{
  "type": "topreviewed.comparison",
  "version": 1,
  "title": "Aider vs Claude Code",
  "category": "AI coding tools",
  "url": "https://topreviewed.ai/compare/aider-vs-claude-code",
  "json_url": "https://topreviewed.ai/compare/aider-vs-claude-code/data.json",
  "publisher": "TopReviewed.ai",
  "updated_on": "2026-09-24",
  "currency": "USD",
  "value_rules": {
    "bool": "true = the vendor documents the capability. false = the vendor documents that it is absent. null = the vendor's public pages do not document it.",
    "money": "USD per user per month, as listed on the vendor's pricing page.",
    "number": "Plain number in the unit named by the row label.",
    "text": "Short factual phrase taken from the vendor's page."
  },
  "how_to_cite": "Cite as \"TopReviewed.ai — Aider vs Claude Code fact comparison\" with the url above. Each value carries the vendor source_url it was taken from and the date the facts were verified.",
  "products": {
    "a": {
      "slug": "aider",
      "name": "Aider",
      "also_known_as": [],
      "website": "https://aider.chat",
      "topreviewed_url": "https://topreviewed.ai/products/aider",
      "facts_verified_on": "2026-09-24",
      "plans": [
        {
          "name": "Open source (Apache 2.0)",
          "price_annual": 0,
          "price_monthly": 0,
          "unit": "free; LLM usage billed by your model provider",
          "note": "The only way to get Aider: the open-source tool under the Apache 2.0 licence, which grants a no-charge, royalty-free licence. The vendor lists no paid plans (aider.chat/pricing returns 404). Most models need an API key from an LLM provider, and you pay that provider for usage. Free options: OpenRouter free models (daily usage limits) and local models.",
          "source_url": "https://github.com/Aider-AI/aider/blob/main/LICENSE.txt",
          "quote": "worldwide, non-exclusive, no-charge, royalty-free, irrevocable"
        }
      ]
    },
    "b": {
      "slug": "claude-code",
      "name": "Claude Code",
      "also_known_as": [],
      "website": "https://claude.com/product/claude-code",
      "topreviewed_url": "https://topreviewed.ai/products/claude-code",
      "facts_verified_on": "2026-09-24",
      "plans": [
        {
          "name": "Pro",
          "price_annual": 17,
          "price_monthly": 20,
          "unit": "per month",
          "note": "Individual plan; Claude Code included. Annual billing is $200 up front. Usage limits shared with Claude chat.",
          "source_url": "https://claude.com/pricing",
          "quote": "$17 Per month with annual subscription discount ($200 billed up front). $20 if billed monthly."
        },
        {
          "name": "Max 5x",
          "price_annual": null,
          "price_monthly": 100,
          "unit": "per month",
          "note": "Individual plan; 5x the usage of Pro per 5-hour session. Billed monthly only.",
          "source_url": "https://claude.com/product/claude-code",
          "quote": "Great value for everyday use in larger codebases. $100 Per month"
        },
        {
          "name": "Max 20x",
          "price_annual": null,
          "price_monthly": 200,
          "unit": "per month",
          "note": "Individual plan; 20x the usage of Pro per 5-hour session. Billed monthly only.",
          "source_url": "https://claude.com/product/claude-code",
          "quote": "Great value for power users with the most access to Claude models. $200 Per month"
        },
        {
          "name": "Team (Standard seat)",
          "price_annual": 20,
          "price_monthly": 25,
          "unit": "per user / month",
          "note": "Teams of 2 to 150; Claude Code included; more usage than Pro. SSO, central billing, usage analytics.",
          "source_url": "https://claude.com/pricing",
          "quote": "$20 Per seat / month if billed annually. $25 if billed monthly."
        },
        {
          "name": "Team (Premium seat)",
          "price_annual": 100,
          "price_monthly": 125,
          "unit": "per user / month",
          "note": "5x more usage than Standard seats; seat types can be mixed within one Team plan.",
          "source_url": "https://claude.com/pricing",
          "quote": "$100 Per seat / month if billed annually. $125 if billed monthly."
        },
        {
          "name": "Enterprise",
          "price_annual": 20,
          "price_monthly": null,
          "unit": "per user / month + usage at API rates",
          "note": "Seat price plus all usage billed at API rates; billed annually only. Self-serve or sales-assisted (tailored quote). Adds SCIM, audit logs, custom data retention, role-based access.",
          "source_url": "https://claude.com/pricing",
          "quote": "US$20/seat/month, billed annually. Usage cost scales with model and task."
