llama.kt

Kotlin/Android JNI binding for llama.cpp: GGUF on-device inference, extracted from llama.rn

A new way for AI to search for data

View on GitHub

2GitHub stars

102commits on main

0forks

C++ 78.9%, C 20.7%, Kotlin 0.3%, Shell 0.1% · created 2026-07-01 · last push 2026-10-23

What XERJ indexed

Snapshot

627 files · 39.9 MB

The whole repository at commit cad0ec9562 (2026-10-07). main is 19 commits ahead.

Selected work

hokanosekai
@hokanosekai

“TEN-123: real model-load stages; TEN-114 fix moved into a patch”. 8 files, 239 lines in patches, llama-kt, example.

Licence

The repository

Apache-2.0

From GitHub's licence detection. A person still checks the LICENSE file at the pinned commit.

The XERJ corpus

Apache-2.0, with credit

The author agreed by email on 2026-10-16. 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

androidedge-aiggufinferencejnikotlinllama-cppllm

Example questions

How does llama.kt implement android?
Where does llama.kt handle “TEN-123: real model-load stages; TEN-114 fix moved into a patch”?
What does patches do in llama.kt?

The prompt

Paste it into your AI agent. It clones tensai-app/llama.kt at the pinned commit and indexes it on your machine.

Search the GitHub repository tensai-app/llama.kt with XERJ (https://hub.xerj.org/corpus/tensai-app--llama-kt).
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/hokanosekai/llama.kt llama.kt && git -C llama.kt checkout cad0ec95620d0dd951fc277fec0223f9ea4171e4
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./llama.kt --url http://127.0.0.1:9200 --prefix llama-kt --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.

hokanosekai AI, prompts and agents corpora llm-course candle simonw-llm dynalm-project/dynalm CubicLM/CubicLM GiacomoSaccaggi/Mithril

Stats: GitHub API, fetched 2026-10-23. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.