Infrastructure & Ops
Foundational AI infrastructure — agent frameworks, LLM gateways, observability platforms, and integration layers. These are the tools production AI applications depend on: rate limiting, cost tracking, tracing, fallbacks, and connecting agents to external APIs. The plumbing of the agentic stack.
AgentMail
Email inbox API built for AI agents. Create, send, receive, search, and manage email programmatically with SDKs for Pyt…
AgentOps
Observability platform purpose-built for AI agents. Track agent sessions, LLM calls, tool use, and costs. Integrates wi…
Claude MCP
Anthropic's Model Context Protocol — open standard for connecting AI models to tools, data sources, and services with u…
Cloudflare Agents SDK
TypeScript SDK for building stateful AI agents on Cloudflare Durable Objects. Built-in SQL state, WebSocket, task sched…
Composio
Tool integration platform for AI agents. 250+ pre-built integrations with GitHub, Slack, Salesforce, and more. Handles…
Langfuse
Open-source LLM observability and analytics. Trace, evaluate, and debug LLM apps with prompt versioning, score tracking…
Oracle AI Database 26ai
World's first AI-native database with agents running inside the kernel. Features no-code Agent Factory, unified vector…
Portkey
AI gateway with unified API for 200+ LLMs, plus observability, caching, fallbacks, and cost management. Drop-in replace…
Vercel AI SDK
TypeScript toolkit for building AI applications with React Server Components, streaming, tool calling, and multi-provid…
Agent TARS
ByteDance's multimodal AI agent for desktop and browser automation — controls GUIs, browsers, and shell via vision and…
Agno
Python framework for building multi-agent platforms — define agents in code, deploy as FastAPI services. 40k GitHub sta…
Airbyte Agents
Context layer for AI agents: MCP server and Python SDK giving agents unified access to 50+ business data connectors wit…
Amazon Bedrock AgentCore
Production agent runtime on AWS with microVM isolation, 8-hour sessions, persistent memory, browser automation, MCP gat…
AutoGen
Microsoft's open-source multi-agent framework. Supports conversational, autonomous, and human-in-the-loop agent pattern…
AWS MCP Suite
Official AWS MCP servers (GA May 2026) — 15+ servers for S3, Lambda, DynamoDB, CDK, and Bedrock. Adds sandboxed Python…
Azure AI Foundry
Microsoft's unified platform for building, evaluating, and deploying AI agents with access to OpenAI and open-source mo…
BabyAGI
Foundational autonomous task-management agent that launched the AI agent movement; uses GPT-4 and a vector store to cre…
Blocks
Agent networking platform — connect any agent (CrewAI, LangChain, bare Python) to a public catalog via one SDK call. Ca…
CAMEL
Pioneering multi-agent framework for role-playing collaboration, scaling-law research, and MCP server exports with 20+…
Cloudflare MCP
Official Cloudflare MCP server suite. Lets AI agents manage Workers, KV storage, D1 databases, R2 buckets, and deploy e…
Container Use
MCP server that gives coding agents isolated containerised environments in separate git branches, enabling multiple age…
Copilot Studio
Microsoft's low-code platform for building custom AI copilots and agents with enterprise connectors, knowledge groundin…
CopilotKit
React and TypeScript SDK for building in-app AI copilots and agentic UIs. Includes real-time human-in-the-loop controls…
CrewAI
Multi-agent orchestration framework for building teams of AI agents that collaborate, delegate, and solve complex tasks…
Darkbloom
Decentralized inference on idle Apple Silicon Macs. OpenAI-compatible API, end-to-end encrypted, hardware-attested priv…
Datadog LLM Observability
End-to-end monitoring for LLM applications — trace prompts, evaluate responses, track costs, and debug AI pipelines in…
Dify
Open-source LLM app and agent development platform. Build, test, and deploy RAG pipelines, chatbots, and multi-agent wo…
E2a
Authenticated email gateway for AI agents — receive emails as webhooks or WebSocket, send via HTTP API, and verify send…
Endara
Desktop app + Rust relay that aggregates MCP servers behind one endpoint. Add GitHub, Notion, Slack, and custom servers…
Flowise