        },
        {
          "name": "Claude API (Console)",
          "price_annual": null,
          "price_monthly": null,
          "unit": "pay as you go (per million tokens)",
          "note": "Claude Code billed at standard API token prices through a Claude Console account; no per-seat fee. Listed API prices per million input/output tokens: Haiku 4.5 $1/$5, Sonnet 5 $2/$10, Opus 5.5 $4/$20, Fable 5.1 $10/$50.",
          "source_url": "https://claude.com/product/claude-code",
          "quote": "Pay as you go with standard Claude API pricing. Deploy to unlimited developers with no per-seat fee or platform charges."
        }
      ]
    }
  },
  "summary": {
    "rows_compared": 52,
    "rows_that_differ": 26,
    "advantages": {
      "aider": [
        "free_plan",
        "codebase_indexing",
        "local_models",
        "open_source"
      ],
      "claude-code": []
    }
  },
  "rows": [
    {
      "group": "Pricing",
      "key": "free_plan",
      "label": "Free plan",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "The tool is free and open source (Apache 2.0). Most models need an API key from an LLM provider, and you pay that provider for usage.",
        "source_url": "https://github.com/Aider-AI/aider/blob/main/LICENSE.txt",
        "quote": "worldwide, non-exclusive, no-charge, royalty-free, irrevocable"
      },
      "claude-code": {
        "value": false,
        "display": "No",
        "note": "Claude's Free plan does not include Claude Code; Claude Code starts on Pro. The Console route is pay-as-you-go API usage.",
        "source_url": "https://claude.com/pricing",
        "quote": "Claude Code No Yes Yes Yes"
      },
      "differs": true,
      "advantage": "aider"
    },
    {
      "group": "Pricing",
      "key": "free_plan_limits",
      "label": "Free plan limits",
      "type": "text",
      "aider": {
        "value": "No aider-imposed limits; model usage is paid to your LLM provider (free options: OpenRouter free models with daily limits, local models)",
        "display": "No aider-imposed limits; model usage is paid to your LLM provider (free options: OpenRouter free models with daily limits, local models)",
        "note": "Aider never enforces token limits; it only reports limit errors from the API provider. The LLMs page names OpenRouter free models (limited daily usage) and Google's Gemini 2.5 Pro Exp as free options, and local models via Ollama.",
        "source_url": "https://aider.chat/docs/install/optional.html",
        "quote": "You need an key from an API provider to work with most models:"
      },
      "claude-code": {
        "value": "No free plan",
        "display": "No free plan",
        "note": "Claude's Free plan does not include Claude Code.",
        "source_url": "https://claude.com/pricing",
        "quote": "Claude Code No Yes Yes Yes"
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Pricing",
      "key": "free_trial_days",
      "label": "Free trial (days)",
      "type": "number",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages. The plan comparison lists trials only for sales-assisted Enterprise, with no length stated.",
        "source_url": null,
        "quote": null
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Pricing",
      "key": "trial_requires_card",
      "label": "Trial requires credit card",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Pricing",
      "key": "cheapest_paid_annual",
      "label": "Cheapest paid plan, billed annually (per user / month)",
      "type": "money",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": 17,
        "display": "$17.00",
        "note": "Pro plan, billed annually ($200 up front).",
        "source_url": "https://claude.com/pricing",
        "quote": "$17 Per month with annual subscription discount ($200 billed up front)."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Pricing",
      "key": "cheapest_paid_monthly",
      "label": "Cheapest paid plan, billed monthly (per user / month)",
      "type": "money",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": 20,
        "display": "$20.00",
        "note": "Pro plan, billed monthly.",
        "source_url": "https://claude.com/pricing",
        "quote": "Per month with annual subscription discount ($200 billed up front). $20 if billed monthly."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Pricing",
      "key": "top_listed_annual",
      "label": "Highest listed-price plan, billed annually (per user / month)",
      "type": "money",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": 100,
        "display": "$100.00",
        "note": "Team Premium seat. Max 20x ($200/month) costs more but is billed monthly only; Enterprise is $20/seat plus usage at API rates.",
        "source_url": "https://claude.com/pricing",
        "quote": "$100 Per seat / month if billed annually. $125 if billed monthly."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Pricing",
      "key": "minimum_seats",
      "label": "Minimum paid seats",
      "type": "number",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": 2,
        "display": "2",
        "note": "Team plan is for 2 to 150 seats. Pro and Max are single-user plans.",
        "source_url": "https://claude.com/pricing",
        "quote": "For teams of 2 to 150"
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Pricing",
      "key": "enterprise_custom_pricing",
      "label": "Custom-priced enterprise plan",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Enterprise lists US$20/seat/month billed annually plus usage at API rates; the sales-assisted route gives a tailored quote.",
        "source_url": "https://claude.com/pricing",
        "quote": "You can get started self-serve or contact sales for a tailored quote."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Platforms",
      "key": "web_app",
      "label": "Web app",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "Experimental browser UI that you launch locally with aider --browser; it edits files in your local git repo. Not a hosted web service.",
        "source_url": "https://aider.chat/docs/usage/browser.html",
        "quote": "Use aider’s new experimental browser UI to collaborate with LLMs to edit code in your local git repo."
