context-guardian
Compaction for local models that actually fires and never bricks the session. OpenAI-compatible proxy + DeepSeek Harness engine
What XERJ indexed
Snapshot
The whole repository at commit d144d75d88 (2026-10-23). It is the newest commit on main.
Selected work
“detect the window on vLLM and llama.cpp, not only Ollama”. 3 files, 312 lines in tests, the project root.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-30. 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-toolllmlocal-llmopenai-appythoncoding-assistantcompactioncontext-management
Example questions
- How does context-guardian implement ai-tool?
- Where does context-guardian handle “detect the window on vLLM and llama.cpp, not only Ollama”?
- Show the llm code in context-guardian.
Inside the indexed corpus
- 177 files, 2.4 MB in total, about 14.0 KB per file.
- The selected commit changed 3 of those files (1.7%).
- Languages by size: Python 65.5%, JavaScript 34.5%, Dockerfile 0.1%.
- On GitHub since 2026-08-13, last push 2026-10-31, 117 commits on main.
Licence on GitHub and in the corpus
GitHub reported MIT for LuminariSoftwares/context-guardian on 2026-10-31, and the LICENSE file at commit d144d75d88 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
LuminariSoftwares (@LuminariSoftwares) has 4 selected repositories on the hub.
Their other repository pages: LuminariSoftwares/tool-guardian, LuminariSoftwares/code-guardian, LuminariSoftwares/stack-guardian.
Using XERJ with context-guardian
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- Index a reference library for a coding agent
- ripgrep vs a code index for coding agents: 30 tasks
- Best MCP servers for local code search in 2026, compared
The prompt
Paste it into your AI agent. It clones LuminariSoftwares/context-guardian at the pinned commit and indexes it on your machine.
Search the GitHub repository LuminariSoftwares/context-guardian with XERJ (https://hub.xerj.org/corpus/luminarisoftwares--context-guardian). 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/LuminariSoftwares/context-guardian context-guardian && git -C context-guardian checkout d144d75d880f24c1cb60836bec2f2c8d9c745c71 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./context-guardian --url http://127.0.0.1:9200 --prefix context-guardian --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
LuminariSoftwaresAI, prompts and agents corporagpt-engineerdunorth595--ai-agent-memorycassandraLuminariSoftwares/tool-guardiancfanzx/dsh-compact-relayjidekaixin2dian/dsh-toolgate
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.