Ólafur Aron Jóhannsson

What an agent can do with the kjarni corpus

olafurjohannsson/kjarni: Local embeddings, semantic search, classification, reranking, chat, speech to text, summarization, translation and image search for C#, Go,

• Look up how kjarni implements rust, classification, csharp, with answers cited to file and line.
• Reuse a worked example: the commit “Speed up CPU encoders and Whisper; fix batched decoding; add multilin…” (18 files · Rust).
• Answer from kjarni's real Rust source instead of memory (AI, prompts and agents).

• How does kjarni implement rust?
• What does crates/kjarni-transformers do in kjarni?

Search the GitHub repository olafurjohannsson/kjarni with XERJ (https://hub.xerj.org/corpus/olafurjohannsson--kjarni).
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/olafurjohannsson/kjarni kjarni && git -C kjarni checkout 7a68b2e7305126d9f55a5ffc06eaf228e3dcb9da
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./kjarni --url http://127.0.0.1:9200 --prefix kjarni --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: Apache-2.0. Keep the copyright notice and credit the authors.

corpus olafurjohannsson--kjarni · AI, prompts and agents
Related corpora: candle, avro, fobakic/OpenAnima, Kirky-X/vecboost
AI search and retrieval with XERJ · Case study: reference coding for agents