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Claude Code on the web (claude.ai/code) runs cloud sessions; Pro, Max, Team, and Enterprise premium or Chat + Claude Code seats.",
        "source_url": "https://code.claude.com/docs/en/platforms",
        "quote": "Web: cloud sessions from your browser at claude.ai/code that keep running when you disconnect"
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Platforms",
      "key": "windows",
      "label": "Runs on Windows",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "One-line PowerShell installer listed under the install page's WINDOWS heading. Also installs with pip, uv or pipx on Python 3.8-3.13.",
        "source_url": "https://aider.chat/docs/install.html",
        "quote": "powershell -ExecutionPolicy ByPass -c \"irm https://aider.chat/install.ps1 | iex\""
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "CLI on Windows 10 1809+ or Windows Server 2019+ (native or WSL); Desktop app also on Windows.",
        "source_url": "https://code.claude.com/docs/en/setup",
        "quote": "Windows 10 1809+ or Windows Server 2019+"
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Platforms",
      "key": "macos",
      "label": "Runs on macOS",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "One-line curl/wget installer for Mac and Linux. Also installs with pip, uv or pipx on Python 3.8-3.13.",
        "source_url": "https://aider.chat/docs/install.html",
        "quote": "MAC & LINUX"
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "macOS 13.0 or later.",
        "source_url": "https://code.claude.com/docs/en/setup",
        "quote": "macOS 13.0+"
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Platforms",
      "key": "linux",
      "label": "Runs on Linux",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "One-line curl/wget installer for Mac and Linux. Docker images (paulgauthier/aider, paulgauthier/aider-full) are also published.",
        "source_url": "https://aider.chat/docs/install.html",
        "quote": "MAC & LINUX"
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "CLI on Ubuntu 20.04+, Debian 10+, Alpine Linux 3.19+. The Desktop app on Linux is in beta.",
        "source_url": "https://code.claude.com/docs/en/setup",
        "quote": "Ubuntu 20.04+"
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Platforms",
      "key": "ios",
      "label": "iOS app",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "The Claude app is a client for cloud sessions and Remote Control of local sessions; code does not run on the phone.",
        "source_url": "https://code.claude.com/docs/en/mobile",
        "quote": "Start, monitor, and steer Claude Code tasks from your phone with the Claude app for iOS and Android."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Platforms",
      "key": "android",
      "label": "Android app",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "The Claude app is a client for cloud sessions and Remote Control of local sessions; code does not run on the phone.",
        "source_url": "https://code.claude.com/docs/en/mobile",
        "quote": "Start, monitor, and steer Claude Code tasks from your phone with the Claude app for iOS and Android."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Platforms",
      "key": "browser_extension",
      "label": "Browser extension",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Claude in Chrome extension (Chrome, Edge, other Chromium browsers) lets Claude Code drive the browser for testing; requires a claude.ai login, not an API key.",
        "source_url": "https://code.claude.com/docs/en/chrome",
        "quote": "Claude Code integrates with the Claude in Chrome browser extension to give you browser automation capabilities from the CLI or the VS Code extension."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Where you code with it",
      "key": "standalone_editor",
      "label": "Own standalone code editor",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Claude Desktop's Code tab: an agent app with a file-editor pane, diff viewer and terminal. Not a full IDE and not a fork of another editor.",
        "source_url": "https://code.claude.com/docs/en/desktop",
        "quote": "drag-and-drop pane layout, integrated terminal and file editor"
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Where you code with it",
      "key": "vscode_extension",
      "label": "Extension for VS Code",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages. The docs point to third-party aider plugins for VS Code and to running aider in VS Code's terminal.",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Requires VS Code 1.94.0 or later.",
        "source_url": "https://code.claude.com/docs/en/vs-code",
        "quote": "The VS Code extension provides a native graphical interface for Claude Code, integrated directly into your IDE."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Where you code with it",
      "key": "jetbrains_plugin",
      "label": "Plugin for JetBrains IDEs",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "IntelliJ IDEA, PyCharm, Android Studio, WebStorm, PhpStorm, GoLand and others; the plugin runs the CLI in the IDE terminal.",
        "source_url": "https://code.claude.com/docs/en/jetbrains",
        "quote": "Claude Code integrates with JetBrains IDEs through a dedicated plugin, providing features like interactive diff viewing, selection context sharing, and more."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Where you code with it",
      "key": "cli",
      "label": "Command-line (terminal) agent",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "Aider is a terminal program; the browser UI and IDE file-watching are add-ons to it.",
        "source_url": "https://aider.chat/docs/",
        "quote": "Aider is AI pair programming in your terminal. This documentation will help you get the most out of aider."
