needtoknow
Permission-aware retrieval for RAG: every user gets only the chunks they are allowed to read. Works with any vector store, permission system (OpenFGA, OPA, ACLs) and framework (LangChain, LlamaIndex). Fails closed
What XERJ indexed
Snapshot
The whole repository at commit 3e5a52caf8 (2026-10-15). main is 423 commits ahead.
Selected work
“permission-aware retriever core”. 11 files, 937 lines in needtoknow, tests, the project root.
Licence
The repository
Checked by a person at the pinned commit.
The XERJ corpus
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
access-controlauthorizationlangchainllamaindexllmopenfgapythonrag
Example questions
- How does needtoknow implement access-control?
- Where does needtoknow handle “permission-aware retriever core”?
- What does needtoknow do in needtoknow?
The prompt
Paste it into your AI agent. It clones muzakkirhussain011/needtoknow at the pinned commit and indexes it on your machine.
Search the GitHub repository muzakkirhussain011/needtoknow with XERJ (https://hub.xerj.org/corpus/muzakkirhussain011--wardowl). 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/muzakkirhussain011/needtoknow needtoknow && git -C needtoknow checkout 3e5a52caf8989bca582d971529de33c6f07e2bd1 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./needtoknow --url http://127.0.0.1:9200 --prefix needtoknow --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
Syed Muzakkir HussainAI, prompts and agents corporahaystackadalflowgraphragtejas-parjane/business-intelligent-rag-agentShauryaaSharma/lore-backendSheikhSarvar/pyrag-core
Stats: GitHub API, fetched 2026-10-23. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.