DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to let a coding agent batch-rewrite drafts through a local server with Humanizer Local Model

Run the 12B model as a local llama-server and have an agent send each draft to it.

Authorization notice. Humanizer Local Model is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forA developer or team building an automated pipeline that rewrites many AI-drafted texts and needs a local, scriptable endpoint.

The problemRewriting many drafts by hand does not scale, and a cloud service may not suit private text.

The outcomeA local llama-server answering rewrite requests, with an agent looping over a folder of drafts and saving each rewrite.

What you need first

  • A Mac with Apple silicon (M1 or newer) or a Windows x64 PC, for the app
  • Enough free disk space and memory for the model; the app suggests a size for your machine, down to 8 GB machines
  • Python 3.8 or newer for the hz command line tool
  • llama.cpp (llama-server), curl and jq for the one-command server route

Steps

  1. Start the model with llama-server --hf-repo jialinyyzz/humanizer --hf-file humanizer-12b-Q8_0.gguf -c 8192 -np 1 -ngl 99 --port 8080. On a 16 GB machine, use humanizer-12b-Q6_K.gguf instead.
  2. Download the prompt format with curl -sLO https://huggingface.co/jialinyyzz/humanizer/resolve/main/prompt_format.json.
  3. Send each draft to /completion using the jq and curl pipeline in Option 2 of the README, not /v1/chat/completions.
  4. Save each returned text to its own output file and keep the draft next to it for review.
  5. Read docs/USAGE.md for the folder script and the troubleshooting table before you scale up.

Prompt for your agent

Using the sgaofen/humanizer-local-model repo, start llama-server with the Q8_0 GGUF on port 8080 and rewrite every .txt file in <input-folder> through the /completion endpoint with the prompt format from prompt_format.json. Expected output: one rewritten .txt per input file in <output-folder>. Verify that a single test draft returns non-empty text from the .content field before running the whole folder.

Caveat. The README says this is a plain text-completion model, not a chat model, so it must be called through /completion with the stated prompt format.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page