{
 "sym": "Ca",
 "updated": "2026-08-06",
 "verdict": "Claude Code, if you can only hold one \u2014 it leads every satisfaction survey that exists (46% \"most loved\", 91% CSAT), tops the Terminal-Bench 2.1 harness leaderboard, and reached a $2.5B run-rate faster than any dev tool in history. Cursor is the pick when IDE speed matters more than agentic depth; Codex when you want maximum autonomous throughput on a $20 plan; Copilot when enterprise procurement decides; OpenCode when you refuse lock-in.",
 "top5": [
  {
   "rank": 1,
   "name": "Claude Code",
   "maker": "Anthropic",
   "url": "https://claude.com/product/claude-code",
   "docs": "https://code.claude.com/docs",
   "pricing": "Pro $17\u201320/mo \u00b7 Max $100\u2013200/mo \u00b7 Team from $20/seat \u00b7 Enterprise seat + API usage",
   "best_for": "Deep, multi-file agentic work \u2014 architecture, refactors, ship-a-feature-from-a-sentence \u2014 from terminal, IDE, CI, or phone.",
   "why": "Leads every independent satisfaction metric: 46% \"most loved\" vs Cursor's 19% and Copilot's 9%, 91% CSAT, NPS 54 (JetBrains AI Pulse, Jan 2026); 44% of developers choose it specifically for complex tasks; #1 on the Terminal-Bench 2.1 harness leaderboard (83.8%, Jun 2026). $2.5B annualized run-rate by Feb 2026 \u2014 the fastest-scaling dev tool ever.",
   "watch": "Cost at heavy use \u2014 power users outgrow Pro fast and land on Max tiers. Copilot still out-adopts it inside 10,000+-employee orgs.",
   "evidence": [
    {
     "stat": "$2.5B annualized run-rate (Feb 2026)",
     "src": "https://sacra.com/c/anthropic/"
    },
    {
     "stat": "46% most-loved \u00b7 91% CSAT \u00b7 NPS 54 (JetBrains AI Pulse, Jan 2026, 10k+ devs)",
     "src": "https://blog.jetbrains.com/research/2026/04/which-ai-coding-tools-do-developers-actually-use-at-work/"
    },
    {
     "stat": "#1 Terminal-Bench 2.1 harness: Claude Code + Fable 5, 83.8% (Jun 2026)",
     "src": "https://www.tbench.ai/leaderboard/terminal-bench/2.1"
    }
   ],
   "tile_note": "agentic depth, most-loved"
  },
  {
   "rank": 2,
   "name": "Cursor",
   "maker": "Anysphere \u2192 SpaceX (closing Q3 2026)",
   "url": "https://cursor.com",
   "docs": "https://cursor.com/docs",
   "pricing": "Hobby free \u00b7 Pro $20/mo \u00b7 Pro+ $60 \u00b7 Ultra $200 \u00b7 Teams $40/user",
   "best_for": "Founders who live in an IDE and want the fastest inner loop \u2014 tab completion, inline agent edits, and background cloud agents in one polished editor.",
   "why": "The fastest-growing software company on record: $1B ARR (Nov 2025) \u2192 $3B (May 2026), 1M+ paying users, 50,000 enterprise customers \u2014 and the subject of the largest startup acquisition ever, SpaceX's $60B all-stock purchase agreed June 16, 2026.",
   "watch": "Post-acquisition model-routing risk: Cursor depends on Anthropic/Google models and the new owner has its own (Grok). Pricing and limits have changed repeatedly; large complex changes still favor Claude Code/Codex.",
   "evidence": [
    {
     "stat": "$3B ARR by May 2026; $1B Nov 2025",
     "src": "https://en.wikipedia.org/wiki/Cursor_(company)"
    },
    {
     "stat": "SpaceX to acquire Cursor for $60B in stock (Jun 16, 2026; close expected Q3)",
     "src": "https://techcrunch.com/2026/06/16/spacex-to-acquire-cursor-for-60b-in-stock-days-after-blockbuster-ipo/"
    },
    {
     "stat": "19% most-loved \u2014 second overall (JetBrains, Jan 2026)",
     "src": "https://blog.jetbrains.com/research/2026/04/which-ai-coding-tools-do-developers-actually-use-at-work/"
    }
   ],
   "tile_note": "the AI-native IDE"
  },
  {
   "rank": 3,
   "name": "OpenAI Codex",
   "maker": "OpenAI",
