Infrastructure & Ops

Email inbox API built for AI agents. Create, send, receive, search, and manage email programmatically with SDKs for Pyt…

Builds, deploys and runs continuous autonomous agents through a low-code block-based builder, the project that populari…

Defines the Agent2Agent interoperability protocol and SDKs so agents built on different frameworks discover each other,…

Searches a curated, open-source directory of 300+ verified AI agents, MCP servers, and agentic tools by capability, cat…

ByteDance's multimodal AI agent for desktop and browser automation — controls GUIs, browsers, and shell via vision and…

Observability platform purpose-built for AI agents. Track agent sessions, LLM calls, tool use, and costs. Integrates wi…

Python framework for building multi-agent platforms — define agents in code, deploy as FastAPI services. 40k GitHub sta…

Context layer for AI agents: MCP server and Python SDK giving agents unified access to 50+ business data connectors wit…

Production agent runtime on AWS with microVM isolation, 8-hour sessions, persistent memory, browser automation, MCP gat…

Handles agent authorization, tool calling, and governance so agents act on behalf of users. MCP runtime with Python/JS…

Traces, evaluates and debugs LLM and agent applications from an open-source observability platform built on OpenTelemet…

Microsoft's open-source multi-agent framework. Supports conversational, autonomous, and human-in-the-loop agent pattern…

Official AWS MCP servers (GA May 2026) — 15+ servers for S3, Lambda, DynamoDB, CDK, and Bedrock. Adds sandboxed Python…

Microsoft's unified platform for building, evaluating, and deploying AI agents with access to OpenAI and open-source mo…

Foundational autonomous task-management agent that launched the AI agent movement; uses GPT-4 and a vector store to cre…

Deploys models as production inference APIs with dedicated GPU deployments, Truss packaging, and OpenAI-compatible endp…

Routes LLM requests across 23+ providers through one OpenAI-compatible API, with automatic failover, load balancing, se…

Agent networking platform — connect any agent (CrewAI, LangChain, bare Python) to a public catalog via one SDK call. Ca…

Evaluates and observes LLM applications end to end: capture traces, score them with evals, iterate in a prompt playgrou…

Drives a local open-source Chromium using your existing logged-in sessions, feeding external agents compact page snapsh…

Pioneering multi-agent framework for role-playing collaboration, scaling-law research, and MCP server exports with 20+…

Anthropic's Model Context Protocol — open standard for connecting AI models to tools, data sources, and services with u…

Gives coding agents a disposable, network-restricted Linux VM with root in the guest while your files and keychain stay…

TypeScript SDK for building stateful AI agents on Cloudflare Durable Objects. Built-in SQL state, WebSocket, task sched…

Official Cloudflare MCP server suite. Lets AI agents manage Workers, KV storage, D1 databases, R2 buckets, and deploy e…

Cloudflare platform for running agents, apps, and background work on the edge network, with integrated compute, storage…

Gives AI agents onchain wallets and the ability to transact, with action providers for payments, swaps, and smart contr…

Tool integration platform for AI agents. 250+ pre-built integrations with GitHub, Slack, Salesforce, and more. Handles…

MCP server that gives coding agents isolated containerised environments in separate git branches, enabling multiple age…

Microsoft's low-code platform for building custom AI copilots and agents with enterprise connectors, knowledge groundin…

React and TypeScript SDK for building in-app AI copilots and agentic UIs. Includes real-time human-in-the-loop controls…

Multi-agent orchestration framework for building teams of AI agents that collaborate, delegate, and solve complex tasks…

Git code hosting from Cursor built for agent-driven development, with repository storage, review surfaces, and native i…

Decentralized inference on idle Apple Silicon Macs. OpenAI-compatible API, end-to-end encrypted, hardware-attested priv…

End-to-end monitoring for LLM applications — trace prompts, evaluate responses, track costs, and debug AI pipelines in…

Runs a self-hostable DBA agent for Postgres and MySQL that monitors workloads, rewrites slow queries and proposes index…

Open-source LLM app and agent development platform. Build, test, and deploy RAG pipelines, chatbots, and multi-agent wo…

Disposable, isolated container sandboxes for running untrusted agent-generated code, with filesystem and network isolat…

Authenticated email gateway for AI agents — receive emails as webhooks or WebSocket, send via HTTP API, and verify send…