Open-source drag-and-drop UI for building LLM flows and AI agents. Deploy as a self-hosted server with REST API for int…
GAIA by AMD
AMD's open-source Python/C++ framework for AI agents running fully locally on AMD NPU/GPU. Includes MCP integration, RA…
Google MCP Toolbox
Official Google MCP server for 30+ databases — BigQuery, Postgres, AlloyDB, Spanner, MySQL, Redis, Neo4j. YAML-configur…
Google Workspace MCP
MCP server giving AI agents full control over 12 Google services — Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms,…
Honeycomb MCP
Hosted MCP server letting AI assistants query Honeycomb observability data, analyse telemetry datasets, inspect alerts,…
LangChain / LangSmith
Framework for building LLM applications with chains, agents, and tool use — plus LangSmith for tracing, evaluation, and…
Langflow
Visual builder for AI agents and workflows — drag-and-drop graphs compiled to REST endpoints. Every flow becomes an MCP…
LangGraph
Graph-based agent orchestration with stateful multi-actor workflows. Deploy agents as REST APIs via LangGraph Platform.…
Langroid
Lightweight Python multi-agent framework from CMU and UW-Madison where agents are first-class objects with task delegat…
LiteLLM
AI gateway unifying 100+ LLM providers under one OpenAI-compatible API. Cost tracking, guardrails, load balancing. pip…
MaxKB
Open-source enterprise RAG platform for building AI agents. Upload docs, auto-vectorize, and orchestrate multi-step wor…
MetaGPT
Multi-agent framework where AI agents role-play as engineers, PMs, and QA to collectively produce software from a singl…
n8n
Open-source workflow automation with AI agent capabilities — build complex multi-step automations with 400+ integration…
Nango
Open-source OAuth and API integration platform. 300+ pre-built integrations. Handles token refresh, rate limits, and we…
Notion Workers
Hosts custom code Workers in a secure sandbox and connects external AI agents like Claude and Codex into Notion workspa…
Ollama
Run LLMs locally — Llama, Mistral, Gemma, DeepSeek, and 100+ models via CLI and REST API. OpenAI-compatible endpoint at…
Open WebUI
Self-hosted AI platform with OpenAI-compatible REST API, MCP support, and a pipelines SDK. Supports Ollama, OpenAI, Ant…
OpenAI Agents SDK
Python framework for building multi-agent systems with handoffs, guardrails, and tool use — the official OpenAI agent o…
PagerDuty AIOps
Intelligent incident management with AI-powered event correlation, noise reduction, and automated incident response.
Pulumi AI
Infrastructure as code with AI — generate cloud infrastructure definitions from natural language using Pulumi's multi-l…
Pydantic AI
Type-safe Python agent framework from the Pydantic team. Built-in MCP client, ships a sandboxed Python execution MCP se…
RAGFlow
Open-source RAG engine with deep document parsing (tables, charts, images) and an official MCP server. Deploy via Docke…
Replicate
Run open-source AI models in the cloud — image generation, language models, video, audio via simple API calls.
Sangria
Payment SDK letting merchants accept on-chain payments from AI agents. TypeScript and Python SDKs return HTTP 402 until…
Sentry AI
Error monitoring with AI-powered issue grouping, root cause analysis, and automated fix suggestions for production appl…
SentryWatch Monitor
Error monitoring and alerting agent that watches your services and delivers real-time incident summaries.
Terraform MCP
Official HashiCorp MCP server connecting AI assistants to Terraform Registry APIs for live provider docs, module search…
Twilio ConversationRelay
Real-time voice AI framework connecting LLMs to phone calls — build conversational AI agents over Twilio's voice infras…
Vertex AI Agent Builder
Google Cloud's platform for building AI agents with grounding, tool use, and multi-turn conversation — supports A2A pro…
VirtualSMS
SMS verification API with real SIM-backed numbers for AI agents. Buy numbers, fetch OTPs, check balance via REST or MCP…
vLLM
High-throughput LLM inference server with OpenAI-compatible API. Serves Llama, Mistral, Qwen, and 30+ model families wi…
WSO2 Agent Manager
Governs, secures, and scales enterprise AI agents across frameworks with zero-trust runtime, OpenTelemetry observabilit…