   "url": "https://openai.com/codex/",
   "docs": "https://developers.openai.com/codex",
   "pricing": "Bundled with ChatGPT: Plus $20/mo \u00b7 Pro $100\u2013200/mo \u00b7 Business $25/user; token credits since Apr 2026",
   "best_for": "Maximum autonomous task volume per dollar \u2014 parallel cloud agents, background automation, and near-benchmark-top models on a $20 entry.",
   "why": "The volume play: user base exploded from under 1M weekly (Feb 2026) to ~9M (Jul 2026) after the GPT-5.6 launch; business usage grew 6x Jan\u2013Apr 2026; sits within a point of the harness-leaderboard top (Codex + GPT-5.5, 83.1% Terminal-Bench 2.1).",
   "watch": "Capacity strain moves limits under your feet \u2014 context was cut from 372k to 272k tokens during the July surge. OpenAI models only; the IDE-native experience trails Cursor.",
   "evidence": [
    {
     "stat": "~9M weekly users by Jul 15, 2026 (from <1M in Feb)",
     "src": "https://thenewstack.io/gpt-5-6-codex-user-surge/"
    },
    {
     "stat": "Codex + GPT-5.5: 83.1% Terminal-Bench 2.1 (May 2026)",
     "src": "https://www.tbench.ai/leaderboard/terminal-bench/2.1"
    },
    {
     "stat": "6x business/enterprise usage growth Jan\u2013Apr 2026",
     "src": "https://www.getpanto.ai/blog/codex-ai-statistics"
    }
   ],
   "tile_note": "parallel agents, benchmark top"
  },
  {
   "rank": 4,
   "name": "GitHub Copilot",
   "maker": "Microsoft / GitHub",
   "url": "https://github.com/features/copilot",
   "docs": "https://docs.github.com/en/copilot",
   "pricing": "Free tier \u00b7 Pro $10/mo \u00b7 Pro+ $39 \u00b7 Business $19/user \u00b7 Enterprise $39/user; usage-based AI credits since Jun 2026",
   "best_for": "Teams standardized on GitHub \u2014 cheapest paid entry, deepest PR/CI integration, easiest org-wide rollout, 90% of the Fortune 100.",
   "why": "The installed-base king: 4.7M paid subscribers (+75% YoY, Microsoft FY26 Q2), ~42% paid share, 56% adoption in 10,000+-employee orgs. Multi-model (OpenAI, Anthropic, Google) with enterprise policy controls nobody else matches.",
   "watch": "Lowest satisfaction of the leaders \u2014 9% \"most loved\", and 29% workplace usage against 42% paid share implies shelfware seats. The June 2026 usage-based billing shift produced 10\u201350x bill spikes for agentic power users.",
   "evidence": [
    {
     "stat": "4.7M paid subscribers, +75% YoY (Microsoft earnings, Jan 28, 2026)",
     "src": "https://axis-intelligence.com/github-copilot-statistics/"
    },
    {
     "stat": "9% most-loved vs 29% workplace usage (JetBrains, Jan 2026)",
     "src": "https://blog.jetbrains.com/research/2026/04/which-ai-coding-tools-do-developers-actually-use-at-work/"
    },
    {
     "stat": "Usage-based billing backlash: 10\u201350x spikes for power users (Jun 2026)",
     "src": "https://www.techtimes.com/articles/317536/20260601/github-copilot-pricing-change-drives-backlash-agentic-bills-jump-10x-50x-power-users.htm"
    }
   ],
   "tile_note": "the enterprise default"
  },
  {
   "rank": 5,
   "name": "OpenCode",
   "maker": "SST (open source, MIT)",
   "url": "https://opencode.ai",
   "docs": "https://opencode.ai/docs",
   "pricing": "Free, MIT-licensed \u00b7 bring any API key or existing Claude/ChatGPT/Copilot subscription \u00b7 optional pay-per-use Zen gateway",
   "best_for": "Lock-in-averse and cost-sensitive builders who want one agent harness over 75+ model providers \u2014 including open-weight and local models.",
   "why": "The definitive open-source agent: ~190k GitHub stars, ~900 contributors, top write-in of the State of AI 2026 survey (389 mentions). As near-frontier open models close the benchmark gap at a sixth of the cost, a provider-agnostic harness captures that arbitrage in a way no closed subscription can.",