Routes each request across specialist open-weight models behind a single endpoint, allocating compute per task to cut i…

Desktop app + Rust relay that aggregates MCP servers behind one endpoint. Add GitHub, Notion, Slack, and custom servers…

Google cloud workspace for building and deploying full-stack AI applications, combining an agentic editor with Firebase…

Production inference platform for open models with fast function calling, structured output, and fine-tuning behind an…

Open-source drag-and-drop UI for building LLM flows and AI agents. Deploy as a self-hosted server with REST API for int…

AMD's open-source Python/C++ framework for AI agents running fully locally on AMD NPU/GPU. Includes MCP integration, RA…

DevOps platform with a documented REST and GraphQL API for repositories, merge requests, CI pipelines, and issues.

MCP server directory with a public paginated JSON API for programmatic discovery, plus hosting and inspection tooling f…

Official Google MCP server for 30+ databases — BigQuery, Postgres, AlloyDB, Spanner, MySQL, Redis, Neo4j. YAML-configur…

MCP server giving AI agents full control over 12 Google services — Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms,…

Connects AI agents to Grafana via an official MCP server — query dashboards, datasources, Prometheus and Loki, and mana…

Low-latency inference API running open models on custom LPU hardware, with an OpenAI-compatible interface and tool-call…

Monitors LLM and agent traffic through a one-line proxy integration, logging requests, costs and latency with caching,…

Gives agents x402 V2 paid-request access on Solana USDC — settlement verification, receipts, entitlements, atomic meter…

Hosted MCP server letting AI assistants query Honeycomb observability data, analyse telemetry datasets, inspect alerts,…

Agents that perform read-only production debugging, tracing failures across services without mutating state. Y Combinat…

Durable execution platform for event-driven and long-running agent workflows, with automatic retries, step functions, a…

Runs local LLMs 100% offline in a desktop app and connects cloud models, exposing a local OpenAI-compatible API. Privac…

Connects agents to 100+ third-party MCP integrations with managed OAuth, hosted or self-hosted servers, and Strata prog…

Framework for building LLM applications with chains, agents, and tool use — plus LangSmith for tracing, evaluation, and…

Visual builder for AI agents and workflows — drag-and-drop graphs compiled to REST endpoints. Every flow becomes an MCP…

Open-source LLM observability and analytics. Trace, evaluate, and debug LLM apps with prompt versioning, score tracking…

Graph-based agent orchestration with stateful multi-actor workflows. Deploy agents as REST APIs via LangGraph Platform.…

Lightweight Python multi-agent framework from CMU and UW-Madison where agents are first-class objects with task delegat…

Self-hosts an open ChatGPT-style platform with custom Agents, MCP tools, Code Interpreter, and multi-provider models. E…

AI gateway unifying 100+ LLM providers under one OpenAI-compatible API. Cost tracking, guardrails, load balancing. pip…

Runs open LLMs locally with an OpenAI- and Anthropic-compatible server, the lms CLI, a headless daemon, and MCP support…

Serves local LLM, vision, image and voice inference behind an OpenAI-compatible API, letting agents run on consumer har…

Gives agents public tunnel URLs for localhost with live HTTP traffic inspection, snapshot publishing, and access contro…

Builds and runs enterprise agents entirely inside private cloud or on-prem infrastructure, keeping data and model calls…

Persistent CPU and GPU virtual machines for agents that need long-running state, letting a session keep its filesystem…

Open-source enterprise RAG platform for building AI agents. Upload docs, auto-vectorize, and orchestrate multi-step wor…

Builds MCP servers and clients in Python with typed tool, resource, and prompt primitives plus stdio and streamable HTT…

Open-source healthcare developer platform providing a FHIR-native backend, API, and SDK for building compliant clinical…

Multi-agent framework where AI agents role-play as engineers, PMs, and QA to collectively produce software from a singl…

Serverless cloud for running Python functions, GPU workloads, and sandboxed agent code, defined in code and deployed wi…

Official MCP server from GMO Pepabo for searching and registering domains, managing contracts, and configuring DNS reco…

Open-source workflow automation with AI agent capabilities — build complex multi-step automations with 400+ integration…

Open-source OAuth and API integration platform. 300+ pre-built integrations. Handles token refresh, rate limits, and we…

