“Claude Code has transformed how we build Giselle. It understands our monorepo architecture, coding conventions, and domain concepts — making implementation feel like pair programming with a senior engineer who knows the entire codebase. Code reviews that used to take hours now take minutes as Claude spots edge cases and suggests improvements. Our development velocity has never been higher. Thank you for building the future of software development!”
AI Coding AgentsMaker says so +1 · source ↗
Claude Code
Anthropic's agentic coding CLI that runs in a terminal, reads and edits a codebase, runs commands, and completes multi-step engineering tasks.
772 makers' products we track use Claude Code. For AI coding agents it's the most chosen of 6 options: 772 of the 909 makers' products we know the AI coding agents of (85%). Among the 657 launched in 2026, 84% chose it, against 87% of those launched in 2024 or earlier. 740 open-source projects also declare it in their code. What makers like most: Holds deep context across large multi-module codebases, so one change can span UI, backend, docs and infrastructure. Their most common complaint: Quality can shift between releases because of harness changes, such as a quietly lowered default reasoning effort. On GitHub, 159 public pull requests moved projects to Claude Code from tools we list, and 116 moved them away.
Profile checked
Works with AI agents:llms.txt- Oct 2026 473 more makers' products found using Claude Code (now 737).
- Oct 2026 Claude Code got 61 new Product Hunt reviews (now 797). source
How makers use Claude Code
Makers' products we track use Claude Code for AI coding agents (772), most often alongside Vercel (26%), Next.js (18%), Resend (16%).
What Claude Code is used for
Claude Code vs the alternatives makers chose
For AI coding agents, 772 of the 909 makers' products we know the choice of picked Claude Code (85%), the most of 6 options. Among those launched in 2026 it's 84%.
| Option | Makers' products | 2026 launches | Free for | Team of 5, 10,000 users | Open source | |
|---|---|---|---|---|---|---|
| 772 85% | 84% | None | $100/mo · Pro | No | ||
| 145 16% | 19% | None | $40/mo · ChatGPT Go | Yes | Compare → | |
| 44 5% | 5% | None | $50/mo · Go | Yes | Compare → | |
| 27 3% | 2% | None | $50/mo · Pro | No | Compare → | |
| 4 0% | 0% | — | — | Yes | ||
| 1 0% | 0% | — | — | Yes |
For AI coding agents: how many of the 909 makers' products we know the AI coding agents of chose each option, and the share among the 657 launched in 2026, since a tool that came first has products from every year, and what each costs for a team of 5 with 10,000 users.
Costs are the cheapest plan that fits, from each vendor's pricing page, at the usage our stack planner assumes for a product with that many users. Free for: the users its cheapest plan a business can use stays free for.
Often paired with
Share of the 772 makers' products on Claude Code that show this choice.Markets that build with it most
Product Hunt markets where Claude Code is in far more of the stacks we know than across every market (15%).
When to use Claude Code, and when not
Pick Claude Code if
- You're comfortable in a terminal and want to hand off whole tasks. AI Coding Agents →
- You already use Claude Code or Codex in the terminal and want it in your editor too. AI Code Editors →
- You already pay for Copilot, Cursor or Claude and want review from the same tool. AI Code Review →
Something else fits better if
- You already pay for ChatGPT: OpenAI Codex.
- You want to switch between model providers freely or keep your tools open source: OpenCode or Pi or goose.
- You want to try a terminal agent without paying for a subscription: Gemini CLI.
- Tasks start as GitHub issues and you want pull requests back without running anything locally: GitHub Copilot or Jules.
- Tasks arrive in Slack, Linear or a ticket tracker and you want an agent to pick them up there: Devin or Factory.
Claude Code is Anthropic's agentic coding tool. You describe a task in plain language, and it reads the codebase, edits files across the project, runs commands such as tests and git, and reports back. The CLI runs on your machine and talks directly to the model API, with no Anthropic backend server or remote index of your code in between.
More about Claude Code
It comes as a terminal CLI for macOS, Linux and Windows (native or WSL), an extension for VS Code and Cursor, a JetBrains plugin, a desktop app, and a web version at claude.ai/code where sessions run in the cloud. In manual mode it asks before editing files or running commands; auto mode lets a classifier approve safe actions instead, and an optional sandbox isolates shell commands from the filesystem and network. Project instructions live in CLAUDE.md (it can also read AGENTS.md), and you extend it with MCP servers, skills, hooks and plugins.
