Practical LLM Applications on the Linux Command Line

Interface

Usage: myllmcalllocal [-h] <task>.txt

The task itself is simply a text file. There is no provider configuration, API key, model option or OpenCode dependency. The only runtime prerequisite is a working local Ollama installation with at least one downloaded model.

Design characteristic

Model selection is intentionally interactive rather than configuration-driven. This makes the script well suited for manual experiments and illustrates the local inference mechanism without an additional abstraction layer. For unattended or repeatable workflows, the later scripts replace this interaction with ~/models.txt.

Example configuration

default:openrouter/deepseek/deepseek-v4-flash-0731
myopencodecall:openrouter/deepseek/deepseek-v4-flash-0731
myopenrouterimagerecognition:openrouter/qwen/qwen3-vl-8b-instruct
myopenrouterocr:openrouter/qwen/qwen3-vl-8b-instruct
myyoutubesubs_local:openrouter/deepseek/deepseek-v4-flash-0731
myyoutubesubs:openrouter/deepseek/deepseek-v4-flash-0731
myollamaocr:glm-ocr

Lookup policy

1. Require $HOME/models.txt.
2. Look for <script-name>:<model>.
3. If absent, look for default:<model>.
4. If neither exists, terminate with an explicit error.

For OpenCode calls, model identifiers use OpenCode's provider/model notation. The local myollamaocr script is the deliberate exception because it talks directly to Ollama and therefore uses Ollama's own model name such as glm-ocr.

myollamaocr · local OCR

This script bypasses OpenCode and calls the local Ollama generate API directly. The image is Base64 encoded, inserted into a JSON request with jq, and sent to http://127.0.0.1:11434/api/generate. The recognized text is written beside the image as a .txt file.

base64 -w 0 "$INPUT" > "$IMAGE64"

jq -n \
    --rawfile image "$IMAGE64" \
    --arg model "$MODEL" \
    '{
        model: $model,
        prompt: "Text Recognition:",
        images: [$image],
        stream: false
    }' > "$REQUEST"

curl --data-binary "@$REQUEST" \
     "$OLLAMA_URL"

myopenrouterocr · OCR through OpenCode

Here OpenCode supplies the attachment handling and provider abstraction. The script contributes the task-specific OCR prompt, the input file and the configured model. With the supplied configuration, that model is obtained through OpenRouter.

opencode run \
    -m "$MODEL" \
    'Perform OCR on this scanned document.
     Transcribe all visible text accurately,
     preserve line and paragraph structure where possible,
     and output only the transcription.' \
    -f "$file" \
    > "$out"

myyoutubesubs · online source

yt-dlp downloads automatic subtitles for a single YouTube URL or a URL list. An AWK stage removes WebVTT headers, timestamps, tags, entities, empty lines and immediately repeated lines. The result becomes a normal text file. With -s, OpenCode summarizes that file.

yt-dlp \
  --write-auto-subs \
  --skip-download \
  "$URL"

# ... VTT cleanup with awk ...

opencode run -m "$MODEL" -f "$file" \
  "Summarize the content of the attached file
   concisely and completely. Output only the summary." \
  > "$tmp"

fold -s -w 80 "$tmp" > "$condensed"

myyoutubesubs_local · local MP4 source

The local counterpart processes all MP4 files in the current directory. ffprobe locates an embedded subtitle stream, preferring the stream marked as default. ffmpeg extracts it as SRT, with WebVTT as fallback. The same cleanup and optional OpenCode summarization then follow.

ffprobe -v error \
  -select_streams s \
  -show_entries stream=index:stream_disposition=default \
  -of csv=p=0 -- "$file"

ffmpeg -v error -y -i "$file" \
  -map "0:${stream_index}" -c:s srt "$srt"

opencode run -m "$MODEL" \
  "Summarize the content ... without translation." \
  -f "$inputfile" \
  > "$tmp"