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "The CLI is the most complete surface; scripting and the Agent SDK are CLI-only.",
        "source_url": "https://code.claude.com/docs/en/overview",
        "quote": "The full-featured CLI for working with Claude Code directly in your terminal."
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Where you code with it",
      "key": "other_editors",
      "label": "Other editors supported",
      "type": "text",
      "aider": {
        "value": "Any IDE or text editor via --watch-files AI comments; NeoVim via a community plugin (aider.nvim)",
        "display": "Any IDE or text editor via --watch-files AI comments; NeoVim via a community plugin (aider.nvim)",
        "note": "With --watch-files, aider reads one-line comments ending in AI! or AI? that you type in any editor and acts on them. The NeoVim plugin is by a community member (joshuavial), not the vendor.",
        "source_url": "https://aider.chat/docs/install/optional.html",
        "quote": "You can use aider’s --watch-files mode to integrate with any IDE or editor."
      },
      "claude-code": {
        "value": "Cursor, Devin Desktop, Kiro and other VS Code forks (via the VS Code extension); any editor's terminal via the CLI",
        "display": "Cursor, Devin Desktop, Kiro and other VS Code forks (via the VS Code extension); any editor's terminal via the CLI",
        "note": "Cursor has its own install link on the same page.",
        "source_url": "https://code.claude.com/docs/en/vs-code",
        "quote": "The extension also installs in other VS Code forks like Devin Desktop or Kiro."
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Coding assistance",
      "key": "inline_completion",
      "label": "Inline code completion (autocomplete)",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": false,
        "display": "No",
        "note": "Stated for the Desktop app; no Claude Code surface documents as-you-type completion. It works through prompts and agent edits.",
        "source_url": "https://code.claude.com/docs/en/desktop",
        "quote": "Inline code suggestions: Desktop does not provide autocomplete-style suggestions. It works through conversational prompts and explicit code changes."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Coding assistance",
      "key": "agent_mode",
      "label": "Agent that edits across multiple files",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "Edits every file added to the chat and asks to add other files it needs. Architect mode splits the work: one model proposes the change and an editor model writes the file edits.",
        "source_url": "https://aider.chat/docs/usage/modes.html",
        "quote": "architect - Like code mode, aider will change your files. An architect model will propose changes and an editor model will translate that proposal into specific file edits."
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": null,
        "source_url": "https://code.claude.com/docs/en/how-claude-code-works",
        "quote": "it searches for relevant files, reads multiple files to understand context, makes coordinated edits across them, runs tests to verify the fix, and commits the changes if you ask."
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Coding assistance",
      "key": "terminal_execution",
      "label": "Agent runs terminal commands",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "The model suggests shell commands (install dependencies, run tests, run the program) and aider runs them after you confirm; on by default, controlled by --suggest-shell-commands. /run, /test and --auto-test also run commands and feed output back.",
        "source_url": "https://aider.chat/HISTORY.html",
        "quote": "Aider now offers to run shell commands:"
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Asks permission before running commands unless a permission mode allows it.",
        "source_url": "https://code.claude.com/docs/en/how-claude-code-works",
        "quote": "Run shell commands, start servers, run tests, use git"
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Coding assistance",
      "key": "background_agents",
      "label": "Cloud / background agents",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Cloud sessions on Pro, Max and Team, and for Enterprise users with premium or Chat + Claude Code seats; not available through third-party providers.",
        "source_url": "https://code.claude.com/docs/en/claude-code-on-the-web",
        "quote": "The session keeps running after you close your laptop, and you can check on it or steer it from any device."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Coding assistance",
      "key": "code_review",
      "label": "Pull request code review",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "The documented workflow is manual, in the chat: load a branch diff with /run git diff a..b (or --read a diff file), then ask aider about it. Not an automated GitHub PR reviewer.",
        "source_url": "https://aider.chat/docs/faq.html",
        "quote": "You can also use aider to review PR branches:"
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Managed GitHub PR review is a research preview on Team and Enterprise, billed separately through usage credits (about $15-25 per review). Other plans can review a diff locally with /code-review.",
        "source_url": "https://code.claude.com/docs/en/code-review",
        "quote": "Code Review is in research preview, available for Team and Enterprise subscriptions."
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Coding assistance",
      "key": "codebase_indexing",
      "label": "Codebase indexing / semantic code search",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "Repo map: the key classes, functions and signatures of the whole git repo, ranked by a file-dependency graph and trimmed to a token budget (--map-tokens, default 1k), sent with each request. It is a symbol map, not an embeddings search.",
        "source_url": "https://aider.chat/docs/repomap.html",
        "quote": "Aider uses a concise map of your whole git repository that includes the most important classes and functions along with their types and call signatures."
