opencode-context-compress
Durable context compression for OpenCode 2. Replaces native auto-compaction: folds old history into compressed blocks, keeps a recent…
A new way for AI to search for data
4GitHub stars
What XERJ indexed
Selected work
“drive transform tests through the plugin context hook”. 9 files, 1,132 lines in tests, lib/messages.
Licence
The repository
MIT
Checked by a person at the pinned commit.
The XERJ corpus
MIT, with credit
The author agreed by email on 2026-10-21. 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
Example questions
- Where does opencode-context-compress handle “drive transform tests through the plugin context hook”?
- What does lib/messages do in opencode-context-compress?
The prompt
Paste it into your AI agent. It clones AidenGeunGeun/opencode-context-compress at the pinned commit and indexes it on your machine.
Search the GitHub repository AidenGeunGeun/opencode-context-compress with XERJ (https://hub.xerj.org/corpus/aidengeungeun--opencode-context-compress). 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/AidenGeunGeun/opencode-context-compress opencode-context-compress && git -C opencode-context-compress checkout e80e926ecc3cfc890d05555460500cd35dbf1698 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./opencode-context-compress --url http://127.0.0.1:9200 --prefix opencode-context-compres --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
Aiden KimAPI design and specification corpora
Selected work and consent: the XERJ registry.