Agent Frameworks

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.

Multi-agent coordination framework

A framework for coordinating multiple AI agents working together on complex development tasks. Defines agent roles, communication patterns, task delegation strategies, and inter-agent workflows to break down large projects into manageable, parallel workstreams handled by specialized agents. Ideal for teams experimenting with multi-agent architectures where different AI models handle distinct aspects of software development.

Microsoft's zero-code-change RL trainer for AI agents

Agent Lightning is Microsoft Research's open-source framework that makes AI agents trainable through reinforcement learning with virtually zero code changes. Supports RL, Automatic Prompt Optimization, and Supervised Fine-tuning across any agent framework including LangChain, OpenAI Agents SDK, AutoGen, and CrewAI. 14K+ GitHub stars, ranked among Microsoft's top 50 most-starred projects.

Transparent AI agent framework with 100+ skills and real-time visibility

Agent Zero is an open-source general-purpose AI agent framework with 16,700+ GitHub stars that uses the computer itself as a tool. Unlike structured orchestration frameworks, it provides full transparency where every thought, action, and tool call is visible and editable in real time, supporting 100+ extensible skills.

Browser-based autonomous AI agent platform

AgentGPT is an open-source browser-based platform with 36K+ GitHub stars for creating and deploying autonomous AI agents without any setup or installation. Give an agent a name and goal in plain language, and it autonomously decomposes the objective into subtasks, executes them, and iterates toward completion. Built with Next.js and supports multiple LLM providers. Features include web search, code execution, and task chaining. No technical expertise required to create functional AI agents.

Production-ready multi-agent platform by Alibaba

AgentScope is an open-source multi-agent platform with 22K+ GitHub stars developed by Alibaba. Designed for production-ready multi-agent applications with built-in distributed execution, fault tolerance, and agent-to-agent messaging. Features memory management with compression, a drag-and-drop workstation for visual agent building, multi-modal support, and flexible pipelines for sequential, parallel, and conditional agent orchestration. Supports all major LLM providers.

TypeScript AI agent standard library

Standard library of AI tools and integrations for TypeScript-based agents. Works with any AI SDK and includes ready-made integrations for search, web scraping, email, and other common tool patterns. Saves developers from rebuilding common agent capabilities from scratch, providing well-tested, type-safe building blocks for rapid AI agent development.

Non-agent approach to automated software engineering via localize-and-repair

Agentless takes a deliberate non-agent approach to LLM-powered software engineering. Instead of autonomous agents making tool calls, it uses a structured localize-then-repair pipeline: first narrowing down which files and functions are relevant, then generating targeted patches. Achieved competitive SWE-Bench results at $0.34 average cost per issue. Adopted by OpenAI for o3 evaluations. 3,000+ GitHub stars, MIT licensed. A counterpoint to the agent-heavy trend in AI coding tools.

Local-first auditable AI agent workspace and append-only runtime

Apache Maka is an open-source, local-first AI agent workspace under the Apache Software Foundation that uses an append-only event log to record model messages, tool calls, and permissions for deterministic session replay and auditability.

AI agent that builds other AI agents

Archon is an open-source AI meta-agent created by Cole Medin that autonomously builds, refines, and optimizes other AI agents. Now evolving into Archon OS, it serves as a knowledge and task management backbone for AI coding assistants. The system uses an agentic coding workflow with framework knowledge bases for Pydantic AI, LangGraph, and other agent frameworks, enabling developers to describe what they need and let Archon generate the agent code, test it, and iterate until it works.

Agentic IM chatbot platform with multi-platform LLM integration

AstrBot is an open-source agentic chatbot infrastructure that connects multiple instant messaging platforms including Telegram, Discord, Slack, WeChat, QQ, Feishu, and DingTalk to AI language models. It supports multi-provider LLM integration, MCP protocol, knowledge bases, persona management, multimodal input, and a plugin ecosystem with over 1,000 community extensions. Features include a web management UI, sandbox code execution, and auto-context compression for efficient conversations.

