The AI agent stack, curated.

Every serious tool for building, running, and shipping AI agents — frameworks, memory, evals, browser infra, voice, sandboxes, and more. Hand-reviewed, no filler.

55 tools listed
8 categories
Weekly updates

AG2

Open-source multi-agent framework, community continuation of the original AutoGen research project.

Frameworks & Orchestration free open source GitHub ↗

AgentOps

Observability for AI agents with session replays, cost tracking, and integrations for 400+ frameworks and LLMs.

Evals & Observability freemium open source GitHub ↗

AI SDK (Vercel)

Vercel's unified TypeScript SDK for AI apps and agents with streaming and multi-provider model support.

Frameworks & Orchestration free open source GitHub ↗

Anchor Browser

Hosted, human-like Chromium instances that let agents handle logins, forms, and sites without APIs.

Browser & Computer Use freemium

Apify

Marketplace of thousands of ready-made scraping and automation Actors, callable by agents via MCP.

Search & Data APIs freemium

Arcade

MCP runtime handling agent authorization, prebuilt tools, and governance for business systems.

Tool Integrations freemium open source GitHub ↗

Arize Phoenix

Open-source (ELv2) tracing, evaluation, and experimentation platform for agent development from Arize.

Evals & Observability freemium open source GitHub ↗

Bland AI

Enterprise phone-call automation with AI voice agents and bundled per-minute pricing for the full stack.

Voice Agents freemium

Braintrust

Eval and observability platform for AI products: trace production behavior and run quality experiments.

Evals & Observability freemium

Browser Use

Open-source Python library plus hosted agents and browser infrastructure for AI-driven web automation.

Browser & Computer Use freemium open source GitHub ↗

Browserbase

Managed headless browser infrastructure with APIs for agents to navigate, log in, and extract web data.

Browser & Computer Use freemium

Claude Agent SDK

Anthropic's Python/TypeScript library exposing the Claude Code agent loop, tools, and context management.

Frameworks & Orchestration paid GitHub ↗

Cognee

Open-source agent memory that turns documents and context into a queryable knowledge graph.

Memory freemium open source GitHub ↗

Composio

Tool and auth layer giving agents managed OAuth and executable actions across 1,000+ apps.

Tool Integrations freemium open source GitHub ↗

Confident AI

Evaluation and observability platform built on DeepEval, the open-source LLM testing framework.

Evals & Observability freemium open source GitHub ↗

CrewAI

Python framework and enterprise platform for building crews of role-based AI agents that work together.

Frameworks & Orchestration freemium open source GitHub ↗

Daytona

Open-source infrastructure for executing AI-generated code, with sub-90ms sandbox creation and Git support.

Sandboxes & Deployment freemium open source GitHub ↗

E2B

Open-source Firecracker-based sandboxes for safely running LLM-generated code, with sub-200ms startup.

Sandboxes & Deployment freemium open source GitHub ↗

ElevenLabs

AI voice platform with TTS, STT, and cloning, plus conversational agents across phone, chat, and WhatsApp.

Voice Agents freemium

Exa

Web search and contents API built for AI agents, backed by an index of 100B+ documents.

Search & Data APIs freemium

Firecrawl

Open-source web scraping and crawling API that turns websites into clean, LLM-ready data.

Search & Data APIs freemium open source GitHub ↗

Fly.io

Public cloud with fast-booting VMs; its Sprites product runs persistent Linux machines for agent workloads.

Sandboxes & Deployment paid

Galileo

AI evaluation and observability platform that turns offline evals into production guardrails.

Evals & Observability freemium

Google Agent Development Kit (ADK)

Google's open-source kit for building, evaluating, and deploying agents in Python, TypeScript, Go, and Java.

Frameworks & Orchestration free open source GitHub ↗

Haystack

Open-source orchestration framework from deepset for production agents and RAG pipelines.

Frameworks & Orchestration free open source GitHub ↗

Helicone

Open-source AI gateway and observability layer to route, log, and analyze LLM requests.

Evals & Observability freemium open source GitHub ↗

Hyperbrowser

Cloud browser platform positioning itself as web infrastructure for AI agents, with scraping and session APIs.

