DemoFlow
Verified, polished demo videos of your web app from one JSON scenario. Local CLI on Playwright + FFmpeg, with an MCP server for Claude Code
What XERJ indexed
Snapshot
The whole repository at commit cffa0f50ad. It is the newest commit on develop.
Selected work
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The owner added it on hub.xerj.org after signing in with GitHub, on 2026-10-29. Same terms as the repository. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution
ai-agentsbrowser-automationchromiumclaude-codeclidemo-videoe2e-testingffmpeg
Example questions
- How does DemoFlow implement ai-agents?
- Show the browser-automation code in DemoFlow.
Inside the indexed corpus
- 966 files, 10.4 MB in total, about 11.0 KB per file.
- Languages by size: TypeScript 94.5%, JavaScript 2.3%, MDX 2.1%, Shell 0.9%, Dockerfile 0.2%.
- On GitHub since 2026-10-17, last push 2026-10-27, 724 commits on develop.
Licence on GitHub and in the corpus
GitHub reported MIT for AndreyBegma/DemoFlow on 2026-10-29, and the LICENSE file at commit cffa0f50ad was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Andriy (@AndreyBegma) has 4 selected repositories on the hub.
Their other repository pages: AndreyBegma/glass-ui, AndreyBegma/claude-code-plugin, AndreyBegma/Nautelle.
Using XERJ with DemoFlow
- Code search MCP for Claude Code: cite file:line, not grep DemoFlow is tagged mcp on GitHub.
- What is an MCP memory server?
- A local search tool for Codex and Cursor DemoFlow is tagged claude-code on GitHub.
- Local code search MCP that uses fewer tokens than grep
The prompt
Paste it into your AI agent. It clones AndreyBegma/DemoFlow at the pinned commit and indexes it on your machine.
Search the GitHub repository AndreyBegma/DemoFlow with XERJ (https://hub.xerj.org/corpus/andreybegma--demoflow). Run these in a shell, in order, and check each result before the next: 1. xerj --help (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh 2. git clone https://github.com/AndreyBegma/DemoFlow DemoFlow && git -C DemoFlow checkout cffa0f50ad5dac7c6e7350fd7b3ee18c524f6f97 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./DemoFlow --url http://127.0.0.1:9200 --prefix demoflow --progress plain 5. xerj autoindex map --url http://127.0.0.1:9200 Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt Licence: MIT. Keep the copyright notice and credit the authors.
Related
AndriyAI, prompts and agents corporaxerj-blogpostsgotlexbuildAnayDhawan/openvidstudioldmallari/scenecastricfanin/netwright
Stats: GitHub API, fetched 2026-10-29. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.