You sign in with a Claude subscription or an Anthropic Console API key. The CLI, VS Code and JetBrains integrations also run against Amazon Bedrock, Google Cloud or Microsoft Foundry, which lets a company bill and keep inference in its own cloud account. Web sessions handle long tasks in parallel, including on repositories you don't have locally.
It needs an internet connection and works only in Anthropic's supported countries. Command sandboxing needs WSL 2 rather than native Windows, and on consumer plans your sessions can be used for training unless you turn that setting off.
Claude Code pros and cons
What makers like most: Holds deep context across large multi-module codebases, so one change can span UI, backend, docs and infrastructure. Their most common complaint: Quality can shift between releases because of harness changes, such as a quietly lowered default reasoning effort.
Pros
- Holds deep context across large multi-module codebases, so one change can span UI, backend, docs and infrastructure. PHPH 2PH 3PH 4
- Carries complex multi-step tasks through end to end, such as waiting on CI, reading logs and iterating until green. PHHNHN 2PH 2
- Hooks, skills, subagents, plugins and MCP make it a host that teams extend and build products on. PHPH 2HNPH 3
- Subscription plans give much more usage than the same money spent on API tokens. HNHN 2HN 3
Cons and watch-outs
- Quality can shift between releases because of harness changes, such as a quietly lowered default reasoning effort. HNHN 2HN 3HN 4
- Subagents are opaque and hard to steer, and the default setup feels heavy, so power users strip tools and prompts. HNHN 2HN 3HN 4
- The subscription only works inside Claude Code, not in other harnesses people prefer. HNHN 2HN 3
- The CLI is resource hungry, using hundreds of megabytes of RAM per idle session. HNHN 2
Themes that recur in makers' words and Hacker News comments, each linked to what it summarises, with how Product Hunt tags its reviews.
5.0★ from 797 reviews on Product Hunt ↗What Hacker News says about Claude Code
On Hacker News, 22% of comments about Claude Code recommend it and 25% criticize it: net praise −4%, 8th best liked of 9 tools HN discusses for AI coding agents. Commenters chose it 2.3× as often per month in 2026 as in 2025.
By year
| Year | Comments choosing it, per month | Net praise |
|---|---|---|
| 2025 | 87 | +12% |
| 2026 (8 mo) | 200 | −12% |
In their words
- “I've built some amazing things, when 1 Million tokens dropped, that was peak Claude Code for me” HN, Apr 2026
- “This trip has been nothing BUT fun for me!” HN, Jun 2026
- “I’ve been fighting Claude Code’s attempts to put everything in memory lately” HN, Apr 2026
Hacker News comments January 2023 to August 2026 that name Claude Code in a sentence like "I use" or "we moved to", Claude read a sample of 50 and the counts scale it to all of them; net praise is comments recommending it minus comments criticizing it, as a share of all comments about it. How it's counted, and how HN compares with makers.
Reliability and open issues
Claude Code's status page posted 33+ incidents in the last 90 days, 16 major.
Incidents on its status page
33+ in the last 90 days, 16 major · 33+ in the last year- major Elevated errors for Claude Opus 5.5 Oct 2026
- major Elevated errors for Claude Mythos 5.1 and Claude Fable 5.1 Oct 2026
- major Elevated errors on claude.ai, Claude Code, Claude Cowork and the Claude API Sep 2026
Who switches
More projects move to Claude Code: 159 pull requests in, 116 out; the most come from Cursor and leave for OpenCode.