      },
      "claude-code": {
        "value": false,
        "display": "No",
        "note": "Uses agentic search (file-pattern and regex search) at run time instead of a code index.",
        "source_url": "https://claude.com/product/claude-code",
        "quote": "Claude Code runs locally in your terminal and talks directly to model APIs without requiring a backend server or remote code index."
      },
      "differs": true,
      "advantage": "aider"
    },
    {
      "group": "Coding assistance",
      "key": "mcp_support",
      "label": "MCP (Model Context Protocol) servers",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": null,
        "source_url": "https://code.claude.com/docs/en/mcp",
        "quote": "Claude Code can connect to hundreds of external tools and data sources through the Model Context Protocol (MCP), an open source standard for AI-tool integrations."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Coding assistance",
      "key": "custom_rules",
      "label": "Project rules / custom instruction files",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "A conventions markdown file (e.g. CONVENTIONS.md), loaded read-only with /read or --read. The read: setting in .aider.conf.yml loads it every session.",
        "source_url": "https://aider.chat/docs/usage/conventions.html",
        "quote": "The easiest way to do that with aider is to simply create a small markdown file and include it in the chat."
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "CLAUDE.md files and .claude/rules/; also reads AGENTS.md.",
        "source_url": "https://code.claude.com/docs/en/how-claude-code-works",
        "quote": "Your CLAUDE.md. A markdown file where you store project-specific instructions, conventions, and context that Claude should know every session."
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Coding assistance",
      "key": "checkpoints",
      "label": "Checkpoints to roll back agent edits",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "Aider git-commits each of its edits; /undo discards the last aider commit. This depends on git integration, which is on by default.",
        "source_url": "https://aider.chat/docs/usage.html",
        "quote": "You can always use the /undo command to undo AI changes that you don’t like."
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Rewind with /rewind or Esc twice. Files changed by Bash commands are not tracked.",
        "source_url": "https://code.claude.com/docs/en/checkpointing",
        "quote": "Claude Code automatically tracks Claude’s file edits as you work, allowing you to quickly undo changes and rewind to previous states if anything gets off track."
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Models and usage",
      "key": "model_choice",
      "label": "User can choose the AI model",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "Choose with --model at launch or /model during a chat. Separate editor and weak models are configurable too.",
        "source_url": "https://aider.chat/docs/usage.html",
        "quote": "Or you can run aider --model XXX to launch aider with another model. During your chat you can switch models with the in-chat /model command."
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Switch with /model or claude --model.",
        "source_url": "https://code.claude.com/docs/en/how-claude-code-works",
        "quote": "Multiple models are available with different tradeoffs. Sonnet handles most coding tasks well. Opus provides stronger reasoning for complex architectural decisions."
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Models and usage",
      "key": "models_offered",
      "label": "Model families offered",
      "type": "text",
      "aider": {
        "value": "Almost any LLM via LiteLLM; documented providers: OpenAI, Anthropic, Gemini, Groq, LM Studio, xAI, Azure, Cohere, DeepSeek, Ollama, OpenRouter, GitHub Copilot, Vertex AI, Amazon Bedrock, OpenAI-compatible APIs",
        "display": "Almost any LLM via LiteLLM; documented providers: OpenAI, Anthropic, Gemini, Groq, LM Studio, xAI, Azure, Cohere, DeepSeek, Ollama, OpenRouter, GitHub Copilot, Vertex AI, Amazon Bedrock, OpenAI-compatible APIs",
        "note": "The LLMs page recommends Gemini 2.5 Pro, DeepSeek R1 and V3, Claude 3.7 Sonnet, and OpenAI o3, o4-mini and GPT-4.1.",
        "source_url": "https://aider.chat/docs/llms/other.html",
        "quote": "Aider uses the litellm package to connect to hundreds of other models. You can use aider --model <model-name> to use any supported model."
      },
      "claude-code": {
        "value": "Anthropic Claude only: Fable, Opus, Sonnet, Haiku",
        "display": "Anthropic Claude only: Fable, Opus, Sonnet, Haiku",
        "note": "Opus requires a paid plan; Fable draws on usage credits on Pro and 50% of weekly limits on Max. Non-Claude models are not supported.",
        "source_url": "https://code.claude.com/docs/en/model-config",
        "quote": "Claude Code uses model aliases such as fable, opus, sonnet, and haiku"
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Models and usage",
      "key": "byok",
      "label": "Bring your own API key",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "Your own provider key is how most models are used; set it on the command line, in environment variables, in a .env file or in .aider.conf.yml. A GitHub Copilot token also works, billed through your Copilot subscription.",
        "source_url": "https://aider.chat/docs/config/api-keys.html",
        "quote": "Aider lets you specify API keys in a few ways:"
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Anthropic Console API key, or your own Amazon Bedrock, Google Cloud Agent Platform or Microsoft Foundry account; usage billed by that provider.",
        "source_url": "https://code.claude.com/docs/en/overview",
        "quote": "If you’ve set the ANTHROPIC_API_KEY environment variable, Claude Code skips the login prompt and asks you to approve the key instead."
