Levin Mallari
Levin Mallari's work was selected for the XERJ Corpus Hub, the open reference memory AI coding agents search before they write code. When an agent meets the same problem, it gets this implementation back as a worked example, with the author and the repository attached.
Totals across every corpus @ldmallari appears in; a commit selected for two corpora counts once. Files and lines count the selected commits; each corpus indexes the whole repository at its pinned commit.
What an agent can do with the scenecast corpus
ldmallari/scenecast: Turn a short scene file into a narrated, audited walkthrough video of your real web app
- Look up how scenecast implements ai-agents, claude-code, cli, with answers cited to file and line.
- Reuse a worked example: the commit “caption wrap avoids ending a line on a function word, hover ring…” (14 files · TypeScript).
- Answer from scenecast's real TypeScript source instead of memory (AI, prompts and agents).
- How does scenecast implement ai-agents?
- What does packages/cli do in scenecast?
Search the GitHub repository ldmallari/scenecast with XERJ (https://hub.xerj.org/corpus/ldmallari--scenecast). 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/ldmallari/scenecast scenecast && git -C scenecast checkout c5ac5a735b2f005ebdc7cf506d4a8580f9d32b8d 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./scenecast --url http://127.0.0.1:9200 --prefix scenecast --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.
corpus ldmallari--scenecast · AI, prompts and agents
Related corpora: xerj-blogposts, faah, AndreyBegma/DemoFlow, AnayDhawan/openvidstudio
AI search and retrieval with XERJ · Case study: reference coding for agents
Selected work
ldmallari/scenecast
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
Sign in with GitHub or Hugging Face to see more: every selected commit in full (commit date, every folder, licence review state, pin) and the pack builds of each corpus.
[](https://hub.xerj.org/contributors/ldmallari)
Included with the author's permission (email, 2026-10-28), under each repository's own licence, with attribution. Own more repositories? Sign in with GitHub and add them. Want something removed? Reply to the email, withdraw it on /add, or open an issue on xerj-org/xerj.