Cursor → Claude Code48 PRs
- [Common] Migrating the Cursor rules and commands to Claude Codea1exevs/set-forge · 2026-09-29
- Move agent guidance from Cursor rules to Claude Codeadam-tabaczynski/eggs-delivery-system · 2026-09-26
- Port .cursor skills and branch-safety rule to Claude Codeninadrathod/local-studio · 2026-09-22
- Migrate PR review guidelines from Cursor BugBot to Claude Code Reviewduckduckgo/apple-browsers · 2026-09-21
- chore/ACCT-0/ACCT-0/Port Cursor rules and skills to Claude Code config.omids0/accounting-with-google-sheet · 2026-09-19
- Fill in CLAUDE.md and migrate Cursor framework to Claude CodeReforMan/Personal-Professional-Website · 2026-09-15
- fix(ci): allow the cursor bot to trigger Claude Code ReviewWebFirstLanguage/wfl · 2026-08-31
- Allow Cursor bot to trigger Claude Code Reviewyjsoon/howmuch · 2026-08-22
- Vendor nine pstack skills, ported from Cursor to Claude Codegaryyau/agent-setup · 2026-08-20
- Port Cursor pstack and thermos agent stack to Claude Code as kaizen-modepragmaticivan/dotfiles · 2026-08-17
OpenAI Codex → Claude Code43+ PRs
- docs(blog): enlarge pro plan reopening meme in Codex to Claude Code posthon454/hon454.github.io · 2026-10-01
- docs(blog): remove image captions from Codex to Claude Code posthon454/hon454.github.io · 2026-10-01
- docs: add Codex to Claude Code desktop experience posthon454/hon454.github.io · 2026-10-01
- Add OpenAI Codex plugin marketplace to Claude Code project settingsbrandohermoso47-rgb/cliente-vault-web-app · 2026-10-01
- fix(agents): hold Codex to Claude Code's parity — kept to the browser, reading images, follow-ups that reach the model on both, and a Claude run that cannot silently lose its toolsimshaikot/browsentic · 2026-09-27
- Port Codex Mobile for Termux to Claude Codehoangkien1703/claude-mobile-termux · 2026-09-25
- Rename to WoW AI and add Codex and Grok next to Claude Codechelinho139/wow-ai · 2026-09-24
- feat: Codex as a second agent next to Claude CodeViperwow/erindi · 2026-09-24
- Switch from Codex to Claude Code and define engineer development goalsyabukichi-lab/incident-ai-assistant · 2026-09-13
- Name the Codex marketplace b-open-io to match Claude Code [OPL-4679]b-open-io/claude-plugins · 2026-09-11
GitHub Copilot → Claude Code40 PRs
- chore: migrate Copilot instructions to Claude Code setupALCops/RoslynTestKit · 2026-09-19
- chore: migrate Copilot instructions to Claude Code setupcezarypiatek/RoslynTestKit · 2026-09-19
- Migrate Copilot instructions to Claude Coderobjackstewart/payment-manager · 2026-09-14
- chore: migrate AI-assisted workflows from GitHub Copilot to Claude Codekhaines/deltasharp · 2026-09-07
- ci: automatically return Copilot fix decisions to Claude Codehide212131/hane · 2026-09-05
- chore: migrate Copilot instructions to Claude Code .claude/ setupALCops/Analyzers · 2026-08-26
- feat(copilot): bring GitHub Copilot CLI to parity with Claude Codejmuise/dotfiles · 2026-08-21
- feat(home): auto-bind Copilot key (F23) to the Claude Code launcher on KDE hostspalazzem/hanzo · 2026-08-17
- chore: migrate Copilot instructions to Claude Code native setupaxsaucedo/kaos · 2026-08-15
- Migrate agent instructions from Copilot to Claude Codeenigmatry/entry-angular-building-blocks · 2026-08-05
OpenCode → Claude Code28 PRs
- ✨ feat(agents): support codex and opencode next to claude codevcmf/minmux · 2026-10-01
- chore: migrate project config from OpenCode to Claude Codepshevche/act-test-runner · 2026-09-07
- feat(claude): migrate opencode config to claude codeian-cq/dotfiles · 2026-09-05
- chore: migrate agent tooling from Copilot CLI/OpenCode to Claude Codeajrussellaudio/dotfiles · 2026-08-10
- Add opencode config to mirror Claude Code setuprishid/dotfiles · 2026-07-29
- Port multi-ai-review engine from opencode to a Claude Code CLI + skillMathieuDoyon/cc-multi-ai-review · 2026-07-15
- feat(ai): migrate from OpenCode to Claude Codeghostkernel-core/ARCRunner · 2026-07-06
- feat(ai): migrate from OpenCode to Claude CodeAutomationNexus/MediaRefinery · 2026-07-06
- feat(ai): migrate from OpenCode to Claude CodeAutomationNexus/ModelDeck · 2026-07-06
- feat(ai): migrate org AI tooling from OpenCode to Claude CodeAutomationNexus/.github · 2026-07-06
Claude Code → OpenCode44 PRs
