#1Top pick
Anthropic's coding agent that edits, runs and ships code from your terminal or IDE
Claude Code is a coding agent from Anthropic that reads your codebase, edits files, runs commands and tests, and makes commits from the terminal, IDE, desktop app or browser. You describe the change in plain language and it plans the work, makes it across many files and checks the result. It comes with paid Claude plans rather than as a separate product.
Why it's here
- +Strong at planning and carrying out multi-step changes
- +Runs your tests and tools to check its own work
- +Works in terminal, IDEs, desktop and web
Watch out for
- −No free plan
- −Heavy use pushes you toward the $100+ Max tiers
- −Terminal-first workflow takes adjustment for some users
#2Free option
AI code editor with an agent that makes changes across your whole project
Cursor is an AI code editor, built on VS Code, with an agent that can edit many files, run terminal commands and fix its own errors. It also offers tab completion, chat over your codebase and background agents that work on tasks while you do something else. It has a free plan and paid individual plans that start at $8 a month.
Why it's here
- +Familiar VS Code interface and extensions
- +Choice of models from several providers
- +Fast tab completion alongside the agent
Watch out for
- −Usage-based limits on heavy agent work
- −You review a lot of diffs in the editor
- −Pricing tiers change often
Free · from $8/moTask agent
#3Free option
GitHub's AI pair programmer and coding agent that turns issues into pull requests
GitHub Copilot is an AI coding assistant from GitHub that offers code completion, chat and a coding agent you can assign issues to. The coding agent works in the background and opens a pull request for you to review. A free plan covers completions and chat; the coding agent starts on the $10 Pro plan.
Why it's here
- +Built into GitHub issues and pull requests
- +Works in VS Code, JetBrains, Visual Studio and more
- +Cheapest paid entry among major coding agents
Watch out for
- −Coding agent not on the free plan
- −Best experience assumes GitHub hosting
- −Premium model requests are metered
Free · from $10/moTask agent
#4Free option
OpenAI's coding agent for the terminal, IDE and cloud, included in every ChatGPT plan
OpenAI Codex is a coding agent from OpenAI that writes features, fixes bugs and proposes pull requests, either locally through its open-source CLI and IDE extension or in cloud sandboxes. It is included in every ChatGPT plan, including Free for quick tasks. Paid plans raise the usage limits.
Why it's here
- +Available on the free ChatGPT plan
- +Runs locally or in cloud sandboxes
- +CLI is open source (Apache-2.0)
Watch out for
- −Free and Go limits are tight for daily work
- −Cloud tasks need a GitHub-connected repo
- −Usage limits differ by plan and can be hard to predict
Free · from $8/moTask agent
#5Free option
Autonomous software engineer from Cognition, now with the Devin Desktop editor
Devin is an AI software engineer from Cognition that takes tasks from Slack, Linear or its web app, works in its own cloud environment and opens pull requests. Cognition also offers Devin Desktop, the editor formerly sold as Windsurf, which comes with Devin plans. There is a free tier with a light quota and paid plans from $20 a month.
Why it's here
- +Works on tasks without someone watching
- +Agent plus a desktop editor in one plan
- +Integrates with common team tools
Watch out for
- −Needs well-scoped tickets to do good work
- −Output still needs code review
- −Windsurf users had to move to the Devin Desktop rebrand
Free · from $20/moAutonomous
#6Free option
Open-source coding agent for VS Code that uses any model you bring
Cline is an open-source coding agent that runs inside VS Code and other editors, planning changes, editing files and running commands with your approval at each step. It is free for individual developers; you pay only for the AI model usage, using your own API keys or a provider of your choice. An Enterprise plan adds team controls.
Why it's here
- +Apache-2.0 open source
- +Works with many model providers, including local models
- +Clear plan-then-act flow with approvals
Watch out for
- −Model costs can add up with no cap
- −More setup than a subscription tool
- −Approving each step slows long tasks
#7Free option
Open-source framework for building stateful, controllable agents as graphs
LangGraph is an open-source framework from LangChain for building agents as graphs of steps with state, memory and human-in-the-loop checkpoints. It gives developers fine control over how an agent moves between tools and decisions. It is MIT licensed, with LangSmith available for tracing and deployment.
