entroly
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper
What XERJ indexed
Snapshot
The whole repository at commit 915814403f (2026-10-13). main is 27 commits ahead.
Selected work

“Expose source-bound cross-agent review in work CLI”. 4 files, 194 lines in entroly, tests.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-26. 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
ai-agentsclaude-codemcptoken-optimizationcontext-compressionhallucination-detectionllmcodex
Example questions
- How does entroly implement ai-agents?
- Where does entroly handle “Expose source-bound cross-agent review in work CLI”?
- What does entroly do in entroly?
Inside the indexed corpus
- 2,014 files, 39.3 MB in total, about 20.0 KB per file.
- The selected commit changed 4 of those files (0.2%).
- Languages by size: Python 80.6%, Rust 16.6%, JavaScript 1.5%, HTML 0.7%, CSS 0.3%.
- On GitHub since 2026-03-07, last push 2026-10-31, 2,202 commits on main.
- The pin is 27 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported Apache-2.0 for juyterman1000/entroly on 2026-10-31, and the LICENSE file at commit 915814403f was reviewed as Apache-2.0. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Jupyterman (@juyterman1000) has 1 selected repository on the hub.
Using XERJ with entroly
- Code search MCP for Claude Code: cite file:line, not grep entroly is tagged mcp on GitHub.
- What is an MCP memory server?
- A local search tool for Codex and Cursor entroly is tagged claude-code on GitHub.
- Local code search MCP that uses fewer tokens than grep
The prompt
Paste it into your AI agent. It clones juyterman1000/entroly at the pinned commit and indexes it on your machine.
Search the GitHub repository juyterman1000/entroly with XERJ (https://hub.xerj.org/corpus/juyterman1000--entroly). 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/juyterman1000/entroly entroly && git -C entroly checkout 915814403f1f5a13fbb6762e652f51e64a1f275f 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./entroly --url http://127.0.0.1:9200 --prefix entroly --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: Apache-2.0. Keep the copyright notice and credit the authors.
Related
JupytermanAI, prompts and agents corpora12-factor-agentsMehradYaghoubi/jev-research-engineeringheadroomlabs-ai/headroomphoenixlucky/zerotoken-skill
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.