- Switch flightdeck from Claude Code to OpenCode V2alexkorotkikh/flightdeck · 2026-09-26
- fix: port brooks-lint bundle from Claude Code to OpenCodeWilliam-Dennis/python-template · 2026-09-18
- Fix Claude Code session forwarding to OpenCodeAlishahryar1/free-claude-code · 2026-09-07
- chore(migration): migrate Claude Code setup to opencodesapientpants/doctrans · 2026-08-26
- chore(tooling): migrate coding setup from Claude Code to opencodeaxelwaserman/travel_pal · 2026-08-25
- Add safe Claude Code to OpenCode migrationsjh9714/dsh-movein · 2026-08-22
- Port execution engine from Claude Code to opencodecomputer-reinvention/soren · 2026-08-16
- fix: migrate Claude Code workflows to OpenCode (DeepSeek V4 Flash)silvertakana/worldwideview · 2026-08-04
- feat: migrate from Claude Code plugin to opencode distribution (Phase…shahboura/ai-sdlc-harness-opencode · 2026-07-14
- feat: enable Claude Code push notifications and add Figma MCP to OpenCodevidbina/dotfiles · 2026-07-09
Claude Code → OpenAI Codex34+ PRs
- Migrate repository guidance from Claude Code to Codexyuru-sha/fuji-calendar · 2026-10-02
- chore: migrate Claude Code workflow to CodexJoycai/Jellyfin-Media-Management-Tool · 2026-10-01
- feat: add live Claude Code to Codex context handoff pathavaargsh/agent-control-plane · 2026-10-01
- Migrate project agent workflow from Claude Code to CodexJoycai/Joycai-Image-Ai-Toolkits · 2026-10-01
- Add post on switching from Claude Code to Codexnninnis/nninnis.github.io · 2026-09-22
- Confine Claude Code runs to the grants Codex getsdark-factory-build/dark-factory · 2026-09-20
- Prototype Claude Code delegation to metered native Codex workersgremlord/gremlord · 2026-09-17
- chore: migrate Claude Code skills to Codexbentleypark/aiwatch · 2026-09-04
- Change first slide title from Claude Code to Codexnarze/claude-code-in-the-cloud-slides · 2026-08-26
- Migrate Claude Code configuration to Codexrjdellecese/confect · 2026-08-24
Claude Code → GitHub Copilot28 PRs
- feat(claude): bring the Claude Code workflow to parity with Copilotkkelvekar/ubs-am-plt-snapshot · 2026-08-21
- Port Claude Code Setup to GitHub Copilotfukuda-yuki/copilot-setup-advisor · 2026-08-06
- [Chore] Remove Claude Code review workflow, switch to GitHub Copilot code reviewfumetothemoon/OhanaMeansFamily · 2026-08-04
- Convert Power Platform skills from Claude Code to GitHub Copilot compatibilitybryanmorris-eaton/GithubCopilot-power-platform-skills · 2026-07-23
- Convert skills from Claude Code to GitHub Copilot compatibility; fix …DanielKerridge/claude-code-power-platform-skills · 2026-07-23
- Migrate routine compute from Claude Code CLI to Copilot Agent Tasks APIwillregelmann/physagent · 2026-07-12
- feat: migrate BarcaTeam harness from Claude Code to GitHub Copilot CLIrbarcelos/BarcaTeam · 2026-07-06
- feat(copilot-port): port Claude Code harness to VS Code Copilot configerikunha/portfolio · 2026-05-19
- Migrate dotfiles from Claude Code to GitHub Copilot CLIalexwaibel/dotfiles-work · 2026-05-11
- Migrate from Claude Code plugins to GitHub Copilot agent skillstk0miya/skills · 2026-04-27
Claude Code → Cursor10 PRs
- feat(cursor): carry the Claude Code harness over to Cursorroesti77/dotfiles · 2026-09-08
- Convert copilot from a Claude Code plugin to a Cursor pluginbernardoforcillo/copilot · 2026-09-07
- feature: add Fable 5.1 and Mythos 5.1 to the Claude Code model list; Fable 5.1 to the Cursor catalogalamops/agetor · 2026-09-02
- feat: swap constitution-guardian from Claude Code Action to Cursor Agentdavidconvotis/field-ops · 2026-07-14
- chore(agents): commit Claude Code guardrails symmetric to the Cursor hooksnozomi-koborinai/terradart · 2026-07-02
- Add cursor plugin — delegate Claude Code tasks to Cursor CLI (Composer 2)ananddtyagi/cc-marketplace · 2026-05-31
- Port Claude Code skills and rules to Cursor commandsjeffreese/ts-media-server · 2026-04-12
- Add relay for Claude Code instructions to Cursor as source of truthecosia/ios-browser · 2026-03-24
- map claude code skills to cursor rulesoxy-hq/skills · 2026-02-08
- Migrate from Claude Code to Cursorfox-corp/Cursor-RLM-Example · 2026-01-27
Public pull requests on GitHub since Oct 2024 whose title says "X to Y" — real code changes moving a project from one tool to another, by developers in general.
