Enis Polat The Github Coder
Enis Polat The Github Coder's work was selected for the XERJ Corpus Hub, the open reference memory AI coding agents search before they write code. When an agent meets the same problem, it gets this implementation back as a worked example, with the author and the repository attached.
Totals across every corpus @enis1enis2 appears in; a commit selected for two corpora counts once. Files and lines count the selected commits; each corpus indexes the whole repository at its pinned commit.
What an agent can do with the KeyGate corpus
enis1enis2/KeyGate: Self-hosted AI API gateway: group upstream provider keys into load-balanced AI pools, route around failing ones, cap spend, and expose one…
- Look up how KeyGate implements ai-gateway, api-gateway, circuit-breaker, with answers cited to file and line.
- Reuse a worked example: the commit “Add per-pool web search and by-ai model selection” (14 files · TypeScript).
- Answer from KeyGate's real TypeScript source instead of memory (AI, prompts and agents).
- Where does KeyGate handle “Add per-pool web search and by-ai model selection”?
- How does KeyGate implement ai-gateway?
- What does backend do in KeyGate?
Search the GitHub repository enis1enis2/KeyGate with XERJ (https://hub.xerj.org/corpus/enis1enis2--keygate). 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/enis1enis2/KeyGate KeyGate && git -C KeyGate checkout a4708c65bc8ee2fa34ec330da3d50db59a5a5a8c 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./KeyGate --url http://127.0.0.1:9200 --prefix keygate --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.
corpus enis1enis2--keygate · AI, prompts and agents
Related corpora: distilabel, guardrails, zumpyx/Aikun, roedyrustam/sinapsai
AI search and retrieval with XERJ · Case study: reference coding for agents
Selected work
enis1enis2/KeyGate
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
Sign in with GitHub or Hugging Face to see more: every selected commit in full (commit date, every folder, licence review state, pin) and the pack builds of each corpus.
[](https://hub.xerj.org/contributors/enis1enis2)
Included with the author's permission (email, 2026-11-03), under each repository's own licence, with attribution. Own more repositories? Sign in with GitHub and add them. Want something removed? Reply to the email, withdraw it on /add, or open an issue on xerj-org/xerj.