sukami
High-performance AI gateway & token optimizer in pure Go. Cut LLM costs & latency with zero code changes
What XERJ indexed
Snapshot
The whole repository at commit 189c61befb (2026-10-26). main is 61 commits ahead.
Selected work

“add standard Prometheus exposition endpoint /metrics i…”. 6 files, 198 lines in pkg/metrics, pkg/proxy, cmd/sukami.
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
ai-gatewayanthropicdeepseekgolanggood-first-issuegroqllmopenai
Example questions
- How does sukami implement ai-gateway?
- What does pkg/metrics do in sukami?
- Show the anthropic code in sukami.
Inside the indexed corpus
- 45 files, 188.7 KB in total, about 4.2 KB per file.
- The selected commit changed 6 of those files (13.3%).
- Languages by size: Go 98.9%, Dockerfile 1%, Makefile 0.2%.
- On GitHub since 2026-10-24, last push 2026-10-29, 100 commits on main.
- The pin is 61 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for alexpatil/sukami on 2026-10-31, and the LICENSE file at commit 189c61befb was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Ganesh Shinde (@alexpatil) has 1 selected repository on the hub.
Using XERJ with sukami
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- Best grep alternative for AI coding agents (2026)
- Ask questions about a GitHub repo without cloning it
- Index a reference library for a coding agent
The prompt
Paste it into your AI agent. It clones alexpatil/sukami at the pinned commit and indexes it on your machine.
Search the GitHub repository alexpatil/sukami with XERJ (https://hub.xerj.org/corpus/alexpatil--sukami). 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/alexpatil/sukami sukami && git -C sukami checkout 189c61befb37d47904c91ce14e9854a63c3f7866 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./sukami --url http://127.0.0.1:9200 --prefix sukami --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
Ganesh ShindeAI, prompts and agents corporaaidergriptapeagentopsENTERPILOT/GoModelkittors/CliRelayoschina/mothx
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.