Apps built with Claude Code
772 makers' products, each linked to the source that shows it, and 740 open-source projects that declare it in their code. The best known on Product Hunt: Raycast (35,521 followers), Happycapy (6,371 followers), Locofy.ai (4,240 followers), Chronicle (3,751 followers), daily.dev (3,452 followers). 2 of the makers' products are gone now (domain lapsed, up for sale or taken down); they chose Claude Code while live.
“Claude Code helps our engineering team move faster inside the actual repo. It is especially useful for debugging, refactoring, writing tests, and getting oriented in complex code without constantly switching contexts.”
AI Coding AgentsMaker says so +1 · source ↗“Couldn't do this without Claude”
AI Coding AgentsMaker says so +1 · source ↗“We use Claude Code to build Superset. It is also one of the terminal agents our users can orchestrate from Superset on desktop and iPhone.”
AI Coding AgentsMaker says so +1 · source ↗“Thanks for helping us build the website that fast!”
AI Coding AgentsMaker says so +1 · source ↗“We greatly appreciate the team at Anthropic for the Claude family of models (especially Opus and Fable), which have become a common part of our dev toolset.”
AI Coding AgentsMaker says so +1 · source ↗“Nimbalyst is built with Claude Code and helps you build with Claude Code.”
AI Coding AgentsMaker says so +1 · source ↗“Claude Code is how we build MindPal itself.”
AI Coding AgentsMaker says so · source ↗“Skills to design and optimize metrics easily - Can refer to skills here: https://github.com/cekura-ai/cla...”
AI Coding AgentsMaker says so · source ↗“Best model to code, we use it 24/7.”
AI Coding AgentsMaker says so · source ↗“Claude Code with Opus is the backbone of my development workflow. The depth of context it provides across a complex, multi-module platform like BrandingStudio.ai is genuinely unmatched; it has significantly accelerated my build and continues to power my iteration speed.”
AI Coding AgentsMaker says so · source ↗“We build Hindsight with Claude Code every day, across a Python API, a Next.js UI and a Rust storage engine. It also became our favourite memory testbed: the Hindsight plugin gives Claude Code long-term memory across sessions, so it remembers past fixes, incidents and conventions instead of rediscovering them.”
AI Coding AgentsMaker says so · source ↗“We tried Cursor and moved to Claude Code, it's just fit how we build better. The skills piece is the difference, we can teach it our own patterns and it actually holds them across the codebase. Tip - Invest early in setting up your own skills instead of using it out of the box. The more you teach it how your codebase actually works, the more it feels like a teammate who knows your patterns rather than a generic autocomplete.”
AI Coding AgentsMaker says so · source ↗“Internally, some team members refer to Claude code as our virtual CTO. Code improvements, suggestions, and quick bulk fixes are all handled by Claude code.”
AI Coding AgentsMaker says so · source ↗“Claude built most of PH ask why we watched”
AI Coding AgentsMaker says so · source ↗“One of the AI tools power our code base”
AI Coding AgentsMaker says so · source ↗“Our agents use Claude Code to build great AI training pipelines with the Lightning Rod SDK.”
AI Coding AgentsMaker says so · source ↗“Our agent uses it to build the automations”
AI Coding AgentsMaker says so · source ↗“We build HarnessRouter with Claude Code, and HarnessRouter runs Claude Code as a product backend for other teams. It is both our daily driver and one of the harnesses we route to.”
