Seven open-source repositories are routinely presented as ready-made businesses, each with a price attached. The repositories are excellent. The prices are real market rates. The gap between them is the entire job — and it is where the money actually goes.
- All seven are real, maintained, and genuinely capable of the work described.
- Every quoted price is a real rate for the service. None is a rate for running the software.
- Two are AGPL-3.0. That changes what you can build on them and is almost never mentioned.
- API costs consume 30–50% of margin on this class of work.
- Several of these projects tell you in their own README to use the paid version in production.
A working assessment of seven repositories that keep appearing in "start an AI agency" lists — what each one actually does, what licence it carries, and what it costs to run as a business. Every figure carries its source and the date it was checked.
The seven repositories
Each of these is a serious project with real adoption. The column that matters is the third one.
| Repository | Sold as | What it actually takes |
|---|---|---|
| pipecat-ai/pipecatBSD-2 · ~13.9k stars | Voice agent, $8,000 | A real-time voice framework, and a good one. It does not include speech-to-text, text-to-speech or telephony — those are separate paid services, and they are where the per-minute cost lives. |
| cline/clineApache-2.0 · ~63.9k stars | Client website, $5,000 | A capable coding agent that genuinely accelerates a developer. It does not replace one. Published vulnerability rates in AI-generated code run 25–62% depending on model and language. |
| gitroomhq/postiz-appAGPL-3.0 · ~34.7k stars | Social retainer, $2,000 | A solid scheduler. Scheduling is the least valuable part of social work — clients pay for judgement about what to post. AGPL licensed. |
| Mintplex-Labs/anything-llmMIT · ~64.6k stars | RAG setup, $3,500 | Genuinely strong, multi-user, Claude-compatible. The work is not installing it — it is the client's documents, which arrive unstructured and contradictory. |
| crewAIInc/crewAIMIT · ~56.9k stars | Agent retainer, $5,000 | Well-built multi-agent orchestration. Defaults to OpenAI; Claude via LiteLLM. Multi-agent is the least reliable pattern in production — more agents means more places to fail silently. |
| browser-use/browser-useMIT · ~109.3k stars | Automation, $1,200 | Excellent browser automation. Its own README recommends the paid cloud for production — the maintainers being honest about where self-hosting stops. |
| firecrawl/firecrawlAGPL-3.0 core · ~170k stars | Lead generation, $5,000 | The strongest scraping API in the category. Self-hosting deliberately omits the managed anti-bot and proxy layer, so success rates drop. Scraping for leads carries GDPR and terms-of-service exposure. |
Star counts are volatile, and that is a finding rather than a footnote. Firecrawl appears as 123.5k in May 2026, 137k in early August, and 170,475 on GitHub's own organisation page within the last week. Recompute rather than trust this page: api.github.com/repos/OWNER/NAME returns stargazers_count. A star count has a shelf life of weeks.
The prices are real. That is the point
The easy dismissal is that the numbers are invented. They are not, and that is precisely why the pitch works.
Voice agency pricing runs $297–497 monthly for small business and $1,497–4,997 for enterprise, with setup fees of $297–997 and reported margins of 50–70%. Social management runs $500–1,500 basic through $3,000–8,000 premium, agency retainers $2,000–6,000. A simple RAG chatbot is "a few thousand dollars"; workflow automation runs several thousand to low five figures.
Every one of these is a real service rate. None of them is a rate for running a repository.
A client pays $5,000 for a website. The repository does not produce a website — it produces code. The distance between those two things is the job, and it is invisible on any slide.
The real cost structure
API bills, at 30–50% of margin
Voice work runs $0.12–0.30 per minute all-in, and the widely advertised per-minute rate is a floor rather than a total — it excludes the speech-to-text, text-to-speech and telephony legs a phone agent cannot function without.
A retainer that looks like 70% margin on a slide is materially thinner once the meter runs, and the meter runs whether or not the client is happy.
The licences
Two of the seven are AGPL-3.0 — postiz and firecrawl. Four are MIT, one is BSD-2. Most write-ups treat all seven identically.
