AI product Open source
An agent skill for turning Claude Code sessions into a fine-tuned coding-agent model using Tinker and llama.cpp. Developed by Migel Tissera and distributed under the MIT license, it provides a nine-step workflow: collect and checksum transcripts, normalize and anonymize them, slice and compact sessions to the model context length, split datasets, train a LoRA on Tinker, compare checkpoints, merge the adapter, and convert and quantize the result to GGUF for local serving. The repository includes Python and shell scripts, reference notes, a synthetic transcript generator for offline dry runs, and support for Claude Code, OpenAI Codex, and OpenCode. It uses Tinker and tinker-cookbook for training and requires a Tinker API key for paid training; dataset preparation and smoke tests run locally.
1 use taken from transcripts — each links to the moment in the video.
Walks a coding agent through turning your Claude Code sessions into a fine-tuned model via a nine-step workflow: collect transcripts, clean and anonymize, train a LoRA on Tinker, merge, and convert to GGUF for local use in llama.cpp.
1 in the library.