AI Coding AgentsMaker says so · source ↗“Claude Code has become a core part of how we build Chronicle. It helps us move quickly from ideas to working features, assisting with everything from prototyping to debugging, while keeping engineers focused on the bigger architectural decisions.”
AI Coding AgentsMaker says so · source ↗“The best coding agent! It drastically helps us accelerate our development.”
AI Coding AgentsMaker says so · source ↗“Claude Code is one of the agent engines behind MausBot. We bring its local CLI into a chat interface, so users can give a bot a job, follow its work and handle approval requests in the conversation using their supported Claude account.”
AI Coding AgentsMaker says so · source ↗“MCP Connectors means implementing an open protocol correctly: parsing tool schemas from any server a user points us to, handling three different auth flows (OAuth, API key, bearer token), and building permission logic that fails safe by default, since this feature can give an AI real access to a CRM, a support desk, or an inbox. That's well-scoped, spec-driven engineering work. We built the connector framework with Claude Code, working through the MCP spec and the edge cases (malformed schemas, expired tokens, servers that don't return what they promise) fast enough to ship a working connector framework, official connectors, and a custom connector option in the same release.”
AI Coding AgentsMaker says so · source ↗“Superior code generation and reasoning capabilities accelerated our development significantly—Claude Code became an essential part of our workflow.”
AI Coding AgentsMaker says so · source ↗“the AI coding agent Kane CLI plugs into as a verification skill.”
AI Coding AgentsMaker says so · source ↗“very helpful for enabling us to make the best router possible!”
AI Coding AgentsMaker says so · source ↗“It handles a large codebase better than anything else we tried, which was most of what we needed.”
AI Coding AgentsMaker says so · source ↗“ClientJam was built solo — with Claude Code as my pair-programmer the whole way. It wasn't "AI wrote my app" so much as a constant collaborator that let one person move like a small team”
AI Coding AgentsMaker says so · source ↗“Couldn't iterate so quickly on disco without Claude Code, especially made accessible via github workflows.”
AI Coding AgentsMaker says so · source ↗“The productivity boost Claude Code provides has been nothing short of amazing. What I was able to accomplish in 5 months with a $140 Claude Pro Max subscription would've cost $30-50K to hire a developer or a year of work if I coded it myself.”
AI Coding AgentsMaker says so · source ↗“Handles huge files and long codebases without breaking a sweat. I prefer it for reasoning-heavy coding tasks over other AI editors.”
AI Coding AgentsMaker says so · source ↗“We compliment Claude Code with our security solution built for vibe-coders using the platform.”
AI Coding AgentsMaker says so · source ↗“Used Claude Code for most of the repetitive dev tasks — writing components, debugging build errors, fixing API routes, and iterating fast on UI changes. What makes it better than alternatives is the deep codebase awareness. It doesn't just look at one file — it understands how everything connects. You say "fix the download button" and it knows which file, which state, which route. Cursor and Copilot feel like autocomplete in comparison. This feels like pair programming with someone who's actually read your code.”
AI Coding AgentsMaker says so · source ↗“Our team uses it to ship code, research, and marketing work in the same workspace.”
AI Coding AgentsMaker says so · source ↗“Best reasoning for complex codebases. Opus handles multi-file refactors that others can't.”
AI Coding AgentsMaker says so · source ↗“Claude code inspired us to make this tool”
AI Coding AgentsMaker says so · source ↗“For all things coding”
AI Coding AgentsMaker says so · source ↗“The best AI coding agent”
AI Coding AgentsMaker says so · source ↗“Our token compression technology has to be compatible and efficient with Claude Code, so we have to use it extensively to understand how we can optimize its context.”
AI Coding AgentsMaker says so · source ↗“The main AI assistant for developing Extra Thursday. imo claude code >> codex”
AI Coding AgentsMaker says so · source ↗“E2E execution of complex tasks by CC is unmatched”
AI Coding AgentsMaker says so · source ↗“Helped us build this TUI faster. Having an AI agent that understands terminal workflows, can write and test code in context, and knows Playwright made development significantly smoother.”
AI Coding AgentsMaker says so · source ↗“It's the one that works against our actual repo and internal docs rather than a chat window, which means I get finished work back instead of suggestions to implement. I use it far outside engineering - investor updates, monthly customer analytics reports, launch copy, contract review. The gap between "assistant" and "does the task" is the whole thing.”
