Show HN: LoopVera – evidence ledger for pipeline debugging (no code yet)

LoopVera, an open-source runtime evidence ledger for debugging vision pipelines and agent workflows, is being developed to provide a see-tweak-diff-sign-off loop without replacing existing operators. The project is in early stages with no runnable code yet, aiming to bring industrial-grade debugging to open-source vision stacks and eventually support AI agent workflows.

English · 简体中文 /ProofRun/LoopVera/blob/main/README.zh-CN.md See inside your vision pipeline.Bring industrial-grade runtime debugging to the open-source vision stack — while exploring theruntime evidence ledger for agent workflowsunderneath. 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 beingopen-sourced step by step, in public— first the reasoning and design, then the specs, then the code skeleton, then working slices. See the . RoadmapPhase 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." 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 loopvera and loopvera open arenot published yet. python 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 /ProofRun/LoopVera/blob/main/docs/zh-CN/vision.md . 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 /ProofRun/LoopVera/blob/main/docs/en/agent-workflows.md · Why not LangGraph / all-in-one /ProofRun/LoopVera/blob/main/docs/en/why-not-langgraph.md . 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. | 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 · Architecture & ADRs | Layering, four pillars, decision records | Engineers who want to shape the design | ⏳ next | 3 · Contracts L0 | JSON Schema, verb catalog, conformance tests | Implementers, spec folks | ⏳ planned | 4 · Code Skeleton | Buildable Rust spine, walking skeleton | Contributors who write real code | ⏳ planned | 5 · First Vertical Slice | observe → diff demo for one library | Early users, integration authors | ⏳ planned | 6+ · Filling in | Gate/authority, more integrations, Studio UI, pip | The whole community | ⏳ planned | Full detail, entry points, and definitions of done: ROADMAP.md . — for LoopVera Vision /ProofRun/LoopVera/blob/main/docs/en/vision.md vision / CV engineers : problem, loop, comparison, honest status.— for AI agent workflows /ProofRun/LoopVera/blob/main/docs/en/agent-workflows.md AI agent developers : the evidence ledger your agents are missing.— for Pipeline debugging pain points /ProofRun/LoopVera/blob/main/docs/en/pipeline-debugging-pain-points.md anyone tuning pipelines : a problems-only discussion piece.— for Why not LangGraph / all-in-one /ProofRun/LoopVera/blob/main/docs/en/why-not-langgraph.md agent-infra : graph orchestration vs. an evidence/authority ledger. All docs are bilingual — see the docs index /ProofRun/LoopVera/blob/main/docs/README.md . This is build-in-public capability exploration, not a commercial launch. There is no fixed ship date . - ⭐ — follow the direction as it evolves. Star / Watch on GitHub https://github.com/Proofrun/LoopVera - 💬 — real pipeline pains and architecture RFCs. This is the GitHub Discussions https://github.com/Proofrun/LoopVera/discussions normative source of truth for decisions. - 🎮 — chat & build help not normative; conclusions go to Discussions . Discord · Open Build https://discord.gg/7Xfz8fCmE - 📖 — see labels like Issues https://github.com/Proofrun/LoopVera/issues good-first-issue , help-wanted , and design-rfc . - 🤝 Read before opening a PR, and the CONTRIBUTING.md /ProofRun/LoopVera/blob/main/CONTRIBUTING.md Code of Conduct /ProofRun/LoopVera/blob/main/CODE OF CONDUCT.md . Early contributors' feedback directly shapes which happy path we wire first. MIT /ProofRun/LoopVera/blob/main/LICENSE © 2026 LoopVera / Proofrun. See every step. Diff every run. Orchestration swappable. Workers swappable. Ledger not.