Agent Frameworks

Intelligent memory layer for AI agents and assistants

Mem0 is an open-source intelligent memory layer for AI agents with 51K+ GitHub stars providing persistent, adaptive memory across sessions. It manages working, short-term, and long-term memory types, enabling personalized AI experiences that improve over time. Features automatic memory extraction from conversations, semantic search over stored memories, multi-format support, and integration with 100+ frameworks. Simple API for adding memory to any LLM-powered application or agent.

Official Chrome DevTools MCP server for coding agents

chrome-devtools-mcp is the Chrome DevTools team's official MCP server that lets coding agents control and inspect a live Chrome browser with first-party Chrome DevTools Protocol fidelity. It exposes Network inspection, Performance traces, Lighthouse audits, console output, and structured DOM snapshots as typed MCP tools, so agents can debug real pages and ship reliable web performance investigations without resorting to brittle DOM scraping.

Secure cloud sandboxes for AI agents

E2B provides secure cloud sandboxes that let AI agents execute code, run terminal commands, and interact with filesystems in isolated environments. Each sandbox spins up in ~150ms with its own OS, giving agents a safe space to run untrusted code. Supports Python, JavaScript, and any language via custom Dockerfiles. Used by AI coding assistants, data analysis agents, and code interpreters. SDK available for Python and JavaScript with a simple API for programmatic sandbox control.

Data framework for LLM applications

Leading Python framework for building LLM-powered applications with focus on data-aware and agentic workflows. Provides tools for RAG (Retrieval-Augmented Generation), document indexing, vector store integrations, query engines, and multi-agent orchestration. 150+ data connectors for various sources. Works with OpenAI, Anthropic, local models, and more. Includes LlamaHub for community tools and LlamaCloud for managed RAG pipelines. 50K+ GitHub stars.

Memory engine and context API for AI assistants

Supermemory is a memory and context platform for AI assistants and agents. It ranks #1 on LongMemEval, LoCoMo, and ConvoMem, supports MCP for Claude/Cursor-style clients, provides plugins for developer tools, and combines memory extraction, user profiles, hybrid search, connectors, and RAG in one API.

Build AI-powered web apps

Open-source TypeScript toolkit by Vercel for building AI-powered apps with streaming chat UIs, structured outputs, tool calling, and agent workflows. Framework-agnostic core with integrations for React, Next.js, Svelte, Vue, and Nuxt. Supports a broad AI SDK v6 provider catalog including OpenAI, Anthropic, Google, xAI, Mistral, Bedrock, Groq, and OpenAI-compatible providers. Includes useChat and useCompletion hooks for rapid UI development. The standard SDK for adding AI features to web apps.

Open-source sandboxes and SDKs for AI agents that control desktops

Open-source computer-use infrastructure for agents that need to drive desktop environments in the background. CUA includes Cua Driver, Sandbox, Run, Bench, and Verified Data across Linux, Windows, macOS, and Android, with MCP and CLI surfaces for screenshots, accessibility trees, keyboard/mouse actions, shell commands, task evaluation, and fleet execution.

Stateful agent orchestration framework by LangChain

LangGraph is LangChain's framework for building stateful, multi-actor AI agent applications as controllable graphs. It models workflows as nodes and edges, enabling cycles, branching, and human-in-the-loop patterns that simple chains cannot express. Features built-in persistence for conversation memory, streaming support, and fault tolerance. Provides fine-grained control over execution flow while supporting single-agent and multi-agent architectures with shared or independent state.

TypeScript AI agent framework

TypeScript-native framework for building AI agents and workflows with great developer experience. Provides primitives for agents with tool calling, RAG pipelines, workflow orchestration with branching/parallel steps, and integration connectors. First-class TypeScript support with type-safe tool definitions. Local dev server with playground UI for testing. Growing as a LangChain alternative for TypeScript developers building AI apps.