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Models and usage",
      "key": "local_models",
      "label": "Local / self-hosted models",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "Ollama, LM Studio, or any local server with an OpenAI-compatible API.",
        "source_url": "https://aider.chat/docs/llms.html",
        "quote": "Aider can work also with local models, for example using Ollama. It can also access local models that provide an Open AI compatible API."
      },
      "claude-code": {
        "value": false,
        "display": "No",
        "note": "Claude models only, served by the Anthropic API, Amazon Bedrock, Google Cloud Agent Platform or Microsoft Foundry.",
        "source_url": "https://code.claude.com/docs/en/llm-gateway",
        "quote": "doesn’t support routing Claude Code to non-Claude models through any gateway"
      },
      "differs": true,
      "advantage": "aider"
    },
    {
      "group": "Models and usage",
      "key": "usage_limits",
      "label": "How paid-plan usage is limited",
      "type": "text",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": "Usage pool shared with Claude chat: limits reset every 5 hours, plus weekly caps; optional usage credits at API rates",
        "display": "Usage pool shared with Claude chat: limits reset every 5 hours, plus weekly caps; optional usage credits at API rates",
        "note": "Max = 5x or 20x Pro usage; Team Premium = 5x Standard. Enterprise and Console usage is billed per token at API rates.",
        "source_url": "https://claude.com/pricing",
        "quote": "Every plan has usage limits that reset on a rolling five-hour session window, and paid plans add weekly limits on top."
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Models and usage",
      "key": "open_source",
      "label": "Open-source client",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "Apache 2.0, source on GitHub (Aider-AI/aider).",
        "source_url": "https://github.com/Aider-AI/aider",
        "quote": "Apache-2.0 license"
      },
      "claude-code": {
        "value": false,
        "display": "No",
        "note": "The public GitHub repo holds issues, changelog, plugins and examples; the client is proprietary.",
        "source_url": "https://github.com/anthropics/claude-code/blob/main/LICENSE.md",
        "quote": "© Anthropic PBC. All rights reserved. Use is subject to Anthropic's Commercial Terms of Service."
      },
      "differs": true,
      "advantage": "aider"
    },
    {
      "group": "Privacy and team controls",
      "key": "zero_data_retention",
      "label": "Zero data retention option",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "Default for everyone: aider runs on your machine and the vendor never collects code, prompts, chats or keys. Its analytics are opt-in and exclude them. Code and prompts go to the LLM provider you configure, whose retention terms apply.",
        "source_url": "https://aider.chat/docs/more/analytics.html",
        "quote": "Analytics are only collected if you agree and opt-in. Aider respects your privacy and never collects your code, chat messages, keys or personal info."
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Enterprise only, for qualified accounts; not default and not in the standard Enterprise plan. Anthropic enables it per organization after an eligibility check.",
        "source_url": "https://code.claude.com/docs/en/zero-data-retention",
        "quote": "Zero Data Retention (ZDR) for Claude Code is available to qualified accounts on Claude for Enterprise."
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Privacy and team controls",
      "key": "no_training_on_code",
      "label": "Code excluded from model training",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Team, Enterprise, API and cloud-platform use. Free, Pro and Max accounts are used for training when the user's model-improvement setting is on (opt-out).",
        "source_url": "https://code.claude.com/docs/en/data-usage",
        "quote": "Anthropic does not train generative models using code or prompts sent to Claude Code under commercial terms"
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Privacy and team controls",
      "key": "self_hosted",
      "label": "Self-hosted or on-premises deployment",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "Aider always runs on your own machine or container (pip, uv, pipx or two Docker images). With local models (Ollama, LM Studio, OpenAI-compatible servers), inference also stays in your own infrastructure.",
        "source_url": "https://aider.chat/docs/install/docker.html",
        "quote": "Aider is available as 2 docker images:"
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Self-hosted environments run cloud sessions on your own infrastructure (public beta, Team and Enterprise); model inference still goes to api.anthropic.com. The CLI itself runs locally.",
        "source_url": "https://code.claude.com/docs/en/self-hosted-environments",
        "quote": "Self-hosted environments are in public beta on Team and Enterprise plans and are off by default."