Why it's here
- +Fine control over agent flow
- +Built-in persistence and human approval steps
- +Large ecosystem and docs
Watch out for
- −More code than higher-level frameworks
- −Concepts take time to learn
- −Best tooling ties into LangSmith
#8Free option
Anthropic's SDK for building agents on the same harness that powers Claude Code
The Claude Agent SDK is an open-source SDK from Anthropic for building agents that use the same tools and agent loop as Claude Code, including file access, command execution, subagents and MCP. It is available for Python and TypeScript. The SDK is MIT licensed; you pay for Claude API usage.
Why it's here
- +Battle-tested agent loop from Claude Code
- +Built-in tools and MCP support
- +Python and TypeScript
Watch out for
- −Designed around Claude models
- −API costs for long sessions
- −Less suited to visual, no-code builders
O#9Free option
OpenAI's lightweight open-source SDK for building agents with tools and handoffs
The OpenAI Agents SDK is an open-source framework for building agents that use tools, hand off to other agents and apply guardrails, with tracing built in. It is small and Python-first, with a TypeScript version too. It is MIT licensed and works with OpenAI and other model providers.
Why it's here
- +Few concepts to learn
- +Built-in tracing and guardrails
- +MIT licensed
Watch out for
- −Fewer built-in integrations than LangChain
- −Best experience with OpenAI models
- −Less suited to complex graph workflows
#10Free option
Open-source library and cloud for AI agents that control web browsers
Browser Use is an open-source Python library that lets AI agents operate a web browser, plus a cloud service that runs those browsers for you. Developers use it to automate web tasks on sites without APIs. The library is MIT licensed; the cloud is pay-as-you-go with a $5 minimum top-up.
Why it's here
- +Large open-source community
- +Works with many models
- +Hosted browsers when you need scale
Watch out for
- −Requires coding
- −Websites change and break flows
- −Model and proxy costs add up
#11Free option
Open-source Python framework for teams of role-based AI agents
CrewAI is an open-source Python framework for building multi-agent systems where agents with defined roles work together on tasks. It is known for being quick to start with. CrewAI also runs a hosted platform with a free Basic plan and custom Enterprise pricing.
Why it's here
- +Simple, readable agent definitions
- +MIT licensed
- +Large community and examples
Watch out for
- −Less fine-grained control than LangGraph
- −Multi-agent runs can be costly in tokens
- −Debugging agent hand-offs is hard
#12Free option
Open-source platform for running autonomous coding agents, formerly OpenDevin
OpenHands (formerly OpenDevin) is an open-source platform for AI coding agents that can write code, run commands and browse the web in a sandbox. You can self-host it for free or use the hosted product. A Teams plan adds a managed setup for up to 10 users.
Why it's here
- +MIT licensed and self-hostable
- +Works with many models
- +Runs agents in isolated sandboxes
Watch out for
- −Self-hosting takes DevOps work
- −Hosted Teams plan is expensive for small teams
- −Less polished than commercial IDE agents
#13Free option
Open-source platform for building AI apps, agents and RAG workflows
Dify is an open-source platform for building AI applications, agents and retrieval workflows with a visual editor. You can self-host the Community Edition with Docker or use Dify Cloud. The cloud Sandbox plan is free with 200 message credits and Professional costs $590 per workspace per year.
Why it's here
- +Self-hostable
- +Visual workflow and RAG tools
- +Works with many model providers
Watch out for
- −License has extra conditions beyond Apache-2.0
- −Self-hosting needs maintenance
- −Less suited to non-technical users
Free · from $49/moTask agent
E#14Free option
Voice agents built on ElevenLabs' realistic voices
ElevenLabs Agents is ElevenLabs' platform for building conversational voice agents for phone, web and apps. It uses the company's text-to-speech voices, and extra call minutes cost $0.08 each with LLM usage billed separately. A free plan includes 15 minutes of calls, and BAAs are available on enterprise.
Why it's here
- +Very natural voices
- +Free plan to prototype
- +Same account covers TTS, dubbing and agents
Watch out for
- −LLM costs are extra
- −Burst minutes cost double
- −HIPAA BAA only on enterprise
Free · from $0.08/minAutonomous
#15Free option
Vercel's agent for building React and Next.js apps and UIs from a prompt
v0 is an AI app builder from Vercel that generates React and Next.js interfaces and full apps from text, images or screenshots. It writes production-style code with common component libraries and deploys straight to Vercel. The free plan allows a few messages a day; paid plans start at $30 per user a month.
