# Which Agent Should I Use? (Agent Showdown)

Site: https://whichagentshouldiuse.com

> A directory of AI agents and agent tools, with pricing checked against official sites and real setup examples.

## Coding agents

- [Cursor](https://whichagentshouldiuse.com/agents/cursor): AI code editor with an agent that edits across files, plus cloud agents. Pricing: Free $0; Plus $8/mo; Premium $30/mo; Super $100/mo; Ultra $200/mo; Teams $30+/user/mo (checked 2026-10-14, source https://cursor.com/pricing). Best for: coding-in-an-editor, refactoring, cloud-agents.
- [Claude Code](https://whichagentshouldiuse.com/agents/claude-code): Terminal coding agent from Anthropic that reads, edits and runs code in your repo. Pricing: Included with Claude Pro ($20/mo monthly, $17/mo annual) and Max (from $100/mo) (checked 2026-10-13, source https://www.anthropic.com/pricing). Best for: terminal-coding, refactoring, large-codebases.
- [GitHub Copilot](https://whichagentshouldiuse.com/agents/github-copilot): Code completions, chat and a cloud agent that opens pull requests on GitHub. Pricing: Free $0; Pro $10/mo; Pro+ $39/mo; Max $100/mo (checked 2026-10-13, source https://github.com/features/copilot/plans). Best for: coding-in-an-editor, pull-request-automation, code-review.
- [Windsurf](https://whichagentshouldiuse.com/agents/windsurf): AI code editor with the Cascade agent. Pricing: Free $0; Pro $20/mo; Max $200/mo; Teams $80/mo + $40/user (checked 2026-10-13, source https://windsurf.com/pricing). Best for: coding-in-an-editor, refactoring.
- [Devin](https://whichagentshouldiuse.com/agents/devin): Autonomous software engineer that works through tickets in its own environment. Pricing: Free $0; Pro $20/mo; Max $200/mo; Teams $80/mo + $40/user; Enterprise custom (checked 2026-10-14, source https://devin.ai/pricing). Best for: cloud-agents, pull-request-automation.
- [Replit Agent](https://whichagentshouldiuse.com/agents/replit-agent): Builds and deploys full apps from a prompt inside Replit. Pricing: Core $20/mo ($18/mo annual); Pro $100/mo ($90/mo annual) (checked 2026-10-13, source https://replit.com/pricing). Best for: build-an-app-from-a-prompt, prototyping.
- [Lovable](https://whichagentshouldiuse.com/agents/lovable): Prompt-to-web-app builder for full-stack apps. Pricing: Free $0; Pro from $25/mo ($21/mo annual) for 100 credits; Business from $50/mo; Enterprise custom (checked 2026-10-14, source https://docs.lovable.dev/introduction/subscription-plans). Best for: build-an-app-from-a-prompt, prototyping.
- [Bolt](https://whichagentshouldiuse.com/agents/bolt): In-browser prompt-to-app builder from StackBlitz. Pricing: Free $0; Pro $25/mo; Teams $30/member/mo (checked 2026-10-13, source https://bolt.new/pricing). Best for: build-an-app-from-a-prompt, prototyping.
- [v0](https://whichagentshouldiuse.com/agents/v0): Vercel's agent for generating React/Next.js UI and apps. Pricing: Free $0/mo; Plus $30/user/mo; Business $100/user/mo (checked 2026-10-13, source https://v0.app/pricing). Best for: build-an-app-from-a-prompt, ui-design.
- [Aider](https://whichagentshouldiuse.com/agents/aider): Open-source AI pair programmer in the terminal that commits changes to git. Pricing: Free and open source (you pay your own LLM API costs) (checked 2026-10-13, source https://aider.chat/). Best for: terminal-coding, open-source.
- [Cline](https://whichagentshouldiuse.com/agents/cline): Open-source coding agent for VS Code that plans and acts with your own API key. Pricing: Free and open source for individuals (pay for AI inference at cost or bring your own key); Enterprise custom (checked 2026-10-14, source https://cline.bot/pricing). Best for: coding-in-an-editor, open-source.
- [OpenHands](https://whichagentshouldiuse.com/agents/openhands): Open-source platform for autonomous coding agents (formerly OpenDevin). Pricing: Open source free; Cloud Individual free (BYOK or OpenHands models at cost); Enterprise custom (checked 2026-10-14, source https://www.all-hands.dev/pricing). Best for: cloud-agents, open-source.
- [OpenAI Codex](https://whichagentshouldiuse.com/agents/openai-codex): OpenAI's coding agent in the CLI, IDE and cloud. Pricing: Free $0; Go $8/mo; Plus $20/mo; Pro from $100/mo; Business $20/user/mo (checked 2026-10-13, source https://developers.openai.com/codex/pricing). Best for: terminal-coding, cloud-agents, pull-request-automation.
- [Gemini CLI](https://whichagentshouldiuse.com/agents/gemini-cli): Open-source terminal agent from Google powered by Gemini. Pricing: Free and open source (you pay your own LLM API costs) (checked 2026-10-13, source https://github.com/google-gemini/gemini-cli). Best for: terminal-coding, open-source.

