We check every product on this page once a day and record whether it still answers.
A single-binary CI test runner for LLM apps and agents that defines test cases in YAML and replays model or judge calls offline at no cost.
Works offline
What to know▼
How it works
Defines test cases and scorers in YAML, runs local targets on every pull request via REST or shell, with baselines, trials, model comparisons, and OTel traces.
Pricing
Replays offline for $0.
Best for
Teams that need CI regression testing for LLM apps and agents.
We check every product on this page once a day and record whether it still answers.
A Windows app that turns real screen actions into annotated step-by-step guides with local OCR and no cloud upload, aimed at IT support, helpdesk and training teams.
Works offlineNo subscriptionCan export my data
What to know▼
How it works
A local-first Windows app for turning real desktop actions into professional visual guides: it captures clicks and active windows with consent, offers a structured editor, annotations, blur, and local OCR, and exports to PDF, DOCX, HTML, PowerPoint, or Markdown.
What's different
Keeps screenshots, OCR, and documents entirely local on the user's PC, with no SaaS account and no keystroke logging, unlike cloud-based alternatives.
Pricing
Available on Microsoft Store with a one-time lifetime license.
Best for
IT support, helpdesk, QA, operations, and training teams that need step-by-step documentation from real desktop actions.
We check every product on this page once a day and record whether it still answers.
A CLI linter that statically checks JSON schemas against each LLM provider's constraints so they don't fail at runtime.
Works offline
What to know▼
How it works
A CLI that statically lints JSON schemas/tool definitions against each LLM provider's documented constraints (e.g. Anthropic-rejected keywords, missing additionalProperties), pointing to the exact JSON-Pointer path and reason, with a repair pass that emits a best-effort provider-valid variant.
What's different
Makes no model calls, needs no API key, and has zero runtime dependencies.
Best for
Teams whose schemas work on one LLM provider but 400 on another.
We check every product on this page once a day and record whether it still answers.
A free, on-device tool that lets you draw and talk over your screen so your AI coding agent sees exactly what you mean — built for Claude Code, Cursor and Codex users.
FreeNo sign-upWorks offline
What to know▼
How it works
Draw directly on your screen and talk while your coding agent watches, then get back annotated screenshots, a voice transcript, and a timeline of what you pointed at, all combined together.
What's different
Runs 100% on-device and works with Claude Code, Codex, and Cursor.
Pricing
Free, no account required.
Best for
Developers who need to show an AI coding agent a visual bug or layout idea instead of describing it in words.
We check every product on this page once a day and record whether it still answers.
A tool for building and running automated integration tests across many API types — HTTP, SOAP, databases, message queues and more — for QA and engineering teams, not a hosted API itself.
Watch out · Data is saved offline on your local machine rather than in the cloud.
FreeWorks offline
What to know▼
How it works
A tool for building and running automated integration test cases across many API types — HTTP, SOAP, relational databases (Oracle, SQL Server, PostgreSQL, H2), JMS, FTP(S), SFTP, AMQP, MQTT, IBM MQ and IBM ACE. Includes HTTP stubs/mock servers, data-driven testing, endpoint management and Git-based team collaboration.
What's different
Covers many non-HTTP protocols and database types, not just REST/HTTP APIs.
Pricing
Free.
Best for
QA and engineering teams doing integration, microservices, ESB or SOA testing who need low-code test authoring.
Watch out
Data is saved offline on your local machine rather than in the cloud.
We check every product on this page once a day and record whether it still answers.
An offline QA workspace for recurring marketing reports that recalculates KPIs from a CSV and requires human sign-off before sending reports to clients.
No sign-upWorks offline
What to know▼
How it works
Drop in a CSV to recalculate KPIs, summarize channels, and flag missing or suspicious data before requiring human sign-off.
What's different
No account, upload, or tracking.
Best for
Agencies and teams doing QA on client-facing marketing reports.
We check every product on this page once a day and record whether it still answers.
A Chrome extension that bundles a screenshot or recording with console logs, network requests and environment info into one bug report, entirely on your machine. Built for developers and QA.
Works offlineData stays with youCan export my data
What to know▼
How it works
A Chrome extension that captures a screenshot or video recording along with console logs, network requests and environment info, bundling them into one paste-ready bug report; can export a video to webm or a full HTML report.
What's different
Runs 100% locally — nothing leaves your machine.
Best for
Developers and QA testers who need a complete, shareable bug report without manually collecting logs and screenshots.