Command center for Claude Code and Codex — monitor, steer, and voice-control your AI agents from any device.

Omnara is a command center for Claude Code and Codex sessions across desktop, web, mobile, and Apple Watch. Its public site supports cross-device supervision, parallel agents, worktrees, Git, and session-continuity language, with free-offer metadata; teams should verify detailed pricing, relay, privacy, and enterprise controls before standardizing it.

Official Python SDK for OpenAI agents

OpenAI's Python framework for building multi-agent AI applications with GPT models. Provides primitives for creating agents with tool calling, handoffs between specialized agents, guardrails for input/output validation, and tracing for observability. Supports building complex workflows where agents collaborate on tasks. Includes built-in tools for file search, code execution, and web browsing. Designed for production agent systems with structured output and error recovery patterns.

Workflow automation with AI nodes

n8n is a source-available workflow automation platform for connecting apps, APIs, data, and AI models through visual workflows and code. It supports self-hosted deployments and n8n Cloud, with integrations across communication, databases, CRM, project management, and model providers. Teams can combine deterministic automation with AI-powered steps and agent workflows while retaining control over deployment and data.

AI agent framework for web browser automation

Browser Use is an open-source AI agent framework with 99K+ GitHub stars enabling LLMs to control web browsers via natural language. Y Combinator-backed, it lets agents navigate sites, fill forms, extract data, and complete multi-step tasks autonomously. Built on Playwright with vision-based element detection, multi-tab management, cookie persistence, and self-correcting actions. Supports OpenAI, Anthropic, and local models with a simple Python API for building custom browser agents.

Python agent framework by Pydantic team

Agent framework built on Pydantic for type-safe AI applications. Provides structured outputs, dependency injection, and multi-model support. Created by the Pydantic team, it brings the same validation and typing philosophy that made Pydantic essential for Python APIs to the world of AI agents, ensuring reliable data flow between LLMs and application logic.

AI-powered web browser automation with Playwright

Stagehand is an open-source browser-agent SDK from Browserbase that combines deterministic browser automation with AI primitives such as act(), extract(), observe(), and agent(). Instead of relying only on brittle selectors, developers can use natural-language actions, Zod-backed structured extraction, page observation, action caching, and Browserbase cloud-browser infrastructure for production web automation.

Microsoft’s public-preview runtime governance toolkit for policy, identity, sandboxing, audit, and MCP security around AI agents.

Agent Governance Toolkit is Microsoft’s MIT-licensed public-preview toolkit for governing AI agent runtimes. It adds policy enforcement, zero-trust identity, execution sandboxing, audit, reliability, and MCP security-gateway patterns around tool calls and autonomous actions, helping platform teams move beyond prompt-only guardrails while preserving architecture review requirements.

Headless browser cloud built for AI agents

Browserbase is cloud infrastructure that runs headless Chromium browsers on demand for AI agents and automation workflows, exposing Playwright, Puppeteer, and Selenium endpoints with built-in session replay, residential proxies, CAPTCHA solving, and stealth fingerprints. It also hosts Stagehand and a Model Gateway, letting teams build browser-using agents without maintaining their own fleet of Kubernetes-managed Chromium instances.

Codebase knowledge graph MCP server for AI coding agents

Codebase Memory MCP is an MIT-licensed MCP server that turns a repository into a persistent code knowledge graph for AI coding agents. It gives Claude Code, Cursor, Codex-style agents, and other MCP clients structural queries for functions, classes, call chains, routes, and architecture, helping them explore large projects without repeatedly rereading files or relying only on broad search.

AI IDE and collaboration platform for BYOK coding agents

HumanLayer is an AI IDE and collaboration platform for software-factory workflows with coding agents. Current positioning emphasizes tasks, artifacts, worktrees, multi-agent sessions, and BYOK Claude/Codex/API subscriptions rather than only human approval gates. Treat public code and product terms separately when evaluating open-source claims.

