Where these 46 reports land
Build it3
Scope it24
Keep it19
Category report
Dev Tools
46 products ranked by how much of their useful core an AI coding agent can reproduce: 3 strong builds, 24 scoped builds, and 19 weak replacements.
How the score breaks down here
- Interface
- 45
- Core workflow
- 43
- Data access
- 40
- Operations
- 27
- Trust & safety
- 42
42/100 average buildability
Why people keep paying here
- scale infra28 of 46 reports
Reliability at the vendor's scale is an operations problem, not a prompt.
- execution polish24 of 46 reports
The last 20 percent is sync, migration fidelity, speed, and edge cases.
- proprietary models23 of 46 reports
Model quality and inference operations are part of the product.
The typical achievable core in this category: build the focused developer workflow you use repeatedly, with local configuration.
Build it
Tower
Tower's solo core is compact: build a repository-local Git client assistant that indexes one codebase, calls one model, proposes diffs, runs tests, and records every change. A competent builder can reach a useful personal version, while the paid product mainly wins on model, context, integration.
Scope it
GitHub Copilot
You can use open-source editor agents and local/API models, but Copilot's value is editor integration, model routing, GitHub context, completions, and managed usage.
Scope it
Uncircle
The core loop · read a yml of processes from the repo, run them, stream logs into terminals, show status dots · is a genuine one-sitting build with node-pty and xterm.js, and mprocs already gives you most of it in a TUI for free. What does not one-shot is everything around it: a native window with tray and notifications, killing whole process trees without orphans on three OSes, crash auto-restart that does not flap, and signed auto-updating builds. And since the paid tier is $19 once rather than a subscription, the usual death-list math barely applies.
Build it
GitKraken
GitKraken's solo core is compact: build a repository-local Git client assistant that indexes one codebase, calls one model, proposes diffs, runs tests, and records every change. A competent builder can reach a useful personal version, while the paid product mainly wins on model, context, integration.
Scope it
Outstand
Writing your own posting service is a contained build, and for the networks with open APIs (Bluesky, Mastodon, Telegram) it genuinely is: a queue, a cron tick, one adapter per network, done. The wall is not code. Instagram, TikTok, YouTube, LinkedIn, and Pinterest each require your own developer app and a platform review before they will accept a single post, X meters writes on a paid tier, and then eleven integrations keep changing under you: token refresh, media specs, rate-limit budgets, deprecated endpoints. You can build the API. You cannot one-shot permission to use it.
Build it
Pieces
Pieces's solo core is compact: build a repository-local developer memory + AI assistant that indexes one codebase, calls one model, proposes diffs, runs tests, and records every change. A competent builder can reach a useful personal version, while the paid product mainly wins on model, context, integration.
Scope it
AdaL
The core loop is genuinely reachable: open-source agents already route across model families, run tools, and edit repos, and a focused implementation of wiring gets you a personal version. What does not fall out of a focused implementation is the harness around the model, which is where AdaL claims its numbers come from, plus browser-based verification, clustered code review, and the team controls. You end up with an agent that works and a noticeably worse recovery rate on long tasks.
Scope it
CodeSpring
The core loop, a mind map that turns feature notes into PRDs and kanban tasks fed to a coding agent, is just structured prompting and file generation, well within reach of a one-shot build. What's missing is the polish: the visual mind-map canvas, MCP/CLI integrations with Claude Code, Cursor and Codex, and the docs search. A DIY version gets you most of the value but with a rougher UI and manual glue between the planning docs and your agent of choice.
Scope it
SharpAPI
Any single endpoint here, summarize a text, categorize a product, parse a resume, is one LLM call with a decent prompt and a JSON schema, so the piece you actually need is often an evening of work. What you will not rebuild in a focused implementation is the catalog: 30+ endpoints with tuned prompts, response contracts that survive model upgrades, an async job queue with polling, and maintained SDKs. Rebuild the two or three endpoints you use, pay when you need the shelf.
Scope it
Skribbl
The canvas is the easy half. React Flow plus xterm.js plus node-pty gets you panning, zooming and half a dozen live agent terminals in a focused implementation, and it is a genuinely nice way to watch a fleet work. The gaps are all in the boring layer underneath: knowing when an agent is actually blocked on you rather than just quiet, keeping sessions alive across a restart or a crash, and counting tokens accurately enough that the number can be trusted. Each of those is days of work on its own, and the focused build reads as finished until the first agent silently dies behind a tab you were not looking at.
Scope it
Cursor
You can assemble VS Code plus open-source agents, but Cursor's moat is editor-native agent UX, model routing, cloud agents, context handling, and rapid product iteration.
Scope it
Replit
A dev container plus code-server plus deployment can replace some value, but Replit's beginner-friendly cloud IDE, agents, secrets, hosting, and zero-setup environment are a platform.
Scope it
Yado
Claude Code was never built to leave the laptop. A chat interface is easy. A terminal into a remote container, also fine. The pain starts when you want Claude, the container, and the app to forget they're three completely distinct entities and behave as one thing: signing in with one tap, when on paper that can only happen in a terminal. A chat, when underneath it is always a terminal. Infra that's fast and that keeps one person's AI away from everyone else's code. I thought that was weeks of work. It was months.
