Skip to content
View davidnichols-ops's full-sized avatar
  • 07:38 (UTC -06:00)

Block or report davidnichols-ops

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
davidnichols-ops/README.md

David Nichols

I work on computer vision, inference reliability, and tools for inspecting and controlling what AI agents do.

I'm especially interested in the parts around the model: preserving data and coordinate contracts through a workflow, isolating runtime failures across hardware backends, and making automated decisions traceable to code and policy. Most of my work is in Python, with JavaScript for MCP tooling and a focus on Apple Silicon.

Active project

  • trustcard — tooling for inspecting MCP servers, signing capability manifests, detecting capability drift, and enforcing which tool calls are allowed. Published as mcp-trustcard.

Selected upstream contributions

Merged pull requests in projects maintained by their respective teams:

Project Contribution
Roboflow Inference Reuse a run-scoped thread pool for workflow execution
Roboflow Inference Preserve image dimensions on empty VLM detections
Roboflow Inference Clear every touched namespace in workflow cache blocks
Roboflow Python SDK Return single-upload results from Project.upload()
TensorFlow Fix XLA DenseBincount negative-input validation for runtime tensors
Ultralytics Exclude Sigmoid from TensorRT INT8 quantization
Hugging Face PEFT Document hybrid Mamba-Transformer target_modules pitfalls

All merged upstream pull requests

How I work

I focus on understanding a system well enough to reproduce and explain why it failed—building that judgment through root-cause debugging, differential testing, and maintaining my own tools.

  • Start with a minimal reproducible failure and keep fixes narrow.
  • Add regression tests that fail before the patch and report exact verification boundaries.
  • Keep model observations, deterministic policy, and human authorization separate where reliability matters.

Older repositories hold prototypes, archived experiments, and retired research (including apple-quality-recognition-engine, closed out with a documented engineering postmortem and partial dataset). Each repository's README states its current status.

Pinned Loading

  1. trustcard trustcard Public

    Cryptographic trust infrastructure for MCP servers — signed manifests, TOFU pinning, two-gate enforcement, and the "npm audit" scanner.

    JavaScript 4 1