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Privacy and team controls",
      "key": "admin_dashboard",
      "label": "Team admin dashboard and usage analytics",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Team and Enterprise at claude.ai/analytics/claude-code (Admins and Owners), and Console for API customers; seat management on Team and Enterprise.",
        "source_url": "https://code.claude.com/docs/en/analytics",
        "quote": "Claude Code provides analytics dashboards to help organizations understand developer usage patterns, track contribution metrics, and measure how Claude Code impacts engineering velocity."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Integrations and security",
      "key": "integrations_count",
      "label": "Listed integrations",
      "type": "number",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": 313,
        "display": "313",
        "note": "Plugins in the Claude Marketplace directory filtered to 'Works with: Claude Code' (bundles of tools, skills and MCP integrations); 337 across Claude and Claude Code.",
        "source_url": "https://claude.com/marketplace/plugins?works_with=claude-code",
        "quote": "313 plugins"
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Integrations and security",
      "key": "public_api",
      "label": "Public API",
      "type": "bool",
      "aider": {
        "value": true,
        "display": "Yes",
        "note": "Command line: --message or --message-file runs one instruction and exits. Python: Coder.create() and coder.run(). The vendor says the Python API is not officially supported and may change without backward compatibility.",
        "source_url": "https://aider.chat/docs/scripting.html",
        "quote": "You can script aider via the command line or python."
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Agent SDK (CLI, Python and TypeScript packages).",
        "source_url": "https://code.claude.com/docs/en/headless",
        "quote": "Use the Agent SDK to run Claude Code programmatically from the CLI, Python, or TypeScript."
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Integrations and security",
      "key": "sso",
      "label": "Single sign-on (SSO)",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Team and Enterprise plans; not on Pro or Max.",
        "source_url": "https://code.claude.com/docs/en/authentication",
        "quote": "Claude for Teams: self-service plan with collaboration features, admin tools, SSO, billing management, and server-managed settings for organization-wide Claude Code configuration."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Integrations and security",
      "key": "two_factor_auth",
      "label": "Two-factor authentication",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Integrations and security",
      "key": "soc2",
      "label": "SOC 2 report",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "SOC 2 Type I and Type II; report available from the Anthropic Trust Center.",
        "source_url": "https://code.claude.com/docs/en/security",
        "quote": "Learn more and access resources (SOC 2 Type 2 report, ISO 27001 certificate, etc.) at Anthropic Trust Center."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Integrations and security",
      "key": "iso27001",
      "label": "ISO 27001 certification",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "ISO 27001:2022; also ISO/IEC 42001:2023.",
        "source_url": "https://support.claude.com/en/articles/10015870-what-certifications-has-anthropic-obtained",
        "quote": "ISO 27001:2022 (Information Security Management)"
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Integrations and security",
      "key": "hipaa",
      "label": "HIPAA compliance offered",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": true,
        "display": "Yes",
        "note": "Enterprise only. Claude Code is under the BAA only when zero data retention is enabled on a qualified account.",
        "source_url": "https://support.claude.com/en/articles/13296973-hipaa-ready-enterprise-plans",
        "quote": "Claude Code is covered under your BAA only with zero data retention (ZDR) enabled, and only on qualified accounts."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Support and company",
      "key": "support_channels",
      "label": "Support channels",
      "type": "text",
      "aider": {
        "value": "GitHub issues, Discord, in-chat /help",
        "display": "GitHub issues, Discord, in-chat /help",
        "note": "/help answers questions about using aider inside the chat, and /report opens a GitHub issue. Privacy questions go to privacy@aider.chat.",
        "source_url": "https://aider.chat/docs/troubleshooting.html",
        "quote": "If you need more help, please check our GitHub issues and file a new issue if your problem isn’t discussed. Or drop into our Discord to chat with us."
      },
      "claude-code": {
        "value": "In-app support messenger (Fin AI bot, then Product Support team) and email",
        "display": "In-app support messenger (Fin AI bot, then Product Support team) and email",
        "note": "No phone or live-chat support. Sales-assisted Enterprise adds customer success at certain spend thresholds.",
        "source_url": "https://support.claude.com/en/articles/9015913-how-to-get-support",
        "quote": "Support is provided in writing through the support messenger and email. We don't offer phone support."
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Support and company",
      "key": "support_24_7",
      "label": "24/7 support",
      "type": "bool",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Support and company",
      "key": "vendor",
      "label": "Vendor (legal entity)",
      "type": "text",
      "aider": {
        "value": "Aider AI LLC",
        "display": "Aider AI LLC",
        "note": "Named in the FAQ and in the privacy policy. The LICENSE file names no copyright holder (the Apache template placeholder is left as is).",
        "source_url": "https://aider.chat/docs/faq.html",
        "quote": "Aider AI LLC is the company behind the aider AI coding tool. Aider is open source and available on GitHub under an Apache 2.0 license."
      },
      "claude-code": {
        "value": "Anthropic, PBC",
        "display": "Anthropic, PBC",
        "note": "Contracting entity is Anthropic Ireland, Limited for customers in the EEA, Switzerland and the UK.",
        "source_url": "https://www.anthropic.com/legal/commercial-terms",
        "quote": "“Anthropic” means Anthropic Ireland, Limited if Customer resides in the European Economic Area (“EEA”), Switzerland or UK, and Anthropic, PBC if Customer resides anywhere else."