Browser & Computer Use freemium

Jina AI

Search foundation APIs: URL-to-markdown Reader, web search, embeddings, and rerankers for RAG and agents.

Search & Data APIs freemium open source GitHub ↗

Langfuse

Open-source LLM engineering platform for tracing, prompt management, and evaluations; self-host or cloud.

Evals & Observability freemium open source GitHub ↗

LangGraph

MIT-licensed orchestration library for building stateful, controllable agents as graphs of steps.

Frameworks & Orchestration freemium open source GitHub ↗

LangSmith

LangChain's platform for tracing, evaluating, and monitoring agents, usable with any framework.

Evals & Observability freemium

Letta

Platform for stateful agents with self-editing long-term memory, built by the creators of MemGPT.

Memory freemium open source GitHub ↗

LiveKit

Open-source realtime media stack and Agents framework, with a managed cloud for voice AI in production.

Voice Agents freemium open source GitHub ↗

LlamaIndex

Data framework for agents and RAG over documents, with LlamaCloud for hosted parsing and indexing.

Frameworks & Orchestration freemium open source GitHub ↗

Mastra

TypeScript agent framework with built-in workflows, memory, and observability; Apache-2.0 with a cloud tier.

Frameworks & Orchestration freemium open source GitHub ↗

Mem0

Memory layer that lets agents retain and recall user context across sessions; open source plus hosted API.

Memory freemium open source GitHub ↗

Modal

Serverless cloud for AI workloads: inference, training, and ephemeral sandboxes for untrusted agent code.

Sandboxes & Deployment freemium

Nango

Open-source integration platform connecting products and agents to 900+ APIs, with MCP tool exposure.

Tool Integrations freemium open source GitHub ↗

OpenAI Agents SDK

Lightweight Python library from OpenAI for agents with tools, handoffs, and guardrails; few abstractions.

Frameworks & Orchestration free open source GitHub ↗

Opik

Comet's open-source platform that logs every agent step and automates eval workflows to catch errors.

Evals & Observability freemium open source GitHub ↗

Pipecat

Open-source framework from Daily for building voice and multimodal conversational AI pipelines.

Voice Agents free open source GitHub ↗

Promptfoo

Open-source CLI for testing and red-teaming LLM apps, with a commercial security platform on top.

Evals & Observability freemium open source GitHub ↗

Pydantic AI

Type-safe Python agent framework from the Pydantic team; swap models by changing a string.

Frameworks & Orchestration free open source GitHub ↗

Retell AI

Platform for contact-center voice agents that book appointments, qualify leads, and hand off to humans.

Voice Agents freemium

Runloop

Devboxes: stateful micro-VM environments plus benchmarking and observability for AI coding agents.

Sandboxes & Deployment freemium

Semantic Kernel

Microsoft's open-source SDK for building AI agents and plugins in C#, Python, and Java.

Frameworks & Orchestration free open source GitHub ↗

Serper

Low-cost Google SERP API returning web, news, images, maps, and scholar results as JSON in 1-2 seconds.

Search & Data APIs freemium

Steel

Open-source browser API for running fleets of cloud Chromium sessions behind agent workloads.

Browser & Computer Use freemium open source GitHub ↗

Stripe Agent Toolkit

Stripe's official SDKs, MCP server, and agent skills for adding payments and billing to AI agents.

Tool Integrations free open source GitHub ↗

Supermemory

Memory API for agents with user profiles, vector search, and document ingestion across formats.

Memory freemium open source GitHub ↗

Tavily

Real-time web access API for agents: search, extract, crawl, and research endpoints in one service.

Search & Data APIs freemium

Vapi

Developer platform for building, deploying, and monitoring phone and web voice agents at scale.

Voice Agents freemium

W&B Weave

Weights & Biases toolkit for tracing, evaluating, and monitoring LLM apps and production agents.

Evals & Observability freemium open source GitHub ↗

Zapier MCP

MCP endpoint that lets AI assistants execute real actions across Zapier's 9,000+ connected apps.

Tool Integrations freemium

Zep

Agent memory service built on temporal knowledge graphs for fast retrieval of conversation and business data.

Memory freemium GitHub ↗
Nothing matches that filter. Know a tool we're missing?

Agent Stack Weekly

New tools, launches, and what's actually worth using. No spam.