AI Coding AgentsMaker says so · source ↗“Claude Code is how we build AgentCard. It's also one of our most popular integrations — agents using Claude Code can create and use virtual cards through MCP without leaving the terminal. We use it, we build for it.”
AI Coding AgentsMaker says so · source ↗“Built the whole thing with Claude Code, in the terminal, next to the codebase. The difference from autocomplete is that it argues back about the design before writing it.”
AI Coding AgentsMaker says so · source ↗None of these in makers' own words.
Open source: a project that declares Claude Code as a dependency in its public code — verifiable, but not necessarily a live product.
What its projects tell coding agents
What open-source projects' AGENTS.md and CLAUDE.md files say about Claude Code, in our words — from the 164 files that name it:
Instruction file exists to give Claude Code guidance whenever it works in the repository.62 files
Arize-ai/openinferenceAudiusProject/appsFoundry376/MailspringHEIGE-PCloud/DoItLeantime/leantimeMiguelsPizza/WebMCPMotleyAI/motleycrewNitrino/easysubsNyanNyanovich/nyanPrismer-AI/PrismerStarTrail-org/LEANNTideDra/zotero-arxiv-dailyTriliumNext/TriliumUI5/webcomponents-reactViewTube/viewtubeViren070/AIOStreamsYunYouJun/cookactionbook/actionbookaipotheosis-labs/acialgorithmicsuperintelligence/openevolveapconw/Aix-DBavgupta456/statboticsbasnijholt/agent-clibenadida/helios-serverc9s/bbgochinchang/web-makerchrisvel/tududicontainers/ramalamacube-js/cubecunla/fakeredis-pyecency/vision-mobileesm7/obsidian-map-viewferdium/ferdium-appfredrikburmester/streamystatsgladly-team/tabguaguaguaxia/weekly_reporthaunchen/n8n-skillshhyqhh/inno-agentisucon/isucon9-qualifyjihe520/MathModelAgentjin-bo/agentaojosephgoksu/prime-nestjsk1LoW/molmnr-ai/lmnrlucafaggianelli/plomberylukevella/ralllymattogodoy/nametagmicrosoft/Agent365-Samplesminusxai/minusx-metabasenamespace-ee/upcountnextflow-io/nextflownounsDAO/nouns-monorepooekazuma/svelte-meta-tagsohcnetwork/careplastic-labs/honchoplatformatic/platformaticreact-native-progress-view/progress-viewrecruit-tech/location-staterobotostudio/turbo-start-sanitysebastienheyd/boilerplatetfriedel/claude-office-skillstom-james-watson/breaktimer-appOne shared agent file is written for Claude Code, Codex, Cursor, and Copilot alike.17 files
Cap-go/capgo.appGetBindu/BinduMemTensor/MemOSNVIDIA/NeMo-RetrieverYoungCan-Wang/WyckoffTradingAgentZIZKA-AI-SL/ZizkaDBauthorizerdev/authorizerchrishayuk/larqldeadlock-mod-manager/deadlock-mod-managerfeast-dev/feastlearningequality/kolibrilithops-cloud/lithopsmudler/LocalAIomnigent-ai/omnigentopenaustralia/planningalertsresponsibleai/ASSERTrsclaw-ai/rsclawCLAUDE.md is a thin adapter that only imports AGENTS.md, which stays the canonical file.7 files
Do not add Claude Code attribution or generated-with footers to commits or pull requests.6 files
Skills live in a shared skills directory that .claude/skills links to.5 files
Claude Code hooks enforce checks or set up the environment at edit or session time.3 files
518 of the 544 open-source products built with Claude Code that were worked on in the last 180 days keep instruction files for coding agents — 95%, against 53% of all the projects we read. AGENTS.md is in 390, CLAUDE.md in 462.
Alternatives to Claude Code
All alternatives by situation →Further reading
Questions makers ask about Claude Code
Is Claude Code good for production?
772 makers' products we track run on it, and 2 of them have since gone (the product, not necessarily because of Claude Code). Its own status page posted 33+ incidents in the last 90 days, 16 of them major; vendors decide what they post there, so this doesn't compare across tools. On GitHub, 159 public pull requests moved projects to Claude Code from tools we list, and 116 moved them away. The watch-out makers raise most: Quality can shift between releases because of harness changes, such as a quietly lowered default reasoning effort.
