mattneel/VisualLLM.NET

VisualLLM.Server is a .NET 10 web API that serves as the backend for the VisualLLM.NET system, integrating an in-process llama.cpp runtime for local inference. It provides a deterministic demo interface and exposes server endpoints for interacting with the inference engine, which is packaged as the VisualLLM.Inference NuGet package. The system is currently in its initial release phase (v0.1.1), focusing on establishing core infrastructure, build tooling, and basic smoke tests rather than advanced features.

• Container: VisualLLM.Server (web-api)

7 changes.

This period established the foundational structure for VisualLLM.NET, targeting .NET 10.0 and preparing the VisualLLM.Inference NuGet package. The team implemented the core in-process llama.cpp runtime and a deterministic demo backend, accompanied by build, packaging, and smoke-test tooling. Basic unit tests for the inference engine and server endpoints were added, and the initial release version was set to 0.1.1.

Written by watchdog.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

• CAI 68 → 68 (-0.0)
• Rubric changed (rubric-2026.09.11 → rubric-2026.09.18) — scores are not directly comparable.

• Code Health 98 → 98 (+0.0)
• Architecture 98 → 88 (-10.4)
• Maturity 68 → 68 (+0.0)
• Readiness 58 → 58 (-0.1)
• Security 71 → 77 (+5.8)

• Documentation: no installation or build instructions (README.md)
• Documentation: no usage examples (README.md)
• Low coverage: VisualLLM.Server/Api/BackendHealthSnapshot.vb (VisualLLM.Server/Api/BackendHealthSnapshot.vb)
• Low coverage: VisualLLM.Server/Api/ChatEndpoints.vb (VisualLLM.Server/Api/ChatEndpoints.vb)
• Low coverage: VisualLLM.Server/Api/NativeChatCompletionBackend.vb (VisualLLM.Server/Api/NativeChatCompletionBackend.vb)
• Low coverage: VisualLLM.Server/Hosting/ServerBootstrapper.vb (VisualLLM.Server/Hosting/ServerBootstrapper.vb)
• Low coverage: VisualLLM.Server/Program.vb (VisualLLM.Server/Program.vb)

• CRAP 33: ServerOptions.Parse (src/VisualLLM.Server/Hosting/ServerOptions.vb)
• Low coverage: src/VisualLLM.Server/Api/ChatEndpoints.vb (src/VisualLLM.Server/Api/ChatEndpoints.vb)
• Low coverage: src/VisualLLM.Server/Api/NativeChatCompletionBackend.vb (src/VisualLLM.Server/Api/NativeChatCompletionBackend.vb)
• Low coverage: src/VisualLLM.Server/Hosting/ServerBootstrapper.vb (src/VisualLLM.Server/Hosting/ServerBootstrapper.vb)

• Unchanged — 1 containers · 0 contexts · 0 edges

Written by watchdog.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

mattneel/VisualLLM.NET was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.