Browse
→ AI & Models
→ DEEPBOM for Gemini CLI
DEEPBOM for Gemini CLI
Gemini CLI extension that registers a local MCP server for inspecting AI model deployment artifacts without executing model code. It bundles DEEPBOM, constrains analysis to the Gemini workspace directory, and reports hashes, serialized structure, quantization evidence, artifact defects, cautions, and evidence gaps for formats such as ONNX, TFLite, GGUF, SafeTensors, Core ML, and ExecuTorch. Public GitHub repository created September 18, 2026.
MCP unverified
Integration
| Transport | stdio |
| Auth | none |
| Endpoint | gemini extensions install https://github.com/JunHwan-Kwon/deepbom-gemini |
| Install | gemini extensions install https://github.com/JunHwan-Kwon/deepbom-gemini |
Use Cases
| 01 | Inspect AI model files from Gemini CLI without executing model code |
| 02 | Compare model artifacts and report hashes, operation tables, quantization evidence, defects, and evidence gaps |
| 03 | Keep MCP file access bounded to the directory where Gemini CLI was started |
Tags
deepbom gemini-cli model-audit onnx gguf safetensors artifacts stdio
Machine-readable: /api/servers.json
· JSON-LD schema embedded in <head>