Why it's here
- +Clean React and Tailwind output
- +Direct deploy to Vercel
- +Accepts images and screenshots as input
Watch out for
- −Tied to the React/Next.js stack
- −Free plan is very limited
- −Backend logic is less mature than the UI
Free · from $30/moTask agent
#16
Developer-friendly platform to build and run AI phone agents
Retell AI is a platform for building AI voice agents that make and take phone calls. Pricing is pay-as-you-go per minute, and every account gets templates, call analytics, simulation testing and API access. It is HIPAA-ready with BAA support, which makes it common for healthcare and other regulated builds.
Why it's here
- +Transparent per-minute pricing
- +20 free concurrent calls
- +HIPAA/BAA support
- +Simulation testing before launch
Watch out for
- −You design the call flow yourself
- −Real cost depends on the LLM and voice you pick
- −Not a done-for-you receptionist
#17
API-first voice agent platform where you pick each model
Vapi is a developer platform for building voice AI agents where you choose the speech-to-text, LLM and voice providers. You pay a hosting fee per minute plus each provider's cost, roughly $82–$129 for 1,000 minutes by Vapi's own estimate. HIPAA-eligible handling is a paid add-on.
Why it's here
- +Mix and match providers
- +Free Vapi telephony and WebRTC
- +Strong API and SDKs
Watch out for
- −Stacked pricing is hard to predict
- −HIPAA costs $2,000/mo extra
- −Requires engineering time
#18
Voice agent platform with all-in per-minute pricing
Bland AI is a platform for building AI phone agents for inbound and outbound calls at scale. Its per-minute rate includes the LLM, speech-to-text and text-to-speech, with no token charges, while telephony is billed separately. Enterprise plans add dedicated infrastructure, on-prem options and a BAA.
Why it's here
- +Model costs bundled into one rate
- +No platform fee to start
- +On-prem/VPC on enterprise
Watch out for
- −Higher per-minute rate than DIY stacks
- −Daily call caps on the free-fee plan
- −BAA only on enterprise
#19Free option
Google's asynchronous coding agent that works on your GitHub repo and opens PRs
Jules is an asynchronous coding agent from Google that clones your GitHub repository into a cloud VM, plans the work and opens a pull request when done. You hand it tasks and come back later rather than pairing with it live. The base tier allows 15 tasks a day; Google AI Pro and Ultra plans raise the limits.
Why it's here
- +Usable without paying
- +Works in the background
- +Shows a plan before it changes code
Watch out for
- −GitHub only
- −Not interactive like an editor agent
- −Plan names and limits have changed several times
#20Free option
AWS's agentic IDE that turns specs into code, with a free tier
Kiro is an agentic code editor from AWS that writes requirements and a design spec before generating code, then carries out the tasks it planned. It also supports hooks that run agents on events like saving a file. A free tier includes 50 credits and paid plans start at $20 a month.
Why it's here
- +Spec-first workflow keeps changes traceable
- +Agent hooks automate routine checks
- +Free tier to try it
Watch out for
- −Spec step feels slow for small fixes
- −Credit-based limits
- −Smaller extension and community ecosystem
Free · from $20/moTask agent
#21Free option
Workflow automation with AI agent nodes, cloud-hosted or self-hosted
n8n is a workflow automation platform with built-in AI agent nodes that connect models to your apps, databases and APIs. You build flows visually, drop into code when needed and run them in n8n's cloud or on your own servers. Cloud plans start at €20 a month billed annually and a self-hosted Community Edition is on GitHub.
Why it's here
- +Self-hosting option
- +Hundreds of integrations plus custom code
- +Flexible AI agent and tool nodes
Watch out for
- −Steeper learning curve than Zapier
- −Self-hosted license is fair-code, not OSI open source
- −Debugging complex flows takes time
#22Free option
Type-safe Python agent framework from the team behind Pydantic
Pydantic AI is an open-source Python framework for building agents with typed inputs, outputs and tools, made by the Pydantic team. It works with many model providers and pairs with Pydantic Logfire for observability. It is MIT licensed.
Why it's here
- +Typed, validated outputs
- +Model-agnostic
- +Feels like normal Python
Watch out for
- −Python only
- −Fewer prebuilt integrations
- −Multi-agent patterns are more manual
#23Free option
TypeScript framework for AI agents, workflows, memory and evals
Mastra is a TypeScript framework for building AI agents, workflows and AI-powered apps, with memory, tools and observability included. It suits JavaScript and TypeScript teams that want to stay in their own stack. The core is Apache-2.0 licensed, with some enterprise features under a separate license.