Scope it
GetXAPI
For personal, read-only scale this is genuinely kinda: twscrape plus a throwaway account gets you tweets from a few handles in a contained effort. The gaps are the product: X actively fights automated access, so the DIY version breaks whenever X changes something, burns the accounts it runs on, cannot safely post or DM, has no real-time push, and does not scale. You pay for requests that keep working next week.
Scope it
TranscriptAPI
The happy path is genuinely a one-sitting build: the open-source youtube-transcript-api library fetches a caption track in a few lines, and wrapping it in FastAPI gives you a working personal endpoint. The honest gap is reliability. YouTube rate-limits and IP-blocks caption scraping at any real volume, so the DIY version works until it suddenly does not, and there is no fix without a rotating proxy pool you must rent and operate. The paid product is not selling the parsing; it is selling the unblocked pipe, plus search and playlist endpoints on top.
Scope it
Warp
The visible AI terminal loop is buildable, but a credible replacement needs more than the first screen. Warp earns its keep through model, context, integration, so expect a substantial build and a narrower personal scope.
Scope it
Infracost Cloud
The core developer loop is a credible focused build if the replacement is intentionally narrow: one GitHub App, Terraform on AWS, a small resource catalog, public list prices, basic tag and cost guardrails, and one idempotent pull-request comment. A faithful Infracost Cloud replacement is much harder because the paid product combines broad IaC and multi-cloud coverage with continuously maintained pricing data, policy depth, custom price books, organization-wide visibility, workflows, and enterprise integrations.
Scope it
Linear
The object model is small: issues, states, labels, cycles, projects. A keyboard-first single-player tracker with a board, cycles, and one-way GitHub sync is a contained build. What does not survive the copy is the sync engine, real-time multiplayer, and the integration surface (GitHub two-way, Slack, Figma, Sentry) that make Linear the place a team actually agrees on what is being built.
Scope it
Vapi
A focused inbound agent is a credible contained build with LiveKit Agents or Pipecat. Replacing Vapi as a product is much larger: it combines realtime orchestration, provider abstraction, phone-number and SIP workflows, outbound campaigns, tool calls, testing, observability, scaling, support, and compliance options. Self-hosting can remove Vapi's $0.05 per-minute platform fee, but model, carrier, number, infrastructure, failed-call, monitoring, and engineering costs remain.
Scope it
Wabery
The core loop (send, receive, verify webhooks, retry, inspect conversations) is one-shottable for a single business using Meta's WhatsApp Cloud API. What you cannot one-shot is the reason managed WhatsApp providers exist as products: production messaging infrastructure must stay reliable, secure, monitored, and compliant, while onboarding other businesses requires Meta business verification, app review, and approval for the relevant Tech Provider and Meta Business Partner capabilities. The honest DIY move is to build for your own verified WhatsApp Business Account and phone number; matching Wabery as a multi-tenant provider means operating that infrastructure and completing Meta's approval process.
Scope it
CodeSandbox
You can self-host a browser IDE, but fast templates, previews, cloud VMs, collaboration, and workflow integrations are the product.
Scope it
Aight
A focused multi-backend iPhone prototype is a realistic build when a local companion normalizes each agent protocol, but hardening all four adapters plus Aight's hosted relay, voice, orchestration, sync, and App Store polish is a much larger body of product work.
Scope it
Svix
The core loop here is genuinely small: accept an event, look up subscribed endpoints, sign the payload, POST it, retry on failure with backoff, log the attempt. An agent will produce that in a session, and for a single product sending a few thousand events a day it will work fine. What does not fall out of a one-shot is the boring half: a queue that survives restarts, per-endpoint rate limiting and circuit breaking so one dead customer does not poison your worker pool, replay and manual retry tooling, a portal your customers can log into, and signature schemes that third-party libraries already understand. Svix is also open source, which means the honest DIY move is often self-hosting theirs rather than writing your own. Call it a focused implementation for something you would actually put in front of paying users, and understand that you are now on call for it.
Scope it
TeamViewer
If you only need to reach your own machines, most of TeamViewer's value is reproducible: screen capture, a WebRTC pipe, and synthetic mouse and keyboard events are all solved problems with libraries. An agent can wire that into a working host agent plus browser viewer in a focused implementation, and on your own LAN it will feel fine. What breaks is everything outside your control: connecting through hostile double NAT without your own TURN server, waking a sleeping box, keeping latency sane over mobile networks, and surviving OS permission prompts on macOS after every update. It also stops being a support tool, because the whole point of TeamViewer for helping your parents is that they can install one thing and read you a nine digit number. Build it for your own boxes, keep paying if you support other people's.
Scope it
Composio
If you personally use four apps, not four hundred, most of Composio evaporates. An agent can write you a local MCP server that wraps Gmail, Slack, GitHub and Notion with your own personal access tokens in about a session, and the tool-calling loop works fine. What you are actually buying from Composio is the part nobody enjoys: OAuth app registration per provider, token refresh, per-user credential storage, rate limit handling, and schemas for tools you have not thought of yet. That gets ugly the moment you want more than a handful of integrations, or multiple users, or an OAuth flow instead of a static token you pasted in. Solo and token-based: build it. Multi-tenant or breadth-hungry: pay.
