mze3e /
kognita
Content guardrails check what an AI says. Kognita decides whether it was allowed to ask, before any data is retrieved. An AI gateway and an
A new way for AI to search for data
1GitHub stars
What XERJ indexed
Selected work

“resolve effective client scope once for authority, li…”. 9 files, 251 lines in tests, src/kognita.
Licence
The repository
MIT
Checked by a person at the pinned commit.
The XERJ corpus
MIT, with credit
The author agreed by email on 2026-10-20. 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
Example questions
- What does src/kognita do in kognita?
The prompt
Paste it into your AI agent. It clones mze3e/kognita at the pinned commit and indexes it on your machine.
Search the GitHub repository mze3e/kognita with XERJ (https://hub.xerj.org/corpus/mze3e--kognita). 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/mze3e/kognita kognita && git -C kognita checkout cd62f9576066e7aa2c313036ab633b52dad5caa2 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./kognita --url http://127.0.0.1:9200 --prefix kognita --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
Ahmed MuzammilAI, prompts and agents corpora
Selected work and consent: the XERJ registry.