Why it's here
- +Native TypeScript
- +Workflows, memory and evals in one package
- +Local dev playground
Watch out for
- −Not for Python teams
- −Younger ecosystem
- −Enterprise features under a different license
More developers agents
Listed but not yet reviewed in depth.
AutoGenAutoGen is an open-source programming framework that enables users to develop next-generation LLM applicati…See site
HeliconeHelicone is an open-source platform that facilitates logging, monitoring, and debugging for production-read…See site
HaystackHaystack is a composable open-source AI framework that enables developers to build highly customized AI app…See site
EmbedchainEmbedchain is an Open Source RAG framework designed to load, index, retrieve, and sync any unstructured data.See site
Bit Byte BulletinBit Byte Bulletin is a free learning platform designed to help individuals start their journey in artificia…See site
Virtuals ProtocolVirtuals Protocol empowers individuals to get involved in its ecosystem and earn $VIRTUAL rewards by partic…See site
mymeet.aiMymeet.ai is a powerful tool designed to help professionals streamline their meetings.See site
ImbueImbue is a groundbreaking AI tool that revolutionizes personal computing by introducing advanced, real-worl…See siteSSmol DeveloperSmol Developer introduces an ingenious AI tool that acts as your very own personal developer.See siteWWizbotWizbot enables users to create a customized ChatGPT tailored to their content, which can then be embedded o…See siteCConversoConverso seamlessly integrates your custom GPT from OpenAI or AI Assistant from Voiceflow into a robust omn…See site
Private GPTA private ChatGPT designed for your company's knowledge base provides a secure and efficient way to access…See site
GPT PilotGPT Pilot aims to research how much LLMs can be utilized to generate fully working, production-ready apps w…Open source
GPT EngineerGPT Engineer is an AI-driven tool designed to streamline software development by generating codebases based…See siteBBabyAGIBabyAGI is an AI-powered task management system that leverages OpenAI and vector databases to streamline ta…Open sourceAAIliceAIlice is a fully autonomous, general-purpose AI agent developed by MyShell.ai.Open sourceJJunoWith its AI-moderated research capabilities, Juno autonomously conducts user interviews, leveraging AI to a…See site
ClippyClippy, also known as Clippinator, is an AI-powered code development assistant that utilizes GPT-4 to enhan…Open source
OpenAgentsOpenAgents is an open platform designed for language agents, featuring a user-friendly interface that suppo…Open sourceSSWE AgentSWE-agent is an AI-powered tool that automates the resolution of GitHub issues using GPT-4 and other langua…See site
Agent4RecAgent4Rec is an innovative recommender system simulator that features 1,000 LLM-powered generative agents.See site
VannaMeet Vanna, the AI-powered maestro of business intelligence, ready to transform your data into actionable i…See site
MentantMentat is an AI coding assistant that integrates seamlessly with your command line, providing developers wi…Open sourceSSuperagentAI-powered compliance guidance for regulated industry staff.See site
Praison AIPraison AI, leveraging both AutoGen and CrewAI or any other agent framework, represents a low-code, central…See site
MultionOur AI systems and products expand what people are capable of by helping us get things done on a daily basis.See site
LangchainTeams building with LangChain are driving operational efficiency, increasing discovery & personalization, a…See site
AutoRPAutoRP is a GitHub-based tool that runs AI-powered workflows over codebases.Open source
ChatDevChatDev is an innovative open-source framework designed to facilitate multi-agent collaboration.Open source
ChaindeskChaindesk revolutionizes customer interaction by enabling businesses to train custom ChatGPT AI chatbots fo…Open source
DevonDevon is positioned as an open-source pair programming tool, making it a valuable resource for developers s…Open source
KuaFuAiKuaFuAi introduces a multi-agent system specifically designed for AI-driven software development.Open sourceDDotagentDotagent claims to be faster, cheaper, and smarter than any single large language model (LLM).Open source
EidolonEidolon is a robust, open-source framework built to help developers quickly create and deploy generative AI…Open source
The English CompilerThe English Compiler is a proof-of-concept AI-based compiler designed to convert English-based markdown spe…Open source
Aide by CodestoryAI coding assistant offering smart completion and interactive chat capabilities.See site
B2 AIAd reinsertion tool designed to recapture revenue lost to ad blockers.See site