   "watch": "No vendor support \u2014 community only, and quality tracks whatever model you plug in. Unmanaged token spend on premium models can exceed a flat $20 plan.",
   "evidence": [
    {
     "stat": "~190k GitHub stars, ~900 contributors (Aug 2026)",
     "src": "https://github.com/sst/opencode"
    },
    {
     "stat": "Top freeform write-in, State of AI 2026 survey (389 mentions)",
     "src": "https://2026.stateofai.dev/en-US/coding-agents-assistants/"
    },
    {
     "stat": "75+ providers incl. local models; optional per-request Zen gateway",
     "src": "https://opencode.ai/docs/zen"
    }
   ],
   "tile_note": "open-source, any model"
  }
 ],
 "matrix": {
  "cols": [
   "Pricing model",
   "Free tier",
   "Open source",
   "Runs in",
   "Autonomy",
   "MCP",
   "Enterprise",
   "Models"
  ],
  "rows": [
   [
    "Claude Code",
    "Sub + usage",
    "No (trial)",
    "No",
    "Terminal \u00b7 IDE \u00b7 web \u00b7 mobile \u00b7 CI",
    "Agentic + cloud agents",
    "Yes (native)",
    "SSO \u00b7 policy \u00b7 spend",
    "Anthropic"
   ],
   [
    "Cursor",
    "Sub + usage",
    "Yes",
    "No",
    "IDE \u00b7 CLI \u00b7 cloud \u00b7 CI review",
    "Autocomplete \u2192 agentic",
    "Yes",
    "SSO \u00b7 analytics",
    "Multi-model"
   ],
   [
    "OpenAI Codex",
    "ChatGPT sub + credits",
    "Limited",
    "CLI only",
    "CLI \u00b7 IDE ext \u00b7 web \u00b7 cloud",
    "Agentic + parallel",
    "Yes",
    "Via ChatGPT Ent.",
    "OpenAI only"
   ],
   [
    "GitHub Copilot",
    "Sub + credits",
    "Yes",
    "No",
    "Every IDE \u00b7 CLI \u00b7 web \u00b7 CI",
    "Autocomplete \u2192 agentic",
    "Yes (allowlists)",
    "Strongest org policy",
    "Multi-model"
   ],
   [
    "OpenCode",
    "Free + your tokens",
    "Yes (tool)",
    "Yes (MIT)",
    "Terminal \u00b7 desktop \u00b7 IDE \u00b7 CI",
    "Agentic + subagents",
    "Yes",
    "None (community)",
    "75+ providers"
   ],
   [
    "Devin Desktop",
    "Sub + credits",
    "Yes",
    "No",
    "IDE \u00b7 CLI \u00b7 cloud",
    "Agentic + long-running",
    "Yes",
    "Yes",
    "Multi (SWE-1.5+)"
   ],
   [
    "Aider",
    "Free + your tokens",
    "Yes (tool)",
    "Yes (Apache)",
    "Terminal",
    "Pair-programming",
    "Limited",
    "No",
    "Any (BYOK)"
   ],
   [
    "Cline",
    "Free + your tokens",
    "Yes (tool)",
    "Yes (Apache)",
    "VS Code \u00b7 JetBrains \u00b7 CLI",
    "Agentic, approval-gated",
    "Yes + marketplace",
    "Teams tier",
    "Any (BYOK)"
   ]
  ]
 },
 "rules": [
  {
   "if": "Your bottleneck is hard engineering \u2014 architecture, gnarly refactors, multi-repo work",
   "then": "Claude Code. 44% of developers pick it specifically for complex tasks; pair heavy use with the Max tier rather than fighting Pro limits."
  },
  {
   "if": "You live in an editor and the inner loop is everything",
   "then": "Cursor \u2014 accepting the post-SpaceX model-routing uncertainty as the price of the polish."
  },
  {
   "if": "You want maximum autonomous throughput per dollar, or background agents running in parallel",
   "then": "Codex on ChatGPT Plus at $20 \u2014 the cheapest seat at the benchmark top table."
  },
  {
   "if": "Procurement, compliance, or a GitHub-standard org decides for you",
   "then": "Copilot Business \u2014 the 90%-of-Fortune-100 path, with the honest caveat that its own users love it least."
  },
  {
   "if": "You refuse lock-in, run high token volume, or want open-weight models",
   "then": "OpenCode \u2014 free harness, any provider, and the open-model price-performance keeps improving quarterly."