Build AI agents like LEGO — modular and predictable

Atomic Agents is a lightweight Python framework by BrainBlend AI that applies Atomic Design principles to AI agent development. Each component — agents, tools, context providers — is a single-purpose, reusable building block with Pydantic-enforced input/output schemas for type safety. Built on Instructor for structured LLM outputs, it prioritizes predictability and developer control over the autonomous-but-unpredictable behavior of larger frameworks like LangChain or CrewAI.

Open-source autonomous AI agent platform

AutoGPT is an open-source autonomous AI agent platform with 183K+ GitHub stars that breaks goals into subtasks and executes them independently. Features a visual Agent Builder for creating workflows without coding, persistent cloud-based agents running on triggers, a marketplace of pre-built agents, and a plugin system. Agents can browse the web, write code, manage files, and call tools autonomously while maintaining memory across sessions.

AI agents running automated research

Autonomous research framework by Andrej Karpathy that lets AI agents plan and execute machine learning experiments end-to-end. Agents design experiments, run training loops, analyze results, and iterate on hypotheses with minimal human oversight. Runs efficiently on single-GPU setups and applies agentic patterns beyond software development — bringing autonomous agent workflows to the research process itself.

Type-safe LLM function builder

BAML is a domain-specific language by BoundaryML for building reliable AI workflows and agents through schema engineering. It turns prompt engineering into a structured, type-safe discipline by letting developers declaratively define function schemas, validate LLM responses, and version prompts without fragile JSON parsing or boilerplate. BAML reframes prompt engineering as schema definition, making AI workflows testable and maintainable across models.

Python and TypeScript framework for production multi-agent systems

BeeAI Framework is an Apache-2.0 toolkit for building production-ready AI agents and multi-agent systems in Python and TypeScript. Its docs cover agents, tools, RAG, memory, workflows, backend providers, serving, and A2A/MCP integration surfaces, making it a vendor-neutral option for teams comparing LangGraph, CrewAI, Mastra, and related agent runtimes.

Open-source agentic browser that runs local AI agents in your browsing workflow.

BrowserOS is a privacy-first, open-source agentic browser for running AI assistants locally inside real browsing sessions instead of handing every task to a remote cloud browser.

State machine framework for AI agent tracking

Burr is an open-source Python framework for building applications as state machines with built-in observability and persistence. Designed for AI agents, chatbots, and RAG pipelines where tracking state transitions, debugging decisions, and replaying execution is critical. Features automatic state persistence, a visual UI for inspecting execution flows, time-travel debugging, and integration with LangChain, OpenAI, and any Python code. Apache 2.0 licensed by DAGWorks.

Multi-agent framework for finding scaling laws of agents

CAMEL-AI is an open-source multi-agent framework with 16,500+ GitHub stars, built by a research community of over 100 researchers focused on finding the scaling laws of agents. It supports role-playing agent societies, synthetic data generation pipelines, large-scale social simulations with up to 1M agents via the OASIS platform, and real-world task automation through the OWL project accepted at NeurIPS 2025. CAMEL works with OpenAI, Anthropic, Gemini, Mistral, and local models.

Multi-agent software company simulation for automated development

ChatDev simulates an entire virtual software company through multi-agent collaboration where LLM-powered roles including CEO, CTO, programmer, tester, and designer work together to produce complete software. With 32,000+ GitHub stars and a NeurIPS 2025 accepted paper, it offers a novel approach to automated software development through role-based agent orchestration.

Official agent SDK by Anthropic

Anthropic's Python SDK for building agentic AI applications powered by Claude models. Provides primitives for creating agents with tool use, multi-step reasoning, guardrails, handoffs between specialized agents, and structured output. Supports building complex agent workflows with tracing and observability. Designed for developers building production AI agents that interact with external systems, databases, and APIs using Claude as the reasoning backbone.

AI-powered task management for agentic coding workflows

Claude Task Master is an AI-powered task management system designed for agentic development workflows in IDEs like Cursor, Windsurf, Lovable, and Roo. It breaks complex projects into structured task trees with dependencies, priorities, and complexity scores so AI coding agents can execute work methodically. The MCP server integration enables direct task operations from any compatible client, while tagged task lists support multi-context management across branches and environments.

