English · 简体中文
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 a runnable Studio governance shell (Path B), then architecture, contracts, and the vision workbench wedge. See the Roadmap. Phase 1 (Problem & Vision) is done; Phase 2 (Studio Path B — governance shell you can build and run) is next. This repo has governance and Phase 1 narrative docs — no runnable code here yet. Starring means "watch this direction," not "production-ready."
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.
| Is | Is not |
|---|---|
| A capability proof: can a workflow-state IDE + evidence/authority ledger actually be engineered? | Another graph-orchestration framework or LangGraph replacement |
| Vision pipeline debugging as the first load-bearing skin (direction anchor) | A shipped commercial vision IDE or a stable pip package |
A layered experiment: orchestration swappable, ledger not (Rust director + Core verbs + .loopvera/) |
A project where "docs complete = implementation complete" |
This is the interaction path we are building toward.
pip install loopveraandloopvera openare 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 maskpip 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 workbenchRead the full pain-point + vision write-up: LoopVera Vision · 简体中文.
The LoopVera column is target design — not a claim that everything works today.
imwrite + folders |
ad-hoc matplotlib | wire up Rerun yourself | closed commercial vision IDE | LoopVera (target) | |
|---|---|---|---|---|---|
| every step visible | ✅ | ✅ | ✅ | ||
| tweak param & rerun | ❌ | ❌ | ❌ | ✅ | ✅ |
| side-by-side diff across runs + param diff | ❌ | ❌ | ✅ | ||
| library-agnostic (no operator lock-in) | ✅ | ✅ | ✅ | ❌ own only | ✅ |
| adds the loop for AI (evidence closed loop) | ❌ | ❌ | ❌ | ✅ | |
| price | free | free | free | 💰💰💰 | free / open source |
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.
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.
LoopVera is released in stages so that every step carries standalone value and invites a different kind of contributor. Phase 2 ships a runnable Studio governance shell first — so you can build and run Path B before reading a line of architecture.
| Phase | What ships | Who it invites | Status |
|---|---|---|---|
| 0 · Front Door | README, governance, roadmap, contribution channels | Everyone deciding whether to watch | ✅ done |
| 1 · Problem & Vision | Pain-point narrative, vision, comparison | People who feel the same pain | ✅ done |
| 2 · Studio Governance Shell | Theia Path B + serve/director + H1 smoke + GIF | Rust / Theia / systems contributors | ⏳ next |
| 3 · Architecture & ADRs | Layering, four pillars, decision records | Engineers who want to shape the design | ⏳ planned |
| 4 · Contracts (L0) | JSON Schema, verb catalog, conformance tests | Implementers, spec folks | ⏳ planned |
| 5 · Runtime / Workbench filling | Vision workbench / observe→diff wedge | CV users + UI contributors | ⏳ planned |
| 6+ · Filling in | Gate/authority, more integrations, pip | The whole community | ⏳ planned |
Full detail, entry points, and definitions of done: ROADMAP.md.
- 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.
This is build-in-public capability exploration, not a commercial launch. There is no fixed ship date.
Who's behind this: LoopVera is started and maintained by a single developer, in public. Right now I'm after feedback and design critique more than code: tell me where the direction is wrong while it's still cheap to change.
- ⭐ 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, anddesign-rfc. - 🤝 Read CONTRIBUTING.md before opening a PR, and the Code of Conduct.
Early contributors' feedback directly shapes which happy path we wire first.
MIT © 2026 LoopVera / ProofRun.
See every step. Diff every run. Orchestration swappable. Workers swappable. Ledger not.