Stack · Frameworks & Tools
The build layer
The concrete software an agent is assembled from: orchestration frameworks, execution tools + sandboxes, and SDK / observability harnesses. Filter by layer; ranked by GitHub stars (live). ◆ badges trace each into the graph.
All 49Frameworks 16Tools 7Harnesses 35
All software · ranked by GitHub stars Live data
AutoGPT · Significant Gravitas185,000 ★
langchain · LangChain141,250 ★
browser-use · Browser Use103,381 ★
puppeteer · Google95,303 ★
playwright · Microsoft92,403 ★
servers · Anthropic88,181 ★
daytona · Daytona72,266 ★
MetaGPT · FoundationAgents69,300 ★
autogen · Microsoft59,566 ★
crewAI · CrewAI55,116 ★
litellm · BerriAI52,913 ★
LlamaIndex · LlamaIndex, Inc.50,800 ★
llama_index · LlamaIndex50,719 ★
agno · Agno41,044 ★
langgraph · LangChain36,748 ★
DSPy · Stanford NLP36,100 ★
openai-python · OpenAI31,109 ★
langfuse · Langfuse30,655 ★
All software · 49
| Name | Layer | Kind | Stars | What it is | links · src |
|---|---|---|---|---|---|
| langgraph LangChain | Frameworks | DAG / stateful | 36,748 ★ | Build resilient agents. | ↗ |
| crewAI CrewAI | Frameworks | role-based multi-agent | 55,116 ★ | Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers | ↗ |
| autogen Microsoft | Frameworks | conversational multi-agent | 59,566 ★ | A programming framework for agentic AI | ↗ |
| llama_index LlamaIndex | Frameworks | data / event-driven | 50,719 ★ | LlamaIndex is the leading document agent and OCR platform | ↗ |
| langchain LangChain | Frameworks | chains / agents | 141,250 ★ | The agent engineering platform. | ↗ |
| semantic-kernel Microsoft | Frameworks | plugin SDK | 28,282 ★ | Integrate cutting-edge LLM technology quickly and easily into your apps | ↗ |
| haystack deepset | Frameworks | pipeline / RAG | 25,847 ★ | Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modula | ↗ |
| pydantic-ai Pydantic | Frameworks | typed agents | 18,266 ★ | AI Agent Framework, the Pydantic way | ↗ |
| mastra Mastra | Frameworks | TS-native agents | 25,927 ★ | Mastra is the modern TypeScript framework for AI-powered applications and agents. | ↗ |
| adk-python Google | Frameworks | Agent Development Kit | 20,514 ★ | An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibili | ↗ |
| harness-sdk AWS | Frameworks | model-driven agents | 6,468 ★ | Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any | ↗ |
| agno Agno | Frameworks | multi-agent runtime | 41,044 ★ | Build, run, and manage agent platforms. | ↗ |
| GitHub Spec-Kit GitHub | Frameworks | spec-driven workflow | - ★ | Open-source toolkit for spec-driven development with AI: a phase-per-command workflow (constitution → specify → plan → tasks → implement) that writes to a .specify/ folder tree | ↗ |
| Palantir Ontology Agent Stack Palantir Technologies | Frameworks | Ontology-anchored orchestration + governance | Enterprise agent stack anchored in Palantir's Ontology — a governed digital twin of enterprise data, business logic, and compliance rules. Three components: Agent Engine & SDK (concurrency, async, human approvals, fault tolerance in production workflows), Mindkit (fleet management + dynamic agent generation), Agent Studio (visual low-code agent builder). Agents traverse enterprise object links, execute predefined Action Types under the same governance a human user has, and complement LLM reasoning with deterministic simulation/optimisation tools. Exposes ontology primitives through Ontology MCP so external frameworks (ADK, Microsoft Agent Framework, Claude Desktop) can safely read and write the enterprise source of truth. | ↗ | |
