univo
Compare anything. Keep every record clean. Fast, local duplicate detection for Python data: strings, records and nested objects
What XERJ indexed
Snapshot
The whole repository at commit b1094ac669 (2026-10-27). main is 10 commits ahead.
Selected work

“skip vectors that cannot reach the threshold in single-record s…”. 7 files, 426 lines in crates/univo-engine, benchmarks.
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
deduplicationembeddingsentity-resolutionfuzzy-matchingpyo3pythonrecord-linkagerust
Example questions
- How does univo implement deduplication?
- What does crates/univo-engine do in univo?
- Show the embeddings code in univo.
Inside the indexed corpus
- 254 files, 2.4 MB in total, about 9.6 KB per file.
- The selected commit changed 7 of those files (2.8%).
- Languages by size: Rust 69.5%, Python 30.1%, Just 0.2%, Shell 0.2%.
- On GitHub since 2026-10-07, last push 2026-10-27, 75 commits on main.
- The pin is 10 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for leopoldch/univo on 2026-10-31, and the LICENSE file at commit b1094ac669 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Léo (@leopoldch) has 1 selected repository on the hub.
Using XERJ with univo
- RAG without a vector database: one hybrid index univo is tagged embeddings on GitHub.
- Search API or a vector database for agent memory?
- Batch lookup CVE and GHSA IDs offline in one query The hub files it under Security and vulnerabilities.
- Ask questions about a GitHub repo without cloning it
The prompt
Paste it into your AI agent. It clones leopoldch/univo at the pinned commit and indexes it on your machine.
Search the GitHub repository leopoldch/univo with XERJ (https://hub.xerj.org/corpus/leopoldch--univo). 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/leopoldch/univo univo && git -C univo checkout b1094ac669ef2dd2b02f05114e28aaeae39493d8 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./univo --url http://127.0.0.1:9200 --prefix univo --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
LéoSecurity and vulnerabilities corporacandlevectra-coreflagembeddingilgrad/betula-clusterRomelium/mpatchKirky-X/vecboost
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.