Scope it
Greptile
The mechanical core is genuinely a focused project: a GitHub App that catches pull request webhooks, pulls the diff, retrieves related code from an embedding index of the repo, and posts inline comments from an LLM. You can get to first useful comment with a focused implementation. What you will not get in a focused implementation is signal quality, which is the entire product: knowing when to shut up, not re-flagging the same nit on every push, understanding a monorepo without blowing the context window, and keeping the index fresh without a full reindex on every merge. Expect a bot that is impressive on day one and muted by the team on day nine. Worth building if you own the repo and enjoy tuning prompts; not worth building to save a per-seat fee across a real engineering org.
Scope it
ScreenshotOne
A competent coding agent can build a useful self-hosted screenshot endpoint around Playwright in a contained effort. Matching ScreenshotOne's reliable browser fleet, proxy locations, stealth behavior, maintained blocking rules, videos, and production edge-case handling is a much larger infrastructure product.
Keep it
Zencoder
Do not mistake the interface for the product. Zencoder's durable value is model, context, integration, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.
Keep it
Social Fetch
A personal TikTok or Instagram profile fetcher with Playwright and SQLite is a one-sitting build. Social Fetch is not that. It is kept-alive scrapers on 20+ platforms, proxy routing, anti-bot handling, a stable response schema, and credit metering. Your DIY script breaks when TikTok changes markup. The API bill is for that not being your problem.
Keep it
Qodo
Do not mistake the interface for the product. Qodo's durable value is model, context, integration, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.
Keep it
GitLab Duo
Do not mistake the interface for the product. GitLab Duo's durable value is model, context, integration, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.
Keep it
Bolt.new
A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For Bolt.new, generate and edit a small web project in a local sandbox from structured prompts. The hard boundary is browser sandbox, model orchestration, package execution, deployment, and hosted compute, plus frontier models, context infrastructure, and execution safety.
Keep it
Lovable
The wrapper is easy: a CLI that sends your brief to a model, writes the files, and starts the dev server is the easy part. The model doing the writing is the actual product, and you cannot rebuild that. Everything Lovable puts around it, the hosted preview, the deploy, the database wired up for you, and a non-developer being able to use any of it, goes with the subscription.
Keep it
v0
A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For v0, generate React components from a brief and write them into a local project with previews. The hard boundary is vercel models, design tuning, component data, deployment, and ecosystem integration, plus frontier models, context infrastructure, and execution safety.
Keep it
Windsurf
A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For Windsurf, build a VS Code extension that proposes and applies reviewed multi-file patches. The hard boundary is proprietary coding models, agent context, ide integration, and hosted inference, plus frontier models, context infrastructure, and execution safety.
Keep it
Amazon Q Developer
Do not mistake the interface for the product. Amazon Q Developer's durable value is model, context, integration, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.
Keep it
Augment Code
Do not mistake the interface for the product. Augment Code's durable value is model, context, integration, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.
Keep it
Bito
Do not mistake the interface for the product. Bito's durable value is model, context, integration, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.
Keep it
Blackbox AI
Do not mistake the interface for the product. Blackbox AI's durable value is model, context, integration, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.
Keep it
Devin
Do not mistake the interface for the product. Devin's durable value is model, context, integration, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.
Keep it
Factory
Do not mistake the interface for the product. Factory's durable value is model, context, integration, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.
Keep it
Tabnine
A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For Tabnine, provide local repository completions and chat through a selected model endpoint. The hard boundary is enterprise deployment, private models, ide coverage, governance, and support, plus frontier models, context infrastructure, and execution safety.
Keep it
HikerAPI
The code here is the easy part: instagrapi and friends are open source, and an agent can wrap them in a REST API with a focused implementation. What you cannot one-shot is a farm of aged accounts, residential proxy rotation, fingerprint churn, and a team that patches the client every time Instagram quietly changes an internal endpoint or ships a new challenge flow. Your single account behind your home IP will hit rate limits, then checkpoints, then a permanent ban, usually in that order and usually on the day you need data. A personal build is fine for pulling a few hundred profiles once. It is not fine for anything that has to keep working next month.
Keep it
Google AI Pro
A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For Google AI Pro, build a local assistant client that connects to user-supplied model APIs and stores history. The hard boundary is gemini frontier models, google ecosystem integration, storage bundle, and global infrastructure, plus frontier models, context infrastructure, and execution safety.
Keep it
JetBrains AI Pro
A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For JetBrains AI Pro, build a narrow IDE assistant for code explanation, tests, and reviewed patches. The hard boundary is deep jetbrains ide integration, proprietary models, context, and enterprise tooling, plus frontier models, context infrastructure, and execution safety.
Keep it
Sourcegraph Cody
Do not mistake the interface for the product. Sourcegraph Cody's durable value is model, context, integration, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.