| Palantir Ontology SDK (OSDK) Palantir Technologies | Frameworks | Developer SDK · type-safe ontology access | Multi-language toolkit giving developers direct, type-safe access to Foundry's Ontology from their own environment. Auto-generates types and functions for the developer's Ontology subset with IDE autocomplete; supports reading and writing objects, executing Action Types, subscribing to change streams (WebSocket / TypeScript OSDK), and running high-scale queries. Token-scoped access respects the same user permissions the Ontology enforces. Sits beneath the Agent Stack: OSDK is the SDK; Agent Engine, Mindkit and Agent Studio compose on top; Ontology MCP re-exposes the same primitives to external agents. | ↗ | |
| Palantir AIP Logic Palantir Technologies | Frameworks | LLM-authoring surface · Function-backed workflows | Palantir's authoring surface for LLM-powered Functions inside Foundry. Distinct from AIP Agent Studio (which composes multi-turn agents) — AIP Logic focuses on single-turn LLM invocations wrapped as Ontology Functions that Action Types, Agent Studio agents, and OSDK clients can call. Enforces the same governance, permissioning and ontology binding as any other Function-Backed Action, so an LLM step inside a workflow is not a governance escape hatch. Complements deterministic Functions authored in the same surface — the same file can host a regex extractor, an optimisation call, and an LLM reasoning step, all governed identically. | ↗ | |
| E2B E2B | Tools | code sandbox (microVM) | 12,887 ★ | Open-source, secure environment with real-world tools for enterprise-grade agents. | ↗ |
| servers Anthropic | Tools | MCP reference servers | 88,181 ★ | Model Context Protocol Servers | ↗ |
| stagehand Browserbase | Tools | browser automation | 23,416 ★ | The SDK For Browser Agents | ↗ |
| playwright Microsoft | Tools | browser control | 92,403 ★ | Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single A | ↗ |
| puppeteer Google | Tools | browser control | 95,303 ★ | JavaScript API for Chrome and Firefox | ↗ |
| browser-use Browser Use | Tools | browser agent | 103,381 ★ | 🌐 Make websites accessible for AI agents. Automate tasks online with ease. | ↗ |
| daytona Daytona | Tools | dev sandbox | 72,266 ★ | Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code | ↗ |
| openai-agents-python OpenAI | Harnesses | agent SDK | 27,727 ★ | A lightweight, powerful framework for multi-agent workflows | ↗ |
| anthropic-sdk-python Anthropic | Harnesses | SDK (MCP-native) | 3,717 ★ | ↗ | |
| ai Vercel | Harnesses | TS AI SDK | 25,408 ★ | The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-po | ↗ |
| python-genai Google | Harnesses | Gemini SDK | 3,835 ★ | Google Gen AI Python SDK provides an interface for developers to integrate Google's generative models into their Python | ↗ |
| agents Cloudflare | Harnesses | Agents SDK (Workers) | 5,235 ★ | Build and deploy AI Agents on Cloudflare | ↗ |
| openai-python OpenAI | Harnesses | model SDK | 31,109 ★ | The official Python library for the OpenAI API | ↗ |
| litellm BerriAI | Harnesses | model gateway | 52,913 ★ | Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails | ◆ 1↗ |
| phoenix Arize | Harnesses | observability / evals | 10,449 ★ | AI Observability & Evaluation | ↗ |
| helicone Helicone | Harnesses | observability / gateway | 5,920 ★ | 🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓 | ◆ 1↗ |
| openllmetry Traceloop | Harnesses | OTEL observability | 7,280 ★ | Open-source observability for your GenAI or LLM application, based on OpenTelemetry | ↗ |
| langfuse Langfuse | Harnesses | observability / tracing | 30,655 ★ | 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Inte | ◆ 1↗ |
| Claude Agent SDK Anthropic | Harnesses | agent SDK | 7,600 ★ | Build autonomous agents with Claude Code capabilities: read code, edit files, run commands | ↗ |
| Google ADK Google | Harnesses | agent SDK | 20,600 ★ | Code-first toolkit to build, evaluate and deploy agents; model-agnostic, tuned for Gemini/Vertex | ↗ |
