bce-engine weekly downloads statistics

<p align="center"> <picture> <source media="(max-width: 600px)" srcset="assets/bce-banner-mobile.svg"> <img src="assets/bce-banner.svg" alt="bce — architecture that holds while agents move fast. A human-owned blueprint and an agent code change enter the BCE gate. The gate catches a forbidden dependency, names its source line, and blocks the merge."> </picture> </p>

Check architectural boundaries in agent-written code

Development tree: 0.5.0 candidate, unpublished. The registry release: v0.4.0 remains the supported installation below. Declared-stack enforcement is local development work; no 0.5.0 release, pin or self-adoption is asserted. Before any future candidate installation, verify publication with npm view bce-engine@0.5.0 version dist.integrity. A failed lookup means it is unavailable; do not substitute an unverified installation. The verified 0.4.0 foundation is published and active as the exact Lane-A pin.

The candidate retains the 0.4.0 stack foundation (stack snapshot, stack diff, cross-OS golden-byte proof, and read-only MCP classification) and adds selected declared-stack enforcement to the ordinary gate plus offline v2 replay. It does not add automatic repair or registry resolution.

bce gives coding agents a local, deterministic architecture check. A versioned EngineeringBlueprint records the repository's structural rules. Agents draft those rules from your intent, inspect the code, and repair violations; the same engine checks every pull request. Humans own the intent and approve policy changes. Agents operate the day-to-day loop.

Released support (v0.4.0): TypeScript/JavaScript framework-surface AST extraction, direct TypeScript/JavaScript module boundaries, a Python import-surface MVP, and structured Python module boundaries. Node 22+ is required; the contract remains pre-1.0.

Evidence boundary: a score of 100 means the implemented checks passed over the observed surface. Route guard checks find governed call sites; they do not prove authorization, tenant isolation, or execution on every path. See the route evidence limits and correction, including the export forms missed by the immutable v0.3.0 release. Start with a bounded pilot and verify realistic violations in your own repository.

<!-- award-slot: reserved. Activate only in a PR that links an award actually won. --> <p align="center"> <a href="https://github.com/blueprint-conformance/bce/actions/workflows/self-gate.yml"><img src="https://github.com/blueprint-conformance/bce/actions/workflows/self-gate.yml/badge.svg" alt="self-gate workflow status"></a> <a href="https://github.com/blueprint-conformance/bce/actions/workflows/ci.yml"><img src="https://github.com/blueprint-conformance/bce/actions/workflows/ci.yml/badge.svg" alt="continuous integration workflow status"></a> <img src="assets/badges/tests.svg" alt="tests: 1414"> </p>

Watch BCE govern its own main branch: live GitHub stages, authenticated self-adoption, and explicit evidence boundaries.

Watch the context move

<p align="center"> <a href="https://blueprint-conformance.github.io/bce/films/#context-spectrum"><img src="https://github.com/blueprint-conformance/bce/releases/download/media-2026-09-07/context-spectrum-preview.gif" alt="Animated preview of the architectural zoom from services to components and code. Open the complete interactive C1–C4 context spectrum."></a> </p>

Explore the interactive C1–C4 spectrum · Watch the films · Read the static overview

Follow context narrowing into work, inherited rules surviving the zoom, and findings returning as evidence for review. This illustrates the wider reference architecture; it is not a claim that the complete platform loop is released in BCE. C1–C4 here means architectural zoom levels, distinct from the engine’s constraint type identifiers. The brief preview plays once; the full film and interactive experience have playback controls.

Start with your coding agent

Give your existing agent this task:

Read https://blueprint-conformance.github.io/bce/llms.txt and its agent start guide.
Inspect this repository and identify one supported architecture boundary from our stated intent.
Use BCE to draft the rule, prove a real RED → code fix → GREEN, and wire the local agent loop.
Keep setup advisory and present policy changes for my review. Report unsupported scope explicitly.

The agent start guide routes an existing gated repository straight to MCP run_gate {} and a new repository to local authoring and onboarding. Your current agent can do this with its own tools; BCE needs no additional model account for that path. The blueprint inspection tools and review cockpit let humans examine the same contract and evidence.

Run a real gate

Three commands. No account, hosted service, API key, or repository setup:

npm view bce-engine@0.4.0 version dist.integrity
npm install --save-dev --save-exact bce-engine@0.4.0
npx --no-install bce demo

The released demo runs one conforming tree and one drifted tree. List six targeted recipes for extension registration, tenant access, egress, TypeScript and Python module layering, and configuration widening, then run the boundary closest to your repository:

npx --no-install bce demo --list
npx --no-install bce demo --recipe module-layering

Run the released First Win recipes, or keep the zero-argument proof above.

The architecture package

One checked-in blueprint defines the intended components, relationships, and boundaries. BCE extracts the repository it received, compares the two, and returns one deterministic verdict.…