0 |
| Naboo | Naboo is Reasoning Layer infrastructure for enterprise AI agents, built on a Decision Graph that models how a company actually decides, ships, and unblocks - who decided what, what triggered each decision, what blocks it, and what depends… | emerging | 0 |
| APIs.io | APIs.io is an open-source API search engine and federated discovery network built on the APIs.json specification. It indexes API providers and their individual APIs across the public internet along with the machine-readable artifacts they… | exemplar | 20 |
| Arcade | Arcade.dev is the MCP runtime for production AI agent deployments. The Arcade Engine — a hosted or self-hostable API surface — handles OAuth user authorization, manages user tokens, and exposes 7,000+ pre-built integrations as Model Contex… | exemplar | 4 |
| Dust | Dust is a Paris-based enterprise AI platform for building, deploying, and operating teams of AI agents that have shared context across a company's knowledge and tools. Dust positions itself as the platform for "AI Operators" — the people w… | exemplar | 9 |
| AlphaAI | A REST API and agent-native platform for relevance-scored, ticker-linked financial news, built for trading bots, agent backends, and dashboards. Every article is enriched at ingest with a 1-10 relevance score, one of fourteen categories, v… | exemplar | 1 |
| Seekr | Seekr Technologies builds explainable, auditable, sovereign AI for regulated industries and high-stakes government missions. Its platform, SeekrFlow, is an end-to-end AI operating system that covers document ingestion and AI-ready data pre… | exemplar | 8 |
| Compresr | Compresr is an LLM context-compression API. You send the long context you would otherwise pass to a model plus the query you want answered, and Compresr returns a shorter context that keeps the answer-bearing spans and drops the rest — few… | strong | 1 |
| Airia | Airia (Airia LLC, Atlanta) is an enterprise AI orchestration, security and governance platform: a no-code/low-code/pro-code agent builder, a model routing and cost gateway, an MCP Gateway that fronts 1,000+ app connectors and turns hosted… | strong | 2 |
| Wikidata | Wikidata is a free, collaborative, multilingual knowledge graph hosted by the Wikimedia Foundation. It provides structured linked data for Wikipedia and other Wikimedia projects, as well as a public platform for anyone to read and edit. Wi… | strong | 1 |
| LlamaParse | LlamaParse is an enterprise document parsing and AI pipeline platform from LlamaIndex that converts complex PDFs, Office files, and 130+ document formats into LLM-ready structured outputs. The platform offers six composable products under… | strong | 1 |
| gpt55-token-gateway | gpt55-token-gateway is the self-chosen service name of an unnamed operator running two OpenAI-compatible AI API gateways on the 558686.xyz domain. GPT55 Model Gateway (gpt55.558686.xyz) sells single GPT-5.6 Luna, GPT-5.5 and GPT-5.3-codex… | strong | 5 |
| Mem0 | Mem0 is a memory infrastructure layer that gives AI agents and applications persistent context across sessions. The platform automatically condenses chat history into compact memories that reduce tokens and latency while preserving the rig… | strong | 1 |
| Gumloop | Gumloop is an AI-agent automation platform for building, deploying, and governing agents that automate real work — data analysis, customer support, CRM management, and back-office tasks — across tools like Slack, Microsoft Teams, and Gmail… | strong | 1 |
| Orthogonal | Orthogonal is a unified API and payment layer for AI agents, backed by Pantera Capital and Y Combinator. An agent describes what it needs in natural language and Orthogonal returns the right service from a catalog of 40+ third-party APIs (… | strong | 2 |
| Amazon Bedrock | Amazon Bedrock is a fully managed AWS service that makes high-performing foundation models from leading AI companies available through a unified API for building generative AI applications. It supports text and image generation, conversati… | strong | 2 |
| Space Frontiers | Space Frontiers is a Wyoming corporation whose search and AI product, Machine Library (formerly Space Frontiers search, moved to machinelibrary.ai on 2026-09-12), is a full-text retrieval API and hosted MCP server over a corpus of roughly… | strong | 2 |
| Vectara | Vectara is a Retrieval Augmented Generation (RAG) as a service platform that provides grounded generative AI for enterprises. The API-first platform exposes a unified REST API v2 for managing corpora, ingesting documents, performing semant… | strong | 1 |
| Meta Agent Tools | A registry/catalog of MCP servers, agent skills and plugins. It aggregates MCP metadata from the Official MCP Registry, Smithery and Casdoor, and public skill dumps, exposing a REST/HTTP API, a hosted MCP server, an llms.txt agent guide an… | developing | 1 |
| Quadrillion | Quadrillion Labs builds Qualia, an AI coding agent for researchers that runs hundreds of agents in parallel to compress weeks of research into hours. Qualia is a Jupyter-compatible notebook IDE with autonomous mode, a central knowledge gra… | developing | 1 |
| Toolhouse | Toolhouse is a Backend-as-a-Service platform for building, deploying, and managing "AI workers" (Toolhouse's current product noun, used interchangeably with "AI agents"). The homepage frames the value proposition as "Turn your AI chats int… | developing | 1 |