Always-on cloud engineer that lives in Slack and ships verified PRs

Roomote is a Slack-first cloud coding agent from RooCodeInc that takes prompts end-to-end across GitHub, Linear, Notion, Sentry, and your own dev environment, then opens self-verified pull requests for review. It is the team behind 24K+ star Roo Code going all-in on cloud agents: mention it in Slack, let it run in an isolated environment, and review the PR through your normal GitHub flow.

Build and deploy AI chatbots and agents visually

Botpress is a conversational AI platform founded in 2017 that combines a visual Agent Studio with LLM-native architecture for building chatbots and autonomous agents. It offers a drag-and-drop flow builder, knowledge base indexing from documents and websites, an Autonomous Engine for generative AI workflows, and deployment across web chat, WhatsApp, Telegram, Slack, and other channels. Botpress runs as a cloud SaaS or self-hosted via Docker with pricing starting at $0/month pay-as-you-go.

Source-available LLM app development platform

Source-available LLM application development platform combining a visual no-code canvas with backend capabilities for building AI workflows, RAG pipelines, and agent systems from prototype to production. Integrates hundreds of models from dozens of providers, with PDF/PPT ingestion, ReAct agents with 50+ tool integrations, and multi-step orchestration. Used by both technical and non-technical teams to ship GenAI apps like chatbots and Q&A systems.

Context compression for LLM apps and coding agents

Headroom is an Apache-2.0 context compression layer for LLM apps and coding agents. It compresses tool output, logs, files, RAG chunks, and agent history through a local library, proxy, wrapper, or MCP server, with retrieval hooks for bringing originals back when needed. Treat its savings numbers as Headroom-reported benchmarks, not independent aicoolies measurements.

Knowledge graph-powered RAG framework from HKU

LightRAG is a research-backed RAG framework from Hong Kong University that combines knowledge graph structures with vector search for more contextual retrieval. Published at EMNLP 2025, it extracts entities and relationships from documents to build a structured knowledge graph, then uses dual-level retrieval across both graph and vector representations with five query modes: naive, local, global, hybrid, and mix.

MCP, ACP and Skills support for building production coding agents — interactive or automated.

fast-agent is an Apache-licensed Python framework for building and running LLM agents with full MCP (Model Context Protocol) and ACP support. It ships with an interactive shell mode, Skills management, and multi-model routing — making it a practical platform for coding agents, workflow automation, and agent evaluation across Claude, Codex, HuggingFace, and local models.

Lightweight multi-modal agent framework

Fast, lightweight Python framework for building multi-modal AI agents, formerly known as Phidata. Includes built-in memory, knowledge bases, tools, and reasoning capabilities with 40K+ GitHub stars. Designed for developers who want to build production-ready agents quickly with minimal boilerplate, supporting structured outputs and multi-agent coordination out of the box.

Rust-native multi-agent orchestration for production

GraphBit is a Rust-native, multi-agent orchestration framework built for production. It targets the gap between Python-first frameworks like LangGraph and the operational expectations of enterprise systems — predictable memory, low latency, deterministic concurrency, and the ability to embed an agent runtime in services that already run Rust without dragging in a Python interpreter.

Production-grade browser automation with AI self-healing and Playwright code ownership

Intuned is a code-first browser automation platform that turns natural language prompts into production-ready Playwright code, deploys it, and self-heals it when target sites change. Supports TypeScript and Python with Anthropic Computer Use, OpenAI CUA, Stagehand, Browser-Use, and Gemini Computer Use integrations. Built-in stealth, captcha solving, auth session management, and scheduled runs with concurrency control. No vendor lock-in—you own the code.

Framework for LLM applications

The most widely-used framework for building LLM-powered applications, available in Python and JavaScript. Provides abstractions for chains, agents, RAG, memory, tool usage, and structured output. Integrates with 100+ LLM providers, vector stores, document loaders, and tools. LangSmith offers tracing and evaluation. LangGraph enables stateful, multi-agent workflows with cycles. 100K+ GitHub stars. The de facto standard for LLM application development despite growing alternatives like LlamaIndex.