## Browser agents

- [Browser Use](https://whichagentshouldiuse.com/agents/browser-use): Open-source library and cloud for letting AI agents control a web browser. Pricing: Open-source library free; Cloud is pay-as-you-go per model token (e.g. BU 2.0 $0.60 input / $3.50 output per 1M tokens) (checked 2026-10-13, source https://browser-use.com/pricing). Best for: web-automation, scraping, open-source.
- [Browserbase](https://whichagentshouldiuse.com/agents/browserbase): Headless browser infrastructure for AI agents. Pricing: Free; Developer $20/mo; Startup $99/mo; Custom (checked 2026-10-13, source https://www.browserbase.com/pricing). Best for: web-automation, scraping.
- [Stagehand](https://whichagentshouldiuse.com/agents/stagehand): Open-source SDK from Browserbase for natural-language browser actions (act, extract, observe). Pricing: Free and open source (you pay your own LLM API costs) (checked 2026-10-13, source https://github.com/browserbase/stagehand). Best for: web-automation, scraping, open-source.
- [Manus](https://whichagentshouldiuse.com/agents/manus): General-purpose autonomous agent that browses, researches and builds deliverables. Pricing: Free $0; Pro from $20/mo (also a $40/mo tier); Team from $20/seat/mo; 17% off annual (checked 2026-10-14, source https://help.manus.im/en/articles/11711111-what-is-the-current-membership-pricing-for-manus). Best for: research-reports, web-automation.

## Voice agents

- [ElevenLabs Agents](https://whichagentshouldiuse.com/agents/elevenlabs-agents): Voice AI platform with realistic TTS and conversational voice agents. Pricing: Free; Starter $6/mo; Creator $22/mo; Pro $99/mo; Scale $299/mo; Business $990/mo (checked 2026-10-13, source https://elevenlabs.io/pricing). Best for: voice-agents, text-to-speech, phone-agents.
- [Vapi](https://whichagentshouldiuse.com/agents/vapi): Developer platform for building phone and web voice agents. Pricing: Pay-as-you-go from $0.05/min plus provider costs; $5 free credits to start (checked 2026-10-13, source https://vapi.ai/pricing). Best for: phone-agents, voice-agents.
- [Retell AI](https://whichagentshouldiuse.com/agents/retell-ai): Platform for building and deploying AI phone call agents. Pricing: Usage-based per minute (voice engine, LLM and telephony billed separately) (checked 2026-10-13, source https://www.retellai.com/pricing). Best for: phone-agents, customer-support.
- [Bland AI](https://whichagentshouldiuse.com/agents/bland-ai): Enterprise AI phone calling platform with an API for outbound and inbound calls. Pricing: Starts at $0.14/min with no platform fee; higher tiers lower the per-minute rate (checked 2026-10-13, source https://www.bland.ai/pricing). Best for: phone-agents, customer-support.
- [LiveKit Agents](https://whichagentshouldiuse.com/agents/livekit-agents): Open-source framework and cloud for realtime voice and video AI agents. Pricing: Open-source framework free; LiveKit Cloud usage billed per minute (checked 2026-10-13, source https://livekit.io/pricing). Best for: voice-agents, realtime-video, open-source.
- [Pipecat](https://whichagentshouldiuse.com/agents/pipecat): Open-source Python framework for voice and multimodal conversational agents, maintained by Daily. Pricing: Free and open source (you pay your own LLM API costs) (checked 2026-10-13, source https://github.com/pipecat-ai/pipecat). Best for: voice-agents, open-source.

