Executive summary
EdgeSutra AI 0.2.1 is an evidence-first toolkit that tells engineering teams what is proven, what is merely declared and what is unknown when they plan to run an AI model on an edge device (phone, Raspberry Pi, embedded board, laptop NPU).
The problem
Teams routinely ship quantized models on the strength of a file size, a vendor datasheet or a laptop benchmark. Those are not evidence that a model runs correctly, fast, within memory and within power budget on the real target. The cost of a wrong assumption is a failed field rollout.
What EdgeSutra does
| Capability | Outcome for a decision maker |
|---|---|
One-command audit (edgesutra audit) | A shareable HTML/Markdown/JSON report with a verdict and a list of what was not tested |
| Static compatibility check | Early, cheap rejection of impossible model/runtime/device combinations |
| Safe ONNX metadata inspection | Operators, opsets and SHA-256 read without ever executing the model |
| Host-only benchmark with guardrails | Real timings, labelled as host-only; never passed off as device latency |
| 20 portable agent skills | The same review discipline inside Claude Code, Cursor, Codex, Copilot, Gemini CLI |
What it deliberately does not do
It is not an inference engine and does not run models on devices yet. It never invents energy, carbon, memory-peak or device-latency figures. It cannot output "ready to ship": the best verdict is REVIEW_REQUIRED until on-device evidence and a human sign-off exist.
Why trust it
- Zero runtime dependencies, no network access, no telemetry.
- Recorded test run: 86 tests, 82 passed, 0 failed, 4 skipped on v24.15.0 (win32/x64), plus a 2000-input parser fuzz with 0 unexpected crashes.
- Every public number is regenerated by
npm run proof; see Assurance & evidence. - Apache-2.0, no bundled third-party code or model weights.
Status
Working offline core (v0.2.1). Planned: ONNX Runtime CPU inference, isolated quantization, first real-device connector. See Roadmap.
Creator: Vatsal Shah · Repository: https://github.com/shahvatsalofficial/edgesutra-ai