Build and deploy AI agents on Cloudflare's edge network

Cloudflare Agents is an open-source SDK for building and deploying AI agents that run on Cloudflare's global edge network. It provides durable state, scheduled tasks, WebSocket communication, and browser rendering capabilities within Workers. Agents persist across requests using Durable Objects and can orchestrate multi-step workflows with built-in MCP server support. Over 7,000 GitHub stars.

Open computer-use platform for browser, terminal, and full desktop automation

Coasty is an open-source computer-use platform for teams that want AI agents to operate across browser, terminal, and full desktop surfaces instead of only clicking DOM nodes. The project combines planner/orchestrator logic, visual and input control, local Electron workflows, remote sandbox options, an MCP server, and logs for debugging long-running automations. It is a strong fit for QA, research-to-action, form workflows, and repetitive desktop tasks where browser-only agents are too narrow.

Knowledge graph memory engine for AI agents

Cognee is an open-source knowledge engine that builds persistent memory for AI agents by combining vector search with graph databases. It ingests data from 38+ source formats, structures information into a knowledge graph with embeddings, and enables semantic and relational queries through its ECL pipeline. Its cognitive science-inspired architecture provides superior cross-document entity identification compared to traditional RAG approaches.

Workflow orchestration engine

Netflix-originated workflow orchestration platform with JSON and code-based workflow definitions, human-in-the-loop support, and AI agent orchestration capabilities. With 18k+ GitHub stars, Conductor handles complex distributed workflows at massive scale, offering built-in retry logic, event-driven triggers, and visual workflow monitoring for microservice coordination.

Full-stack framework for building AI copilots with generative UI

CopilotKit is an open-source full-stack framework for building AI-native applications with generative user interfaces. It provides React and Angular SDKs that enable agents to dynamically generate and render UI components, synchronize state between frontend and backend in real time, and implement human-in-the-loop workflows. Supports integration with LangChain, LangGraph, CrewAI and protocols including AG-UI, MCP, and A2A for standardized agent interaction.

Full-lifecycle AI agent optimization and monitoring

CozeLoop is an open-source AI agent optimization platform from ByteDance's Coze ecosystem providing full-lifecycle management from development to production monitoring. It enables developers to debug agent prompts, evaluate agent performance across test cases, optimize reasoning processes, and monitor deployed agents in real-time. Built on Go and React with SDKs for Go, Python, and Node.js, CozeLoop is designed for enterprise-grade AI agent development and operation.

The 5MB open-source agent daemon that hides nothing

CrabTalk is a lightweight five-megabyte daemon that streams every AI agent event to your client in real time including text deltas, tool calls, and thinking steps. It provides complete transparency into agent operations with one-curl installation and bring-your-own-model support. Designed as the observable alternative to opaque agent runtimes where you cannot see what the AI is actually doing.

Programming — not prompting — LLMs

Declarative framework from Stanford University for programming language models rather than prompting them. DSPy treats LLM interactions as programmable modules with input-output signatures and uses optimization algorithms to automatically compile these modules into effective prompts or fine-tuned weights, replacing brittle prompt strings with structured, modular AI software.

LangChain-powered agent harness with planning and subagents

Deep Agents is a production-ready agent framework built on LangChain and LangGraph for complex agentic workflows. It features a planning system for task decomposition, a filesystem backend for persistent operations, sandboxed shell execution, and isolated subagents with independent context windows. Automatic context summarization keeps agents coherent across long sessions, while smart defaults simplify prompt engineering for multi-step autonomous tasks.

ByteDance's open-source agentic workflow platform

DeerFlow is ByteDance's open-source agentic workflow platform that combines LLM-powered agents with deep research capabilities. It features multi-agent orchestration, web research automation, report generation, and podcast creation from research outputs. Built with LangGraph, it supports configurable LLM backends and provides a modern React-based UI for managing complex AI-driven research and content workflows.