## Research agents

- [Perplexity](https://whichagentshouldiuse.com/agents/perplexity): AI answer engine with cited sources and deep research mode. Pricing: Free $0; Pro $17/mo billed annually; Max $167/mo billed annually; Enterprise per seat (checked 2026-10-14, source https://www.perplexity.ai/hub/pricing). Best for: research-reports, web-search.
- [Elicit](https://whichagentshouldiuse.com/agents/elicit): AI research assistant for finding and extracting data from academic papers. Pricing: Free tier; Pro $49/user/mo billed annually; higher tiers available (checked 2026-10-13, source https://elicit.com/pricing). Best for: academic-research, literature-review.
- [GPT Researcher](https://whichagentshouldiuse.com/agents/gpt-researcher): Open-source autonomous agent that writes cited research reports. Pricing: Free and open source (you pay your own LLM API costs) (checked 2026-10-13, source https://github.com/assafelovic/gpt-researcher). Best for: research-reports, open-source.

## Agent frameworks

- [LangGraph](https://whichagentshouldiuse.com/agents/langgraph): Framework from LangChain for building stateful, controllable agent graphs. Pricing: Library free and open source; LangSmith Developer $0/seat, Plus $39/seat/mo (checked 2026-10-13, source https://www.langchain.com/pricing). Best for: build-your-own-agent, multi-agent, open-source.
- [CrewAI](https://whichagentshouldiuse.com/agents/crewai): Python framework for orchestrating role-playing multi-agent crews. Pricing: Basic free (50 workflow executions/mo); Enterprise custom; open-source framework free (checked 2026-10-14, source https://www.crewai.com/pricing). Best for: multi-agent, build-your-own-agent, open-source.
- [AutoGen](https://whichagentshouldiuse.com/agents/autogen): Microsoft's open-source framework for multi-agent conversations. Pricing: Free and open source (you pay your own LLM API costs) (checked 2026-10-13, source https://github.com/microsoft/autogen). Best for: multi-agent, build-your-own-agent, open-source.
- [OpenAI Agents SDK](https://whichagentshouldiuse.com/agents/openai-agents-sdk): Lightweight Python framework from OpenAI for multi-agent workflows with handoffs and guardrails. Pricing: Free and open source (you pay your own LLM API costs) (checked 2026-10-13, source https://github.com/openai/openai-agents-python). Best for: build-your-own-agent, multi-agent, open-source.
- [Pydantic AI](https://whichagentshouldiuse.com/agents/pydantic-ai): Type-safe Python agent framework from the Pydantic team. Pricing: Free and open source (you pay your own LLM API costs) (checked 2026-10-13, source https://github.com/pydantic/pydantic-ai). Best for: build-your-own-agent, open-source.
- [n8n](https://whichagentshouldiuse.com/agents/n8n): Workflow automation platform with AI agent nodes; self-hostable. Pricing: Starter €20/mo; Pro €50/mo; Business €667/mo (billed annually); Enterprise custom; self-hosted Community Edition free (checked 2026-10-14, source https://n8n.io/pricing/). Best for: workflow-automation, build-your-own-agent.