What is Claude Code used for?
Anthropic's agentic coding CLI that runs in a terminal, reads and edits a codebase, runs commands, and completes multi-step engineering tasks. Makers' products we track use it for AI coding agents (772).
What are the pros and cons of Claude Code?
Pros makers name: Holds deep context across large multi-module codebases, so one change can span UI, backend, docs and infrastructure. Carries complex multi-step tasks through end to end, such as waiting on CI, reading logs and iterating until green. Hooks, skills, subagents, plugins and MCP make it a host that teams extend and build products on. Cons: Quality can shift between releases because of harness changes, such as a quietly lowered default reasoning effort. Subagents are opaque and hard to steer, and the default setup feels heavy, so power users strip tools and prompts. The subscription only works inside Claude Code, not in other harnesses people prefer.
What are the alternatives to Claude Code?
For AI coding agents, the other options makers' products we track chose most are OpenAI Codex (145), OpenCode (44), GitHub Copilot (27), Pi (4), Aider (1). Open source or self-hostable among them: OpenAI Codex, OpenCode, Pi, Aider. Each alternative, with the situation it fits, is on the Claude Code alternatives page.
Is Claude Code still popular with new products?
About as much as before: among the 657 makers' products launched in 2026 that made the AI coding agents choice, 84% chose Claude Code, against 87% of the 62 launched in 2024 or earlier.
How much does Claude Code cost per month?
For a team of 5 with 10,000 users, Claude Code costs $100 a month on the cheapest plan that fits (Pro), from its pricing page.
Do developers switch to or away from Claude Code?
On GitHub, 159 public pull requests moved projects to Claude Code from tools we list, most from Cursor (48), OpenAI Codex (43), GitHub Copilot (40); 116 moved them away, most to OpenCode (44), OpenAI Codex (34), GitHub Copilot (28).
When should you use Claude Code?
You're comfortable in a terminal and want to hand off whole tasks (AI coding agents). You already use Claude Code or Codex in the terminal and want it in your editor too (AI code editors). You already pay for Copilot, Cursor or Claude and want review from the same tool (AI code review). Something else fits better if: you already pay for ChatGPT, pick OpenAI Codex; you want to switch between model providers freely or keep your tools open source, pick OpenCode or Pi or goose.
Does it work in VS Code or JetBrains IDEs?
Yes. There is an extension for VS Code (also installable in Cursor) and a plugin for IntelliJ IDEA, PyCharm, WebStorm and other JetBrains IDEs; the JetBrains plugin needs the Claude Code CLI installed separately. source ↗
Is my code used to train Anthropic's models?
On Free, Pro and Max plans it depends on your privacy setting, and data is used for training only when that setting is on. Under commercial terms (Team, Enterprise, API and cloud platforms) Anthropic does not train on your code or prompts unless your organization opts in. source ↗
Where does my code go?
Claude Code runs locally and sends your prompts and the model's outputs to the model API over TLS. There is no separate Anthropic server holding an index of your repository. source ↗
Can we run it through AWS, Google Cloud or Azure?
Yes. It supports Amazon Bedrock, Google Cloud's Agent Platform and Microsoft Foundry, using their regions, credentials and billing, and you can route traffic through a corporate proxy or LLM gateway. source ↗
Does it run on Windows?
Yes, natively from PowerShell or CMD, or inside WSL. Command sandboxing is only supported under WSL 2, and Git for Windows is recommended for native installs so it can use Bash. source ↗
Can it work offline?
No. It requires an internet connection and is available only in Anthropic's supported countries. source ↗
Does it read AGENTS.md?
Yes. Alongside CLAUDE.md files, Claude Code can load AGENTS.md, so one instruction file can be shared with other coding tools. source ↗
Is Claude Code free?
No permanent free tier; paid use starts at $20/mo. source ↗
Is Claude Code open source or self-hostable?
Not open source, and hosted only.
Can AI coding agents work with Claude Code?
It serves an llms.txt docs index.
Who uses Claude Code?
772 makers' products we track, each with a source, and 740 open-source projects declare it in their code. The best known of them on Product Hunt: Raycast (35,521 followers), Happycapy (6,371 followers), Locofy.ai (4,240 followers), Chronicle (3,751 followers), daily.dev (3,452 followers). source ↗