LuminariSoftwares

What an agent can do with the context-guardian corpus

LuminariSoftwares/context-guardian: Compaction for local models that actually fires and never bricks the session. OpenAI-compatible proxy + DeepSeek Harness engine

• Look up how context-guardian implements ai-tool, llm, local-llm, with answers cited to file and line.
• Reuse a worked example: the commit “detect the window on vLLM and llama.cpp, not only Ollama” (3 files · Python).
• Answer from context-guardian's real Python source instead of memory (AI, prompts and agents).

• Where does context-guardian handle “detect the window on vLLM and llama.cpp, not only Ollama”?
• How does context-guardian implement ai-tool?
• What does tests do in context-guardian?

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.

corpus luminarisoftwares--context-guardian · AI, prompts and agents
Related corpora: dunorth595--ai-agent-memory, gpt-engineer, cfanzx/dsh-compact-relay, LuminariSoftwares/tool-guardian
AI search and retrieval with XERJ · Case study: reference coding for agents