The Agent Index

Infrastructure for AI agents. Tools an agent reaches for mid-workflow to do its job. Verified by the builders who use them every day.


  • Anthropic API

    Claude models (Sonnet, Opus, Haiku) via REST API with native tool-use, extended thinking, and MCP support.

    LLM InferenceREST API
  • Google Gemini API

    Gemini 3 Pro and Flash models with native multimodal input, 2M token context, and image generation.

    LLM InferenceREST API
  • Groq

    Ultra-low-latency inference for open models (Llama, Mixtral, Qwen) on custom LPU silicon.

    LLM InferenceREST API
  • OpenAI API

    GPT-4 class models, embeddings, image generation, and the Responses API via REST.

    LLM InferenceREST API
  • Together AI

    Hosted inference for hundreds of open models plus dedicated endpoints and fine-tuning.

    LLM InferenceREST API
  • Letta

    Stateful agent platform with persistent memory, context management, and a REST API for agent servers.

    MemoryREST API
  • Mem0

    Persistent memory layer for AI agents with user-scoped storage, semantic recall, and fact extraction.

    MemoryREST API
  • Zep

    Long-term memory for AI agents built on a temporal knowledge graph (Graphiti).

    MemoryPython Library
  • Chroma

    Embedded and hosted vector database with a simple Python-first API, popular for RAG prototyping.

    Vector StoresPython Library
  • Pinecone

    Fully managed vector database with serverless indexes, hybrid search, and metadata filtering.

    Vector StoresREST API
  • Qdrant

    Rust-based vector search engine with strong filtering, sparse vector support, and a managed cloud.

    Vector StoresREST API
  • Turbopuffer

    Object-storage-native vector database designed to store billions of vectors cheaply on S3.

    Vector StoresREST API
  • Weaviate

    Open-source vector database with native hybrid search, multi-tenancy, and generative modules.

    Vector StoresREST API
  • AssemblyAI

    Speech intelligence API with transcription, speaker diarization, sentiment, and topic extraction.

    Voice and SpeechREST API
  • Cartesia

    State-space-model TTS with sub-100ms first-token latency and streaming voice synthesis.

    Voice and SpeechREST API
  • Deepgram

    Speech-to-text and text-to-speech APIs tuned for low latency and real-time agent pipelines.

    Voice and SpeechREST API
  • ElevenLabs

    High-fidelity voice synthesis with voice cloning, streaming TTS, and a conversational agent API.

    Voice and SpeechREST API
  • Browserbase

    Managed headless browser infrastructure for AI agents with session recording, live view, and stealth.

    Browser AutomationSDK
  • Stagehand

    High-level browser automation library that lets agents describe actions in natural language.

    Browser AutomationTypeScript Library
  • Steel Browser

    Open-source browser API for AI agents with session persistence, proxies, and CAPTCHA handling.

    Browser AutomationREST API
  • Daytona

    Open-source development environments on demand for AI agents to read, edit, and execute codebases.

    Code ExecutionCLI
  • E2B

    Secure cloud sandboxes for AI agents to run code, render files, and execute long-running processes.

    Code ExecutionSDK
  • Modal

    Serverless cloud platform for running Python functions, GPU jobs, and containers on demand.

    Code ExecutionPython Library
  • Riza

    Secure code interpreter API for LLM-generated code with fast-start sandboxes and memory isolation.

    Code ExecutionREST API
  • Exa

    Neural web search API designed for LLMs, with semantic matching, live-crawled content, and similarity queries.

    Web Search and RetrievalREST API
  • Firecrawl

    Scrape any website into clean markdown or structured data with a single API call, including JS-rendered pages.

    Web Search and RetrievalREST API
  • Tavily

    Search API built specifically for AI agents with grounded answers, source citations, and news search.

    Web Search and RetrievalREST API
  • CueAPI

    Scheduling and execution accountability API for AI agents with verified outcomes and retries.

    Scheduling and OrchestrationREST API
  • Inngest

    Durable execution platform for background jobs, AI workflows, and long-running agent steps.

    Scheduling and OrchestrationSDK
  • Trigger.dev

    Background job platform with built-in AI task support, concurrency controls, and wait-until-event primitives.

    Scheduling and OrchestrationSDK
  • Resend

    Developer-first transactional email API with React Email integration and high deliverability.

    CommunicationREST API
  • SendGrid

    Email delivery infrastructure for transactional and marketing mail at high volume.

    CommunicationREST API
  • Arcade AI

    Authenticated tool-calling platform for agents with permissioned actions and per-user credential storage.

    Credentials and Tool ManagementSDK
  • Composio

    Tool and credential management platform for AI agents with 250+ pre-built integrations and OAuth handling.

    Credentials and Tool ManagementSDK
  • Metorial

    Managed MCP and tool-use platform for AI agents with credential vaulting and usage analytics.

    Credentials and Tool ManagementMCP Server
  • Context7

    MCP server that feeds agents up-to-date library documentation and code examples from the source.

    MCP EcosystemMCP Server
  • Model Context Protocol

    Open standard for connecting AI agents to tools and data sources, with a reference server collection.

    MCP EcosystemMCP Server
  • Smithery

    MCP server registry and hosting with one-click install for Claude, Cursor, and other MCP clients.

    MCP EcosystemMCP Server

The Agent Index is open source. The canonical list lives on GitHub, and every entry on this page is generated from that repo at build time. Contributions are welcome as pull requests. Read the rules before submitting; the bar is sharp, but the review is fast.

Tools are added after they show up in production agent workflows or get strong signal from builders with real usage. Inclusion is the editorial judgment. There is no ranking within categories. Every tool listed has earned its place against the same criterion: can an agent complete its full lifecycle through a fully programmatic path?