cache-rag-gateway
Layered LLM caches (exact, semantic, retrieval, prompt) behind a RAG gateway, plus an eval harness measuring cost, latency and wrong answers served
What XERJ indexed
Snapshot
The whole repository at commit 6d96d93acc (2026-10-08). main is 2 commits ahead.
Selected work

“Add charts, story card and dev.to cover, drawn from the logged runs”. 3 files, 244 lines in scripts.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-27. Same terms as the repository. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution
aws-fargatebenchmarkingcachingclaudeevaluationharnessllmollama
Example questions
- How does cache-rag-gateway implement aws-fargate?
- Where does cache-rag-gateway handle “Add charts, story card and dev.to cover, drawn from the logged runs”?
- Show the benchmarking code in cache-rag-gateway.
The prompt
Paste it into your AI agent. It clones Shivb237/cache-rag-gateway at the pinned commit and indexes it on your machine.
Search the GitHub repository Shivb237/cache-rag-gateway with XERJ (https://hub.xerj.org/corpus/shivb237--cache-rag-gateway). 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/Shivb237/cache-rag-gateway cache-rag-gateway && git -C cache-rag-gateway checkout 6d96d93acc59a93236e7f7c838d0d4ced5e7f3c6 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./cache-rag-gateway --url http://127.0.0.1:9200 --prefix cache-rag-gateway --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: MIT. Keep the copyright notice and credit the authors.
Related
Shivang BhatnagarAI, prompts and agents corporaxobotyi--cc-foundry-ai-helpers-skill-engineeringautoragflexraghexagon-codes/hexclaw-desktopBrxerq/claude-cockpitroyisme/pikabaka
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.