hydope

Corpus Hub contributor since 2026-10-25

hydope'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.

1corpus

1selected commit

7files

971lines

★ 3GitHub stars on repo

Totals across every corpus @hydope 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 shortsmash corpus

hydope/shortsmash: ⚒️ Prompt in, finished short out. AI video studio with eyes: CLIP-verified footage, neural voice, karaoke captions, 50-language dubbing…

Look up how shortsmash implements ai-agents, cli, content-creation, with answers cited to file and line.
Reuse a worked example: the commit “ShortSmash Social 0.4 gap fixes: distinct platform openers, real LLM …” (7 files · Python).
Answer from shortsmash's real Python source instead of memory (AI, prompts and agents).

Example questions

How does shortsmash implement ai-agents?
What does shortsmash do in shortsmash?

Paste it into your AI agent. It clones the repo at the pinned commit and indexes it on your machine.

Search the GitHub repository hydope/shortsmash with XERJ (https://hub.xerj.org/corpus/hydope--shortsmash).
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/hydope/shortsmash shortsmash && git -C shortsmash checkout a5e7a97e320c55484bb3c240f1e639162cdff468
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./shortsmash --url http://127.0.0.1:9200 --prefix shortsmash --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 hydope--shortsmash · AI, prompts and agents
Related corpora: licensee, kotaemon, Yuyyxz/kling-prompt-engineering, zyziyun/reelfold
AI search and retrieval with XERJ · Case study: reference coding for agents

Selected work

GitHub ★ 3

hydope/shortsmash

Prompt in, finished short out. AI video studio with eyes: CLIP-verified footage, neural voice, karaoke captions, 50-language dubbing, trend harvesting, official publishing APIs

On GitHub: 68 commits · 129 files at the pinned commit · created 2026-10 · last push 2026-10-25

Languages: Python 92%, Batchfile 3%, PowerShell 2%

a5e7a97e32 ShortSmash Social 0.4 gap fixes: distinct platform openers, real LLM …

selected commit: 7 files · 971 lines · Python · shortsmash, tests

The corpus is the whole repository at the pinned commit, not only the files of the selected commit.

live on the hub · licence clearedcorpus hydope--shortsmashAIMITai-agentsclicontent-creationffmpegmcp-serveropen-source agreed 2026-10-25

[![XERJ Corpus Hub contributor](https://hub.xerj.org/contributors/hydope/badge.svg)](https://hub.xerj.org/contributors/hydope)

Included with the author's permission (email, 2026-10-25), 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.