Official Netlify MCP server that lets agents create sites, trigger deploys, manage environment variables, and inspect b…

Hosts custom code Workers in a secure sandbox and connects external AI agents like Claude and Codex into Notion workspa…

Run LLMs locally — Llama, Mistral, Gemma, DeepSeek, and 100+ models via CLI and REST API. OpenAI-compatible endpoint at…

Stores API keys in a central gateway and injects them into outbound requests at call time, so AI agents can use credent…

Self-hosted AI platform with OpenAI-compatible REST API, MCP support, and a pipelines SDK. Supports Ollama, OpenAI, Ant…

Python framework for building multi-agent systems with handoffs, guardrails, and tool use — the official OpenAI agent o…

Unified API gateway routing requests across hundreds of language models from many providers, with automatic fallback, c…

Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…

Serves agent memories, resources and skills as a virtual filesystem under viking:// URIs, loading context on demand acr…

Traces LLM and agent runs, scores them with LLM-as-a-judge and heuristic metrics, and monitors production quality via P…

World's first AI-native database with agents running inside the kernel. Features no-code Agent Factory, unified vector…

Runs AI agents entirely on your Mac — a native Apple Silicon runtime for local MLX models with shared memory, file acce…

Runs reply-aware cold outbound email for AI agents with managed inboxes, durable sequences, signed webhooks, sender pac…

Intelligent incident management with AI-powered event correlation, noise reduction, and automated incident response.

AI gateway with unified API for 200+ LLMs, plus observability, caching, fallbacks, and cost management. Drop-in replace…

Connects agents to Postgres over MCP with configurable read or write access plus index tuning, EXPLAIN plan analysis an…

Open-source, self-hostable coding agent platform for running cloud coding sessions on your own infrastructure.

Infrastructure as code with AI — generate cloud infrastructure definitions from natural language using Pulumi's multi-l…

Type-safe Python agent framework from the Pydantic team. Built-in MCP client, ships a sandboxed Python execution MCP se…

Open-source RAG engine with deep document parsing (tables, charts, images) and an official MCP server. Deploy via Docke…

Deployment platform with a GraphQL API and CLI for provisioning services, databases, and environments from code.

Cloud platform with a REST API and CLI for deploying web services, cron jobs, and managed databases without server mana…

Run open-source AI models in the cloud — image generation, language models, video, audio via simple API calls.

Builds and deploys full applications autonomously in the cloud, provisioning databases, writing authentication, running…

Error monitoring with AI-powered issue grouping, root cause analysis, and automated fix suggestions for production appl…

Official Sentry remote MCP server — pull issues, traces, and AI root-cause analysis into any coding agent. Works with C…

Builds agent workflows on a visual canvas and ships each one as a versioned REST endpoint or MCP tool, connecting 1,000…

MCP registry and hosted gateway with 14,000+ servers, handling OAuth flows, credential injection, and session reuse acr…

Auto-generates governed MCP servers from existing integration pipelines, OpenAPI specs, and API-management services — n…

Unified routing API for voice models across providers, giving voice agents one interface for speech-to-text, text-to-sp…

Reads Sentry and Datadog errors, reproduces them, and opens pull requests with fixes, using a memory system trained on…

Official HashiCorp MCP server connecting AI assistants to Terraform Registry APIs for live provider docs, module search…

Inference and fine-tuning platform for open models, offering serverless endpoints, dedicated GPU clusters, and an OpenA…

Real-time voice AI framework connecting LLMs to phone calls — build conversational AI agents over Twilio's voice infras…

TypeScript toolkit for building AI applications with React Server Components, streaming, tool calling, and multi-provid…

Google Cloud's platform for building AI agents with grounding, tool use, and multi-turn conversation — supports A2A pro…

SMS verification API with real SIM-backed numbers for AI agents. Buy numbers, fetch OTPs, check balance via REST or MCP…

High-throughput LLM inference server with OpenAI-compatible API. Serves Llama, Mistral, Qwen, and 30+ model families wi…

Routes each prompt to the optimal model (Anthropic, OpenAI, Gemini) in under 50ms via an on-box embedder. Drop-in proxy…

Governs, secures, and scales enterprise AI agents across frameworks with zero-trust runtime, OpenTelemetry observabilit…

Gives AI agents a search engine and payment layer for ~29,000 tools and services — agents discover the best service per…