What the AGPL requires is narrower than usually stated, and worth getting right. Section 13 triggers when users interact with the program itself over a network — modify it and let clients use it remotely, and you owe them the source. Running an unmodified copy internally as a tool to produce a deliverable does not trigger it.Firecrawl LICENSE and README, github.com/firecrawl/firecrawl, checked 22 Aug 2026. SDKs and some UI components are separately MIT.
So the honest version is not "you cannot sell this." It is: the moment you modify an AGPL component and expose it to a client, you have an obligation nobody mentioned — and that is a question for a lawyer, not a caption.
Everything between the demo and the invoice
Discovery. Integration with systems the client already runs. Data cleanup — the real content of any "an afternoon of work" claim. Testing. Liability when it fails at 2am. Support. Churn.
And client acquisition, which is the actual hard part of any agency and appears in none of these pitches. A tool that does the work is worth nothing until someone is paying for the work.
The claim with evidence against it
"A client project, minus the developer" is the one assertion here that published research directly contradicts — and the figure usually quoted for it is stated wrongly, which is worth correcting.
The line in circulation is "Snyk 2026: 40% of AI-generated code contains a critical vulnerability." That conflates two separate findings.
Snyk's 2026 material states that nearly half of AI-generated code contains vulnerabilities — reported as 48% and as "nearly half."2026 Snyk Developer Security Report, as reported Mar 2026 · snyk.io, Jun 2026
The 40% figure traces to Pearce et al., 2022 — the original study of GitHub Copilot, which found roughly 40% of 1,689 generated programs contained vulnerabilities, split about 50% in C against 39% in Python.Pearce, Ahmad, Tan, Dolan-Gavitt & Karri, "Asleep at the Keyboard?", 2022
Neither source supports the word "critical" attached to 40%. Published rates range 25% to 62% depending on model, language and method. The honest statement is a range, not a decimal.
More directly relevant to anyone assembling a business from repositories: Snyk's February 2026 audit of the agent-skills ecosystem scanned 3,984 skills and found 13.4% contained at least one critical-severity issue, alongside 76 confirmed live malicious payloads built for credential theft and data exfiltration.Snyk, "ToxicSkills", 5 Feb 2026
The direction is not in dispute even where the decimals are. Code that ships without a developer reading it is code nobody has read.
A worked example, verified
The argument on this page is that the repository is the engine, not the car. Here is the arithmetic on a real one.
OpenReply — open-source Instagram comment-to-DM automation, MIT licensed, a disclosed fork of an earlier MIT project with the billing layer removed. Landed on GitHub 17 July 2026; 680 stars in fourteen days, ~1.2k now. Genuinely good software.github.com/diwenne/openreply — verified 22 Aug 2026
Its own README says the quiet part: the code deploys in minutes, but the Meta app setup is the part that takes real time. Meta scrutinises automated-DM apps and often rejects the first submission.
Free to clone, $26–63 a month to run, and a business registration document before anyone but you can use it.
None of that makes it a bad project — it is a well-built one, honestly documented. It is the distance between "free repository" and "business" made numeric, which is the whole point of this page.
How to evaluate any repo pitched as a business
Four questions, ordered by how fast they resolve it:
- Is the price a rate for the tool, or a rate for the service? Almost always the second. The repository is the engine; the client is buying the car.
- What is the licence? Thirty seconds on the repository page. AGPL changes what you may build and sell.
- What does the project's own README recommend for production? Several of these say "use the paid version." That is maintainers being honest, and it belongs in your costing.
- Where is client acquisition? Any pitch that promises revenue without addressing how you find the client is describing a tool, not a business.
Every repository here is genuinely useful and worth your time. The repo is the engine, not the car. The chassis, the wheels, the insurance and the driver are the business — and that is what a client is actually paying for.
See also when not to use AI for the same arithmetic from the other side, prompting agents for how these fail in production, and guardrails for what you owe a client whose systems you have automated.