AskYourDatabaseAI-enabled database chat for instant insights and visualizations.See site
DemoGPTGenerator for LangChain code and Streamlit apps powered by AI.Open source
Adept AIAgentic AI for enterprise tech stacks, delivering proven results.See site
Blackbox AIAI-based coding assistant for enhanced, faster development.See site
UFOAI framework for UI interaction on Windows OS.Open source
Airkit.aiCode-free AI agents for commerce and customer support automation.See site
PezzoOpen-source LLMOps platform for efficient AI development.See site
BondAIOpen-source AI agent system with integrations and advanced features.See site
OpenAGIPlatform for creating and managing LLM-powered agents.Open source
Mini AGICompact AI agent with advanced memory and reasoning abilities.Open source
SuperAGIDeveloper-first framework for building autonomous AI agents.Open source
Proficient AIQuickly add conversational AI to your app.See site
AdalaFramework for autonomous data labeling in AI development.Open source
BambooAIData analysis assistant driven by AI for natural language interactions.Open source
Cody by SourcegraphCoding assistant powered by AI for smarter development.See site
GraphlitAccelerate AI app development with seamless data integration.See site
CodeFuse-ChatBotAI assistant for managing the software development lifecycle.Open source
Cody by ajhous44Coding assistant with AI for efficient codebase navigation.Open source
Athena Intelligence24/7 enterprise AI analyst for automated task management.See site
DevOpsGPTAutomation of software development processes using AI.See site
GPT DiscordAdvanced GPT-powered Discord bot with AI features.Open source
Codium AIAI-powered code generation and quality assurance tools for developers.See site
KushoAPI testing tool powered by AI for smooth development workflows.See site
GPT RunnerTool for AI-driven code discussions and preset management.Open source
GPT MigrateAI-based code migration assistant.Open source
AgentScaleBoost real estate commissions by $300k with AgentScale in 12 months.See site
NexusGPTBuild no-code AI agents to automate any workflow.See site
SweepJunior developer powered by AI for automated code updates.See site
MagickVisual AI toolkit for creating intelligent agents and data pipelines.See site
GPTSwarmFramework for building and optimizing LLM agent swarms.See site
bumpgenAI-powered assistant for TypeScript dependency upgrades.Open source
LLM AgentsBuild and manage AI agents using large language models.Open source
WorkGPTFramework for AI agents to complete tasks using diverse APIs.Open source
GitHub Copilot XAI coding assistant to enhance developer productivity.Open source
BloopChatGPT for your code, enabling search, explanations, and generation.See site
TuskAI-powered pull requests for chore tasks.See site
SpellAutomate workflows by delegating tasks to AI agents.See site
DataberryCreate custom AI chatbots and website forms in minutes.See site
SecondAI-driven codebase migration tool for engineering teams.See site
InstruktTerminal-based AI environment for agent development and instruction.Open source
InvictaBuild an AI workforce with no-code agent orchestration.See site
EllipsisAI-driven code reviews and bug fixes for streamlined development.See site
FineAI development environment for efficient software engineering.See site
GitLab DuoAI acceleration of software development with security features.See site
Duckie AIAI support assistant for enhanced customer service.See site
GritAutomation of software maintenance through AI.See site
Devika AIDevika AI, developed by Stition.ai, is an advanced AI software engineer capable of understanding high-level…Open source
MetaGPTMetaGPT is a sophisticated AI framework that leverages large language models to create a collaborative envi…See site
Micro AgentMicro Agent is an open-source tool developed by Builder.io to address the unreliability of AI-generated code.Open source
JARVISMicrosoft Jarvis is an advanced AI platform developed by Microsoft in collaboration with Hugging Face.Open source
Multi-GPTMulti-GPT is an open-source project that creates a collaborative environment for multiple AI agents, each w…Open source
Teenage-AGITeenage-AGI is a Python-based AI agent inspired by BabyAGI and the "Generative Agents: Interactive Simulacr…Open source
VisualAgents.aiVisualAgents.ai is a serverless, zero-install Progressive Web App that allows users to design and deploy AI…See site
MaigeMaige is an AI-driven tool that helps development teams triage and manage GitHub issues.See site
Project OscarProject Oscar is an open-source platform by Google designed to enhance open-source project management.See site