## Comparisons

- [Cursor vs Claude Code](https://whichagentshouldiuse.com/compare/cursor-vs-claude-code)
- [Cursor vs GitHub Copilot](https://whichagentshouldiuse.com/compare/cursor-vs-github-copilot)
- [Cursor vs Windsurf](https://whichagentshouldiuse.com/compare/cursor-vs-windsurf)
- [Claude Code vs OpenAI Codex](https://whichagentshouldiuse.com/compare/claude-code-vs-openai-codex)
- [Claude Code vs Gemini CLI](https://whichagentshouldiuse.com/compare/claude-code-vs-gemini-cli)
- [Claude Code vs Aider](https://whichagentshouldiuse.com/compare/claude-code-vs-aider)
- [GitHub Copilot vs Windsurf](https://whichagentshouldiuse.com/compare/github-copilot-vs-windsurf)
- [GitHub Copilot vs Claude Code](https://whichagentshouldiuse.com/compare/github-copilot-vs-claude-code)
- [OpenAI Codex vs Gemini CLI](https://whichagentshouldiuse.com/compare/openai-codex-vs-gemini-cli)
- [Aider vs Cline](https://whichagentshouldiuse.com/compare/aider-vs-cline)
- [Cline vs Cursor](https://whichagentshouldiuse.com/compare/cline-vs-cursor)
- [Devin vs OpenHands](https://whichagentshouldiuse.com/compare/devin-vs-openhands)
- [Devin vs Claude Code](https://whichagentshouldiuse.com/compare/devin-vs-claude-code)
- [Replit Agent vs Lovable](https://whichagentshouldiuse.com/compare/replit-agent-vs-lovable)
- [Lovable vs Bolt](https://whichagentshouldiuse.com/compare/lovable-vs-bolt)
- [Bolt vs v0](https://whichagentshouldiuse.com/compare/bolt-vs-v0)
- [Lovable vs v0](https://whichagentshouldiuse.com/compare/lovable-vs-v0)
- [Replit Agent vs Bolt](https://whichagentshouldiuse.com/compare/replit-agent-vs-bolt)
- [OpenHands vs Aider](https://whichagentshouldiuse.com/compare/openhands-vs-aider)
- [Windsurf vs Cline](https://whichagentshouldiuse.com/compare/windsurf-vs-cline)
- [Cursor vs OpenAI Codex](https://whichagentshouldiuse.com/compare/cursor-vs-openai-codex)
- [Gemini CLI vs Aider](https://whichagentshouldiuse.com/compare/gemini-cli-vs-aider)
- [Browser Use vs Stagehand](https://whichagentshouldiuse.com/compare/browser-use-vs-stagehand)
- [Browser Use vs Browserbase](https://whichagentshouldiuse.com/compare/browser-use-vs-browserbase)
- [Stagehand vs Browserbase](https://whichagentshouldiuse.com/compare/stagehand-vs-browserbase)
- [Manus vs Browser Use](https://whichagentshouldiuse.com/compare/manus-vs-browser-use)
- [ElevenLabs Agents vs Vapi](https://whichagentshouldiuse.com/compare/elevenlabs-agents-vs-vapi)
- [Vapi vs Retell AI](https://whichagentshouldiuse.com/compare/vapi-vs-retell-ai)
- [Retell AI vs Bland AI](https://whichagentshouldiuse.com/compare/retell-ai-vs-bland-ai)
- [Vapi vs Bland AI](https://whichagentshouldiuse.com/compare/vapi-vs-bland-ai)
- [LiveKit Agents vs Pipecat](https://whichagentshouldiuse.com/compare/livekit-agents-vs-pipecat)
- [Vapi vs LiveKit Agents](https://whichagentshouldiuse.com/compare/vapi-vs-livekit-agents)
- [Perplexity vs Elicit](https://whichagentshouldiuse.com/compare/perplexity-vs-elicit)
- [GPT Researcher vs Perplexity](https://whichagentshouldiuse.com/compare/gpt-researcher-vs-perplexity)
- [Elicit vs GPT Researcher](https://whichagentshouldiuse.com/compare/elicit-vs-gpt-researcher)
- [LangGraph vs CrewAI](https://whichagentshouldiuse.com/compare/langgraph-vs-crewai)
- [CrewAI vs AutoGen](https://whichagentshouldiuse.com/compare/crewai-vs-autogen)
- [LangGraph vs AutoGen](https://whichagentshouldiuse.com/compare/langgraph-vs-autogen)
- [OpenAI Agents SDK vs Pydantic AI](https://whichagentshouldiuse.com/compare/openai-agents-sdk-vs-pydantic-ai)
- [n8n vs CrewAI](https://whichagentshouldiuse.com/compare/n8n-vs-crewai)

## More

- [Full details of every listing](https://whichagentshouldiuse.com/llms-full.txt)
- [Best agent for X index](https://whichagentshouldiuse.com/best)
- [Sitemap](https://whichagentshouldiuse.com/sitemap.xml)