  }
 ],
 "field": [
  {
   "name": "Devin / Devin Desktop",
   "maker": "Cognition",
   "note": "Autonomous cloud engineer + the ex-Windsurf IDE (rebranded Jun 2026); $492M ARR, $26B valuation \u2014 the near-miss for the top 5 mid-rebrand",
   "url": "https://devin.ai",
   "oss": false,
   "entry": "$20/mo + credits",
   "status": "active"
  },
  {
   "name": "Amp",
   "maker": "Amp, Inc. (ex-Sourcegraph)",
   "note": "Frontier agentic CLI, spun out independent Dec 2025; novel ad-supported free tier",
   "url": "https://ampcode.com",
   "oss": false,
   "entry": "usage-based",
   "status": "active"
  },
  {
   "name": "Aider",
   "maker": "community (Apache-2.0)",
   "note": "The original git-native terminal pair programmer; still excellent for structured refactors, momentum slowing",
   "url": "https://aider.chat",
   "oss": true,
   "entry": "free + tokens",
   "status": "active"
  },
  {
   "name": "Cline",
   "maker": "Cline Bot Inc.",
   "note": "Leading open-source agentic VS Code/JetBrains extension (~64k stars) + CLI and SDK",
   "url": "https://cline.bot",
   "oss": true,
   "entry": "free + tokens",
   "status": "active"
  },
  {
   "name": "Kilo Code",
   "maker": "Kilo",
   "note": "Cline+Roo hybrid fork with Architect/Code/Debug modes",
   "url": "https://kilo.ai",
   "oss": true,
   "entry": "free + tokens",
   "status": "active"
  },
  {
   "name": "Zed",
   "maker": "Zed Industries",
   "note": "GPU-fast Rust editor with agentic editing and ACP support",
   "url": "https://zed.dev",
   "oss": true,
   "entry": "free \u00b7 Pro ~$20/mo",
   "status": "active"
  },
  {
   "name": "JetBrains AI / Junie",
   "maker": "JetBrains",
   "note": "AI Assistant + Junie agent across the IntelliJ family; Junie CLI GA Jun 2026",
   "url": "https://www.jetbrains.com/ai/",
   "oss": false,
   "entry": "free \u00b7 Pro $10/mo",
   "status": "active"
  },
  {
   "name": "Antigravity",
   "maker": "Google",
   "note": "Agent-first IDE (Gemini 3), free public preview; Google's flagship after retiring Gemini CLI for individuals",
   "url": "https://antigravity.google",
   "oss": false,
   "entry": "free preview",
   "status": "active"
  },
  {
   "name": "Jules",
   "maker": "Google",
   "note": "Async cloud coding agent, GitHub-connected",
   "url": "https://jules.google",
   "oss": false,
   "entry": "free tier",
   "status": "active"
  },
  {
   "name": "Kiro",
   "maker": "AWS",
   "note": "Spec-driven agentic IDE + CLI \u2014 now AWS's flagship, replacing Amazon Q Developer (EOL Apr 2027)",
   "url": "https://kiro.dev",
   "oss": false,
   "entry": "free \u00b7 Pro $20/mo",
   "status": "active"
  },
  {
   "name": "Factory (Droid)",
   "maker": "Factory AI",
   "note": "Enterprise agent platform (CLI/IDE/Slack); $150M Series C at $1.5B (Apr 2026)",
   "url": "https://factory.ai",
   "oss": false,
   "entry": "usage-based",
   "status": "active"
  },
  {
   "name": "Warp",
   "maker": "Warp",
   "note": "Agentic development environment terminal; core open-sourced 2026",
   "url": "https://warp.dev",
   "oss": true,
   "entry": "free \u00b7 Build $20/mo",
   "status": "active"
  },
  {
   "name": "Trae",
   "maker": "ByteDance",
   "note": "Free-heavy AI IDE with SOLO autonomous mode",
   "url": "https://trae.ai",
   "oss": false,
   "entry": "free \u00b7 Pro ~$10/mo",
   "status": "active"
  },
  {
   "name": "Qodo",
   "maker": "Qodo (ex-Codium)",
   "note": "Code-quality agents for review and testing \u2014 overlaps element Cq",
   "url": "https://qodo.ai",
   "oss": false,
   "entry": "free tier",
   "status": "active"
  },
  {
   "name": "Tabnine",
   "maker": "Tabnine",
