4evergent

4evergent: Autonomous AI Agents on Stellar

A new way for AI to search for data

View on GitHub

5GitHub stars

323commits on main

79forks

TypeScript 93.3%, Rust 2.9%, CSS 2.9%, JavaScript 0.6% · created 2026-09-15 · last push 2026-10-26

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 1421a802df (2026-10-25). main is 18 commits ahead.

Selected work

Praise Temiloluwa Olufemi
@opratem

“add examples directory with first-agent walkthrough s…”. 7 files, 343 lines in examples, the project root.

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

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

Inside the indexed corpus

Languages by size: TypeScript 93.3%, Rust 2.9%, CSS 2.9%, JavaScript 0.6%, Dockerfile 0.2%.
On GitHub since 2026-09-15, last push 2026-10-26, 323 commits on main.
The pin is 18 commits behind main; the corpus answers from the pinned code, not the newest.

Licence on GitHub and in the corpus

GitHub reported MIT for naninu123/4evergent on 2026-10-31, and the LICENSE file at commit 1421a802df was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.

Contributors

Praise Temiloluwa Olufemi (@opratem) has 1 selected repository on the hub.

Using XERJ with 4evergent

RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
Ask questions about a GitHub repo without cloning it
Index a reference library for a coding agent
ripgrep vs a code index for coding agents: 30 tasks

The prompt

Paste it into your AI agent. It clones naninu123/4evergent at the pinned commit and indexes it on your machine.

Search the GitHub repository naninu123/4evergent with XERJ (https://hub.xerj.org/corpus/naninu123--4evergent).
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/naninu123/4evergent 4evergent && git -C 4evergent checkout 1421a802df2d925d3fdae8725eb198c90862e8a7
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./4evergent --url http://127.0.0.1:9200 --prefix 4evergent --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.

Praise Temiloluwa Olufemi AI, prompts and agents corpora

Stats: GitHub API, fetched 2026-10-31. Selected work and consent: the XERJ registry.