Open-source voice AI platform with visual builder and MCP integration

Dograh is an open-source voice AI platform and visual workflow builder. It enables teams to build self-hosted conversational agents, plug in BYOK models and speech engines, connect telephony providers, and orchestrate tools via Model Context Protocol.

Prompt engineering framework treating prompts as versioned Python functions

Ell is a prompt engineering library that treats LLM prompts as versioned, testable Python functions rather than opaque strings. Built by ex-OpenAI researcher William Guss, it provides automatic prompt versioning with content-addressable hashing, a local TensorBoard-like studio for visualizing prompt evolution, and structured output support via Pydantic. 5,800+ GitHub stars, MIT licensed. Designed for teams who want to version-control and systematically improve their prompts over time.

MCP gateway and integration catalog for AI agents

Executor is an MIT-licensed integration layer and MCP gateway for AI agents. It gives Claude Code, Cursor, Codex, and other MCP-speaking clients one endpoint for connected OpenAPI specs, GraphQL APIs, MCP servers, Google Discovery sources, and custom JavaScript tools, with local, cloud, and self-hosted deployment options for teams centralizing tool access.

Visual workflow builder by ByteDance

FlowGram is an open-source visual workflow and flowchart editor framework developed by ByteDance for building node-based workflow applications. It provides a React-based canvas with drag-and-drop node creation, configurable edge routing, zoom and pan controls, and a plugin architecture for extending functionality. FlowGram supports both fixed layout and free-form canvas modes, making it suitable for building AI agent pipelines, data processing flows, and automation builders.

Natural language scripting for LLM-system interaction

GPTScript is an Apache 2.0 licensed framework with 3,300+ GitHub stars that enables natural language scripting where LLMs interact with local systems, APIs, and tools through simple prompt definitions. It supports multiple model providers including OpenAI-compatible APIs and local models, providing a lightweight approach to building AI agents that can execute CLI commands, call APIs, and process files.

Agent Development Kit by Google

Google's open-source framework for building AI agents with Gemini models. Supports multi-agent orchestration, tool use, and deployment to Vertex AI or Cloud Run. Provides a structured approach to agent development with built-in evaluation, testing, and monitoring capabilities, making it the official path for teams building agent systems within the Google Cloud ecosystem.

Modular AI agent framework with off-prompt data

Griptape is an open-source Python framework for building AI agents and workflows with a focus on modularity and enterprise-grade off-prompt data handling. It separates predictable pipeline logic from unpredictable LLM interactions, providing structures for sequential and parallel task execution with built-in memory management and tool integration.

NLP and RAG pipeline framework by deepset

Haystack is an open-source AI orchestration framework by deepset for building production-ready LLM applications with explicit control over retrieval, routing, memory, and generation pipelines. Its component-based architecture lets developers chain specialized pieces into branching, looping pipelines for semantic search, RAG, QA, and autonomous agents. Integrates with OpenAI, Anthropic, Mistral, Cohere, Hugging Face, Azure, AWS Bedrock, and major vector stores.

Agent memory system that learns, not just remembers

Hindsight is an agent memory system that enables AI agents to learn from experience rather than just store conversations. It organizes memories into three biomimetic categories: World knowledge for facts, Experiences for agent events, and Mental Models for learned understanding. The system provides retain, recall, and reflect operations backed by a temporal knowledge graph with parallel retrieval strategies including semantic, keyword, graph traversal, and temporal search.

Open-source natural-language browser automation framework for AI agents

An AGPL-3.0 TypeScript framework that drives a real browser from natural-language tasks — the self-hostable OSS framework from Hyperbrowser, distinct from the vendor's paid cloud browser product.

Turn technical documentation into AI search, RAG, and agents

Technical knowledge and AI agent platform that connects documentation, code repositories, and support platforms into unified search and customer-facing assistants. Features a TypeScript SDK and a no-code visual builder with full two-way synchronization. Delivers citation-backed answers, out-of-the-box MCP server integration, knowledge gap analytics, and seamless embedding across developer portals and help desks.