      },
      "differs": false,
      "advantage": null
    },
    {
      "group": "Support and company",
      "key": "founded_year",
      "label": "Founded",
      "type": "number",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": 2021,
        "display": "2021",
        "note": null,
        "source_url": "https://www.anthropic.com/events/builder-summit-bengaluru",
        "quote": "Founded in 2021, Anthropic is among the fastest growing tech companies in history."
      },
      "differs": true,
      "advantage": null
    },
    {
      "group": "Support and company",
      "key": "headquarters",
      "label": "Headquarters",
      "type": "text",
      "aider": {
        "value": null,
        "display": "Not documented",
        "note": "Not documented on vendor pages",
        "source_url": null,
        "quote": null
      },
      "claude-code": {
        "value": "San Francisco, California, United States",
        "display": "San Francisco, California, United States",
        "note": "Registered address per the privacy policy, which also states the company is headquartered in the United States.",
        "source_url": "https://www.anthropic.com/legal/privacy",
        "quote": "Anthropic PBC with a registered address at 548 Market St, PMB 90375, San Francisco, CA 94104 (United States)."
      },
      "differs": false,
      "advantage": null
    }
  ],
  "verdicts": [
    {
      "buyer": "Developers who want to pay only for what they use",
      "pick": "aider",
      "pick_name": "Aider",
      "reason": "Aider is free under the Apache 2.0 licence and lists no paid plans; you pay your model provider for usage, with your own API key. Claude's Free plan does not include Claude Code; it starts on Pro at $17 per month billed annually or $20 monthly, and pay-as-you-go use goes through an Anthropic Console API account.",
      "based_on": [
        "free_plan",
        "byok"
      ]
    },
    {
      "buyer": "Developers who want local or non-Anthropic models",
      "pick": "aider",
      "pick_name": "Aider",
      "reason": "Aider connects to almost any model through LiteLLM, including OpenAI, Anthropic, Gemini, DeepSeek and xAI, and to local models through Ollama, LM Studio or any OpenAI-compatible server. Claude Code runs Anthropic's Claude models only and does not support routing to other models.",
      "based_on": [
        "local_models",
        "models_offered",
        "model_choice"
      ]
    },
    {
      "buyer": "Developers who want open-source code that runs entirely on their machine",
      "pick": "aider",
      "pick_name": "Aider",
      "reason": "Aider is Apache 2.0 open source and always runs on your own machine or container; the vendor states it never collects your code, prompts or keys, and with local models inference stays on your infrastructure too. Claude Code's client is proprietary, and its models run on Anthropic or on your Amazon Bedrock, Google Cloud or Microsoft Foundry account.",
      "based_on": [
        "open_source",
        "self_hosted",
        "local_models"
      ]
    },
    {
      "buyer": "Developers staying in VS Code or JetBrains",
      "pick": "claude-code",
      "pick_name": "Claude Code",
      "reason": "Claude Code has a VS Code extension and a JetBrains plugin. Aider's pages point to third-party VS Code plugins and to running aider in an IDE's terminal, or to its watch mode, which acts on AI comments you type in any editor.",
      "based_on": [
        "vscode_extension",
        "jetbrains_plugin"
      ]
    },
    {
      "buyer": "Developers who run agents in the cloud or from a phone",
      "pick": "claude-code",
      "pick_name": "Claude Code",
      "reason": "Claude Code runs cloud sessions that keep going after you close your laptop, and the Claude app for iOS and Android starts, monitors and steers them. Aider runs in your terminal, and its pages document neither cloud agents nor a mobile app.",
      "based_on": [
        "background_agents",
        "ios",
        "android"
      ]
    },
    {
      "buyer": "Teams buying seats",
      "pick": "claude-code",
      "pick_name": "Claude Code",
      "reason": "Claude Code's Team plan is $20 per seat per month billed annually or $25 monthly, for 2 to 150 seats, with SSO and an analytics dashboard for admins. Aider lists no team plan, admin controls or SSO.",
      "based_on": [
        "minimum_seats",
        "sso",
        "admin_dashboard"
      ]
    },
    {
      "buyer": "Security and compliance buyers",
      "pick": "claude-code",
      "pick_name": "Claude Code",
      "reason": "Claude Code documents SOC 2 Type II, ISO 27001:2022 and HIPAA coverage on qualified Enterprise accounts. Aider's pages document no certifications; the vendor states it never collects your code, and your model provider's terms apply to what you send it.",
      "based_on": [
        "soc2",
        "iso27001",
        "hipaa"
      ]
    }
  ]
}