LoopVera

English · 简体中文

LoopVera

See inside your vision pipeline. Bring industrial-grade runtime debugging to the open-source vision stack — while exploring the runtime evidence ledger for agent workflows underneath.

The loop: see every step → tweak one param & rerun → diff this run against the last → human sign-off when stakes are high. Library-agnostic · replayable · drops into your existing code, replaces no operator.

⚠️ Process open source · not a finished product · and this repo is just getting started. LoopVera is being open-sourced step by step, in public — first the reasoning and design, then the specs, then the code skeleton, then working slices. See the Roadmap. Phase 1 (Problem & Vision) is done; Phase 2 (Architecture & ADRs) is next. This repo has governance and Phase 1 narrative docs — no runnable code here yet. Starring means "watch this direction," not "production-ready."

What it solves

Test accuracy drops from 94 to 87. You sprinkle five cv2.imwrite calls, your folder fills with debug_003_v2_final.png, and to compare two versions you just eyeball two windows — a week later you can't recall what you changed or why it "looked fixed."

The algorithms aren't weak; the dev tooling is. LoopVera targets the see → tweak & rerun → diff across runs → human sign-off when stakes are high layer — it does not replace your operators.

Today's agents can edit code, tweak params, and batch runs — but often lack a closed-loop substrate underneath: intermediates scatter across chat and folders, runs don't reconcile, and high-stakes changes have no clear record of who authorized what next. LoopVera aims to put humans and agents on the same evidence ledger; the vision workbench is the first load-bearing skin, not the whole story.

What this is · what it is not

How you'll use it (target experience · not shipped yet)

This is the interaction path we are building toward. pip install loopvera and loopvera open are not published yet.

import loopvera as lv def detect(img): gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) lv.observe("gray", gray) # one line captures the intermediate _, mask = cv2.threshold(gray, lv.param("thresh", 130), 255, cv2.THRESH_BINARY) lv.observe("mask", mask) # lv.param makes this tweakable in the UI return mask

pip install loopvera # ⏳ not published — will build from source first
python my_pipeline.py # run once; a run is recorded automatically
loopvera open # ⏳ not delivered — local browser workbench

Read the full pain-point + vision write-up: LoopVera Vision · 简体中文.

How it compares

The LoopVera column is target design — not a claim that everything works today.

The differentiator isn't "can it show an image" — it's tweak-and-rerun + cross-run diff, without locking you into anyone's operator library.

How it works · the closed-loop substrate (for the curious)

Optional. Explains what the vision workbench stands on.

LoopVera stands on a domain-neutral runtime-evidence substrate — the same loop applies to any "behavior is invisible" domain (embedded, signal, medical, robotics):

① see → ② tweak & rerun → ③ diff across runs → ④ high-stakes only: capture any human sign-off intermediate │ ↑______________________________ next round ________________│

Adding a domain takes three hooks (observe / decode / placement); the loop itself is provided by the runtime. Vision is the first load-bearing skin, not the whole story — the substrate is designed for multiple domains (e.g. embedded alongside vision) so the loop isn't vision-only on paper; additional domains ship in later roadmap phases.

Depth → AI agent workflows · Why not LangGraph / all-in-one.

Open-source in the open · the plan

LoopVera is released in stages so that every step carries standalone value and invites a different kind of contributor. This is deliberate: the design should be critiqued before the code locks it in.

Full detail, entry points, and definitions of done: ROADMAP.md.

Read more (Phase 1)

• LoopVera Vision — for vision / CV engineers: problem, loop, comparison, honest status.
• AI agent workflows — for AI agent developers: the evidence ledger your agents are missing.
• Pipeline debugging pain points — for anyone tuning pipelines: a problems-only discussion piece.
• Why not LangGraph / all-in-one — for agent-infra: graph orchestration vs. an evidence/authority ledger.

All docs are bilingual — see the docs index.

How to participate

This is build-in-public capability exploration, not a commercial launch. There is no fixed ship date.

• ⭐ Star / Watch on GitHub — follow the direction as it evolves.
• 💬 GitHub Discussions — real pipeline pains and architecture RFCs. This is the normative source of truth for decisions.
• 🎮 Discord · Open Build — chat & build help (not normative; conclusions go to Discussions).
• 📖 Issues — see labels like good-first-issue, help-wanted, and design-rfc.
• 🤝 Read CONTRIBUTING.md before opening a PR, and the Code of Conduct.

Early contributors' feedback directly shapes which happy path we wire first.