   "note": "Privacy-first, air-gap-deployable enterprise assistant; Gartner MQ Visionary (May 2026)",
   "url": "https://tabnine.com",
   "oss": false,
   "entry": "~$39/user/mo",
   "status": "active"
  },
  {
   "name": "Continue",
   "maker": "Continue Dev",
   "note": "Open-source IDE extension + CI-first CLI for headless PR checks",
   "url": "https://continue.dev",
   "oss": true,
   "entry": "free + tokens",
   "status": "active"
  },
  {
   "name": "Goose",
   "maker": "Block \u2192 AAIF foundation",
   "note": "MCP-native local agent framework; ran to 60% of Block internally; foundation-governed since Dec 2025",
   "url": "https://block.github.io/goose/",
   "oss": true,
   "entry": "free + tokens",
   "status": "active"
  },
  {
   "name": "OpenHands",
   "maker": "All Hands AI",
   "note": "Open agent platform (ex-OpenDevin, ~79k stars) with event-sourced replay and CI SDK",
   "url": "https://all-hands.dev",
   "oss": true,
   "entry": "free + tokens",
   "status": "active"
  },
  {
   "name": "Crush",
   "maker": "Charmbracelet",
   "note": "Polished TUI terminal agent in the OpenCode lineage, LSP + MCP",
   "url": "https://charm.land",
   "oss": true,
   "entry": "free + tokens",
   "status": "active"
  },
  {
   "name": "Mistral Vibe",
   "maker": "Mistral AI",
   "note": "Open-source CLI agent + Devstral 2 open-weight coding model",
   "url": "https://mistral.ai",
   "oss": true,
   "entry": "free + tokens",
   "status": "active"
  },
  {
   "name": "Kimi Code CLI",
   "maker": "Moonshot AI",
   "note": "MIT-licensed CLI with coder/explore/plan subagents (Jun 2026)",
   "url": "https://kimi.com",
   "oss": true,
   "entry": "free",
   "status": "active"
  },
  {
   "name": "Grok Build",
   "maker": "xAI",
   "note": "CLI agent with worktree-isolated parallel subagents (May 2026)",
   "url": "https://x.ai",
   "oss": false,
   "entry": "unverified",
   "status": "active"
  },
  {
   "name": "Qwen Code / Qoder",
   "maker": "Alibaba",
   "note": "OSS CLI (BYOK; free hosted tier ended Apr 2026) + Qoder agentic IDE",
   "url": "https://qwen.ai",
   "oss": true,
   "entry": "free + tokens",
   "status": "active"
  },
  {
   "name": "CodeBuddy",
   "maker": "Tencent",
   "note": "IDE + CLI agent on DeepSeek/Hunyuan models",
   "url": "https://codebuddy.ai",
   "oss": false,
   "entry": "free tier",
   "status": "active"
  },
  {
   "name": "Pi / Omp",
   "maker": "community (MIT)",
   "note": "Minimal-core CLI agent wave \u2014 4 tools, sub-1k-token prompt, ~67k stars",
   "url": "https://github.com/badlogic",
   "oss": true,
   "entry": "free + tokens",
   "status": "active"
  },
  {
   "name": "Open Interpreter",
   "maker": "Open Interpreter",
   "note": "Pioneer local code-execution agent; development quiet through 2026",
   "url": "https://openinterpreter.com",
   "oss": true,
   "entry": "free",
   "status": "fading"
  },
  {
   "name": "Gemini CLI",
   "maker": "Google",
   "note": "Free individual access ended Jun 18, 2026 \u2014 enterprise-only via Code Assist; succeeded by Antigravity CLI",
   "url": "https://github.com/google-gemini/gemini-cli",
   "oss": true,
   "entry": "enterprise only",
   "status": "sunsetting"
  },
  {
   "name": "Roo Code",
   "maker": "Roo Code Inc.",
   "note": "Shut down May 15, 2026; team pivoted to Roomote \u2014 successors: Zoo Code, Kilo Code",
   "url": "https://roocode.com",
   "oss": true,
   "entry": "\u2014",
   "status": "dead"
  },
  {
   "name": "Amazon Q Developer",
   "maker": "AWS",
   "note": "Sunsetting into Kiro; signups closed May 2026, end-of-life Apr 30, 2027",
   "url": "https://aws.amazon.com/q/developer/",
   "oss": false,
   "entry": "\u2014",