Open-source personal AI agent for messaging apps

OpenClaw is a free, open-source AI agent framework that turns any LLM into an autonomous personal assistant accessible through messaging apps like WhatsApp, Telegram, Discord, and Signal. Running entirely on your local machine via a Node.js gateway, it connects AI models to system tools, browsers, files, and APIs for multi-step task execution with persistent memory across sessions.

Alibaba's agent framework built for the Qwen model family

Qwen-Agent is Alibaba's Apache-2.0 framework for building AI agents around the Qwen model family. It supports tool use, planning, memory, RAG, Code Interpreter, Browser Assistant, MCP extras, custom tools, and Qwen Chat backend patterns with Qwen3/Qwen3.5 examples. Best fit for teams standardizing on Qwen rather than a generic multi-agent router, with 16.5K+ GitHub stars.

Microsoft’s pytest-native red teaming framework for turning AI agent safety findings into CI tests.

RAMPART is an open-source Microsoft framework for safety and security testing of agentic AI applications. It brings red-team findings into a pytest-native workflow so teams can turn prompt injection, unsafe tool use, and behavioral boundary failures into repeatable regression tests. The strongest aicoolies angle is developer workflow: RAMPART makes agent safety part of CI/CD instead of a one-off security review.

No-code platform for building AI agent workforces

Relevance AI is a no-code platform from Sydney, Australia for building and deploying AI agent workforces that execute business workflows autonomously. Backed by a $24M Series B led by Bessemer Venture Partners, it offers 9,000+ integrations, a visual agent builder, a marketplace of pre-built agents, and multi-model support across OpenAI, Anthropic, and AWS Bedrock. Agents handle sales development, lead research, meeting prep, onboarding, and support workflows.

Multi-agent AI framework

Python framework for orchestrating autonomous AI agents that collaborate to accomplish complex tasks. Define agents with specific roles, goals, and backstories, then organize them into crews with sequential or parallel task execution. Supports tool usage (web search, file I/O, API calls), memory, delegation between agents, and human-in-the-loop input. Works with OpenAI, Anthropic, local models, and more. 25K+ GitHub stars. Leading multi-agent framework alongside LangGraph and AutoGen.

Open-source observability for AI agents

Laminar is an open-source observability platform for AI agents providing tracing, evaluation, and analytics for LLM applications. It integrates with Vercel AI SDK, LangChain, OpenAI, and Anthropic with a single line of code. Features include OpenTelemetry-native SDKs, an extensible evaluation framework with CI/CD support, SQL access to traces and metrics, and a visual debugging timeline for agent reasoning and actions.

The LLM anti-framework for typed AI apps

Mirascope is an open-source Python and TypeScript toolkit for building LLM applications that prioritizes type safety, composability, and 100% test coverage. Positioned as the 'anti-framework,' it provides fine-grained control over LLM interactions using familiar language constructs rather than rigid abstractions, supporting all major providers through a unified interface.

Microsoft's conversational multi-agent framework

AutoGen is an open-source programming framework from Microsoft Research for building AI agents and facilitating cooperation among multiple agents to solve complex tasks through multi-turn conversations. Pioneered conversable agents that interact, use tools, and involve humans in the loop for multi-agent workflows. v0.4 features a redesigned async event-driven architecture with stronger observability, flexible collaboration patterns, and reusable components.

Self-evolution engine for AI agents with auditable updates

Evolver is an open-source self-evolution engine for AI agents that turns run logs into auditable, reviewable updates via its Genome Evolution Protocol. Instead of ad hoc prompt tweaking, teams collect traces and Evolver proposes versioned diffs to prompts, tools and workflows that engineers can approve, reject or roll back like code.

