Delibera
Delibera - Thoughtful AI Decisions. A framework for collective decision making through structured AI deliberation. Supports multi-model councils with RAG (Qdrant, PgVector), debate strategies, Knowledge Keeper, Chairman roles, dependency injection, and context compression
What XERJ indexed
Snapshot
The whole repository at commit a39323d019 (2026-10-09). main is 4 commits ahead.
Selected work

“v10.5.2 - Added WebUI”. 39 files, 3,734 lines in src/Delibera.WebUI, deploy, src/Delibera.Server.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-09. 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
aicouncilembeddingsllmollamaopenaipgvectorqdrant
Example questions
- How does Delibera implement ai?
- Where does Delibera handle “v10.5.2 - Added WebUI”?
- What does src/Delibera.WebUI do in Delibera?
Inside the indexed corpus
- 368 files, 8.4 MB in total, about 23.3 KB per file.
- The selected commit changed 39 of those files (10.6%).
- Languages by size: C# 85%, TypeScript 9.4%, Vue 2.6%, CSS 2%, JavaScript 0.4%.
- On GitHub since 2026-06-05, last push 2026-10-11, 47 commits on main.
- The pin is 4 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for techbuzzz/Delibera on 2026-10-31, and the LICENSE file at commit a39323d019 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Victor Buzin (@techbuzzz) has 1 selected repository on the hub.
Using XERJ with Delibera
- RAG without a vector database: one hybrid index Delibera is tagged embeddings on GitHub.
- Search API or a vector database for agent memory?
- 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 techbuzzz/Delibera at the pinned commit and indexes it on your machine.
Search the GitHub repository techbuzzz/Delibera with XERJ (https://hub.xerj.org/corpus/techbuzzz--delibera). 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/techbuzzz/Delibera Delibera && git -C Delibera checkout a39323d019402f10aa6c1979f9343d43913bdeae 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./Delibera --url http://127.0.0.1:9200 --prefix delibera --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
Victor BuzinAI, prompts and agents corporavectra-coreprompt-engineering-guideautoragtejas-parjane/business-intelligent-rag-agentchatvector-ai/chatvector-aijovempedr0/faiss_index
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.