| Microsoft Agent Framework Microsoft | Harnesses | agent SDK | 12,100 ★ | Unified SDK and runtime for agents and multi-agent workflows; converges AutoGen + Semantic Kernel | ↗ |
| LlamaIndex LlamaIndex, Inc. | Harnesses | data/agent framework | 50,800 ★ | Data framework for LLM apps over private data; document agents plus event-driven Workflows | ↗ |
| Strands Agents Amazon (AWS) | Harnesses | agent SDK | 6,500 ★ | Model-driven, model-agnostic SDK where the model reasons about which tools to call; OTel tracing | ↗ |
| smolagents Hugging Face | Harnesses | agent SDK (code) | 28,300 ★ | Barebones library whose agents think in code: the CodeAgent writes and runs Python, not tool JSON | ↗ |
| DSPy Stanford NLP | Harnesses | LM programming | 36,100 ★ | Programming, not prompting: declaratively compose and auto-optimise LM pipelines | ↗ |
| Letta Letta | Harnesses | stateful agents (memory) | 23,800 ★ | Platform for stateful agents with long-term memory that learn and self-improve across sessions | ◆ 4↗ |
| Genkit Google | Harnesses | app framework | 6,200 ★ | Framework for AI-powered apps across JS, Go and Python; used in production at Google | ↗ |
| Spring AI Broadcom (Spring) | Harnesses | agent SDK (Java) | 9,100 ★ | Application framework bringing Spring idioms to LLM apps and agents in the Java ecosystem | ↗ |
| AutoGPT Significant Gravitas | Harnesses | autonomous platform | 185,000 ★ | One of the original autonomous-agent projects; now a low-code platform for continuous agents | ↗ |
| MetaGPT FoundationAgents | Harnesses | multi-agent (SOP) | 69,300 ★ | Multi-agent framework assigning SOP-based software-company roles (PM, architect, engineer) | ↗ |
| BeeAI Framework IBM / Linux Foundation | Harnesses | agent framework | 3,300 ★ | Framework for production agents in Python and TypeScript, with tools, RAG and orchestration | ↗ |
| Atomic Agents Eigenwise | Harnesses | agent framework | 6,000 ★ | Schema-driven framework on Instructor + Pydantic composing agents as atomic, LEGO-like blocks | ↗ |
| Julep Julep AI | Harnesses | durable agents | 6,600 ★ | Framework for durable, composable agents: workflows that crash and resume, retry and record steps | ↗ |
Common questions
What is the difference between an agent framework, a tool, and a harness?
A framework handles orchestration: the loop, the branching, the state carried between steps. A tool is something the agent acts through, like a code sandbox or a browser. A harness is the SDK that wraps the model call and records what happened. Most production stacks use one of each.
Which AI agent framework should I choose?
Start from how much control flow you need. LangGraph suits agents with branching, retries and long-running state; lighter libraries like the OpenAI Agents SDK suit straightforward call-and-respond agents. Popularity is not fit, so pick for the shape of your problem. (LangGraph)
Why do agents need a code sandbox?
Because model-generated code can be wrong or hostile, and you do not want it running on your own machine. A sandbox gives it an isolated microVM or container with its own filesystem and restricted network. That boundary is what makes it safe to let an agent execute what it writes.
Are AI agent frameworks open source?
Most of the widely used ones are, under MIT or Apache 2.0, including LangGraph, CrewAI, AutoGen and the OpenAI Agents SDK. A few carry custom terms. Check the LICENSE file before you commit, because the build layer is hard to swap out later.
Do I need a framework to build an AI agent?
No. A loop that calls the model, checks for a tool call, runs it and feeds the result back is about fifty lines of code. A framework earns its place once you need persistence, retries, parallel branches, human approval steps or tracing across many runs.
Next in the learning path