Developer tools decision
ShipTell
A single capable developer can build and operate a useful AI changelog automation replacement in about a week using existing OSS components (semantic-release / release-it) and an LLM; the vendor's site provides no evidence of durable moats or proprietary data that would prevent replacement.
Visit website↗Built by Zakir 🇧🇩, who ships 3 products in this index
Not priced
No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.
$50one-off24 h to build
$20/mo3 h/mo upkeep
No published price to break even against.
Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All ShipTell alternatives, with the arithmetic →
What a replacement has to do
- Scan commits/tags, generate human-readable changelog text with an LLM, persist changelog and create a release (git tag/GitHub Release), optionally surface/approve entries via a small UI or PR.
What it still won’t have
- Polished commercial UI/UX and onboarding flows
- Prebuilt integrations beyond GitHub (GitLab, Bitbucket, third-party trackers)
- SLA, commercial support, and analytics dashboards
- Brand, marketing, and any proprietary data the vendor may use
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
ShipTell does not publish a price we could read, so there is nothing to compare against. What building costs is below.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build an AI-driven changelog automation service as a CLI + GitHub Action using Node.js (TypeScript), Express for a tiny web UI, PostgreSQL (or SQLite) for minimal state, and OpenAI-compatible LLM API. Core features: parse git commit history (support Conventional Commits), aggregate changes per release, call an LLM to generate a human-readable changelog section, write/update CHANGELOG.md, create a git tag and GitHub Release via GitHub API, provide a manual approval UI or PR flow, and a GitHub Action to run on release. Out of scope: multi-repo enterprise dashboards, advanced analytics, paid billing. Include error handling, retries for API calls, unit tests for parsing and release logic, and CI configuration to run tests and publish the Action.
How we checked
How the score was reached
- Build verdict base78
- An open-source build was found+5
- 3 cited sources+3
- 3/3 assessment runs agreed+4
- Evidence score90
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 3
Every page the run actually retrieved.
- official productShipTell - AI Changelog Automation
- open sourcesemantic-release/semantic-release
- open sourcerelease-it/release-it
Integrity checks
What held up, and what did not.