   "status": "sunsetting"
  },
  {
   "name": "Windsurf",
   "maker": "Cognition",
   "note": "Brand retired Jun 2, 2026 \u2014 became Devin Desktop after the 2025 Google licensing / Cognition acquisition saga",
   "url": "https://devin.ai",
   "oss": false,
   "entry": "\u2014",
   "status": "renamed"
  }
 ],
 "signals": [
  {
   "fact": "AI code-tools market ~$9.35B (2026) \u2192 $29.96B by 2031, 26.2% CAGR",
   "src": "https://www.mordorintelligence.com/industry-reports/artificial-intelligence-code-tools-market"
  },
  {
   "fact": "Cursor: $1B ARR (Nov 2025) \u2192 $3B (May 2026); SpaceX $60B acquisition agreed Jun 16, 2026 \u2014 the largest startup purchase ever",
   "src": "https://techcrunch.com/2026/06/16/spacex-to-acquire-cursor-for-60b-in-stock-days-after-blockbuster-ipo/"
  },
  {
   "fact": "Claude Code: $1B (Nov 2025) \u2192 $2.5B annualized (Feb 2026); majority enterprise",
   "src": "https://sacra.com/c/anthropic/"
  },
  {
   "fact": "Cognition (Devin + ex-Windsurf): $1B raised at $26B post (May 2026); $492M ARR",
   "src": "https://techcrunch.com/2026/05/27/ai-coding-startup-cognition-raises-1b-at-25b-pre-money-valuation/"
  },
  {
   "fact": "Trust gap persists: AI-generated code stalls at a 56% security pass rate (Veracode, Jul 2026); 46% of devs distrust accuracy (Stack Overflow 2025)",
   "src": "https://www.veracode.com/blog/2026-genai-code-security-report-ai-risk/"
  },
  {
   "fact": "2026 structural shift: free tiers retreating (Gemini CLI, Qwen hosted, Amp waitlist), usage-based billing spreading (Copilot, Kiro, Replit), first OSS casualties (Roo Code)",
   "src": "https://blog.arcbjorn.com/state-of-cli-coding-agents-2026"
  }
 ],
 "notes": "Benchmark caveat: model-level leaderboards (e.g. llm-stats) and harness-level leaderboards (tbench.ai, agent+model pairs) disagree on the leader; we cite the harness leaderboard because it measures the product you actually install. Survey caveat: Stack Overflow's 2026 survey opened June 23 and has no published results yet \u2014 anything citing '2026 Stack Overflow results' is recycling 2025 data. App-builders (Lovable, Replit, Bolt, v0) belong to element Vb \u00b7 Vibe Builder, not here.",
 "sources": [
  "https://www.tbench.ai/leaderboard/terminal-bench/2.1",
  "https://blog.jetbrains.com/research/2026/04/which-ai-coding-tools-do-developers-actually-use-at-work/",
  "https://2026.stateofai.dev/en-US/coding-agents-assistants/",
  "https://sacra.com/c/anthropic/",
  "https://en.wikipedia.org/wiki/Cursor_(company)",
  "https://techcrunch.com/2026/06/16/spacex-to-acquire-cursor-for-60b-in-stock-days-after-blockbuster-ipo/",
  "https://techcrunch.com/2026/05/27/ai-coding-startup-cognition-raises-1b-at-25b-pre-money-valuation/",
  "https://axis-intelligence.com/github-copilot-statistics/",
  "https://thenewstack.io/gpt-5-6-codex-user-surge/",
  "https://github.blog/news-insights/company-news/github-copilot-is-moving-to-usage-based-billing/",
  "https://www.veracode.com/blog/2026-genai-code-security-report-ai-risk/",
  "https://blog.arcbjorn.com/state-of-cli-coding-agents-2026",
  "https://www.mordorintelligence.com/industry-reports/artificial-intelligence-code-tools-market",
  "https://survey.stackoverflow.co/2025/ai/",
  "https://opencode.ai/docs",
  "https://claude.com/pricing",
  "https://cursor.com/pricing",
  "https://github.com/features/copilot/plans",
  "https://developers.openai.com/codex"
 ],
 "element": {
  "number": 5,
  "name": "Coding Agent",
  "group": "Build",
  "essential": true,
  "edition": "v2026.Q3",
  "revision": "r7",
  "license": "CC BY 4.0 \u2014 cite elems.ai",
  "url": "https://elems.ai/e/ca.html"
 }
}