flowd
Local, offline, streaming dictation for Linux with on-device LLM cleanup
A new way for AI to search for data
2GitHub stars
What XERJ indexed
Selected work
“opt-in Nemotron streaming preview”. 13 files, 551 lines in tests, flowd, scripts.
Licence
The repository
MIT
Checked by a person at the pinned commit.
The XERJ corpus
MIT, with credit
The author agreed by email on 2026-10-22. Same terms as the repository. Answers name the repo, the commit and the file:line.
in licence reviewnot in the hub yetsuggested use: adapt with attribution
dictationhyprlandlinuxllama-cpplocal-firstprivacyspeech-to-textwayland
Example questions
- How does flowd implement dictation?
- Where does flowd handle “opt-in Nemotron streaming preview”?
- What does flowd do in flowd?
The prompt
Paste it into your AI agent. It clones harshitsaini17/flowd at the pinned commit and indexes it on your machine.
Search the GitHub repository harshitsaini17/flowd with XERJ (https://hub.xerj.org/corpus/harshitsaini17--flowd). 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/harshitsaini17/flowd flowd && git -C flowd checkout e2f0be70e3f1f19f299a8869edbdae59ce290a4b 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./flowd --url http://127.0.0.1:9200 --prefix flowd --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
harshit sainiAI, prompts and agents corporaeurlex-coremkcertschool-of-sreMSKazemi/yazsespavlenkosa/wayvoicepeteonrails/voxtype
Selected work and consent: the XERJ registry.