Sandboxes for coding agents — Linux VMs, Git, and deploys in one box

Freestyle is YC-backed sandbox infrastructure built for AI coding agents, shipping secure Linux VMs with nested virtualization, Git servers, and one-click web deploys. It lets agents run real workloads, branch repos, and deploy apps under short-lived identities while billing only for active compute. Used in production by vly.ai, Rork, and Vibeflow.

Browser automation with AI vision — no XPath or DOM parsing needed

Skyvern automates browser-based workflows using LLMs and computer vision instead of brittle XPath or CSS selectors. It understands web pages visually, navigating forms, clicking buttons, and extracting data like a human would. Achieved 85.85% success rate on WebVoyager benchmark and SOTA on WRITE tasks for RPA. 21,000+ GitHub stars, AGPL-3.0 licensed. Skyvern Cloud offers managed usage-based hosting for teams that prefer not to self-host the infrastructure.

Drag-and-drop LLM flow builder

Open-source protocol for connecting AI models to external tools and data sources, created by Anthropic. Provides a standardized way for LLMs to interact with APIs, databases, and local files through a universal client-server architecture. Rapidly adopted across the AI ecosystem as the standard interface between AI assistants and the tools they need to be useful.

Self-evolving local computer agent with a reusable skill tree

GenericAgent is a minimal, self-evolving autonomous agent from a 3.3K-line seed and ~3K core loop that gives LLMs system-level control of a local computer. It writes files, runs shell commands, browses the web, and uses keyboard/mouse/screen/mobile tools, while skill crystallization saves successful runs into a reusable skill tree that cuts token cost on repeats.

Kubernetes-native framework for DevOps AI agents

kagent is a Kubernetes-native AI agent framework developed at Solo.io and accepted into the CNCF sandbox. It provides a structured environment for running DevOps-focused agents directly within Kubernetes clusters, with a dedicated kmcp toolkit for cloud-native operations. Unlike general-purpose agent frameworks, kagent targets platform engineers and SREs who need AI assistance with cluster management, troubleshooting, and infrastructure automation workflows.

Open-source toolkit for building AI SRE incident response agents

OpenSRE is Tracer Cloud’s open-source public-alpha Python toolkit for building AI SRE agents that investigate and respond to production incidents. It ships 60+ tools across observability, databases, incident management, communications, deployment and protocol integrations, plus simulation/evaluation workflows for benchmarking agent accuracy before live pager use.

OpenAI's autonomous coding agent orchestration framework

Symphony is OpenAI's open-source framework that turns project work into isolated, autonomous implementation runs. Instead of supervising coding agents line by line, teams assign tasks from project boards and Symphony dispatches agents to handle them independently. Each agent works in an isolated workspace, provides proof of work documentation including CI status and PR review feedback, and can automatically merge approved pull requests.

Next-gen multi-agent framework (AutoGen fork)

AG2 (formerly AutoGen) is an open-source multi-agent AI framework that emerged as a community-driven fork of Microsoft AutoGen, founded by original creators Chi Wang and Qingyun Wu after leaving Microsoft. Licensed Apache 2.0 under open governance, it provides an AgentOS for multi-agent conversations, tool use with any LLM, human-in-the-loop workflows, group chat orchestration, and teachable agents. AG2 Beta adds streaming, event-driven production architecture.

Autonomous scientific discovery via agentic tree search

AI Scientist v2 is Sakana AI's source-available system distributed under the AI Scientist Source Code License for fully autonomous scientific research using LLM-powered agentic tree search. It generates hypotheses, designs experiments, writes and executes code, analyzes results, and produces publishable manuscripts without human intervention. The system uses progressive exploration with backtracking to navigate the research space efficiently.

Open-source desktop AI coworker for browsing and code execution.

Accomplish Coworker is an MIT-licensed open-source AI coworker that runs on the desktop, combining computer-use style browsing with code execution so agents can research, implement, run, and debug workflows in one local environment.