As-Is
What the code actually contains.
ARCHITECTURE CONTRACT · EXPLORER · DETERMINISTIC CHECKS
Tests can pass.
Architecture can still drift.
ArchKeel checks architecture boundaries locally and in CI. Its optional change-check compares a candidate with an expectation published before submission, for humans and coding agents.
Architecture checks for coding agents
Local · No LLM in the checker · MIT · Python, Dart, TypeScript with different analysis scope
RECORDED FINDING / DATAMIMIC EE
An internal import. A declared boundary.
During the DATAMIMIC EE refactoring, ArchKeel reported an internal import even though the public interface existed. It was one of three interface findings; the focused test suite passed.
Python · before / after
from datamimic_ee.errors.context import DescriptorLocation # before
from datamimic_ee.errors import DescriptorLocation # afterRead the case study → · Python guide →
Source: DATAMIMIC EE field notes. We develop both DATAMIMIC and ArchKeel.
ArchKeel main: our own architecture160 files · 45 components
Target
What the contract declares.
Diff
Where implementation and Target differ.
Search · Health check · Perspectives · Fullscreen · SVG and Mermaid export
Open a component to explore its responsibilities, interfaces and dependencies. As-Is, Target and Diff show our own code and the contract declared for it.
Recorded snapshot · 79a2296 · generated 2026-10-29. Analysis limits and UNKNOWN are recorded in the report.
Open the full report ↗Latest published report ↗✓Source evidence for findings✓Declared-change checks✓UNKNOWN stays visible
OUR OWN PRACTICE
Used across rapiddweller projects
Teams at rapiddweller use ArchKeel across projects and technologies, including DATAMIMIC CE, EE and platform projects. The DATAMIMIC case below comes from our own work.
DATAMIMIC CE / EE
In DATAMIMIC CE and EE, ArchKeel surfaced imports across internal interfaces. The case study shows findings, corrections and analysis limits.
Read the case study →Platform projects
Teams also use ArchKeel in platform projects across different technologies.
GREEN TESTS ARE NOT ENOUGH
A decided boundary
becomes a checkable finding.
A coding agent can cross a boundary without failing a behavior test. This rule declares the boundary. The finding identifies the source location.
YOUR CONTRACTJSON · rule excerpt
{
"id": "DEP-RENDER-NO-STORE",
"kind": "forbidden_dependency",
"source": "shop.render",
"target": "shop.store",
"include_type_checking": true,
"rationale": "Text projection consumes typed values without touching persistence.",
"provenance": ["docs/architecture/shop.md"],
"decided_by": "architect"
}10 lines from the Shop rule. The full contract also contains components and other rules.
ARCHKEEL / DOCUMENTED FINDINGFAIL
render → store
Presentation reaches into persistence. This dependency is forbidden by the contract.
shop/render/text.py:9
from shop.store import OrderRepository- rule
- DEP-RENDER-NO-STORE
- finding
- rule.violated
- evidence
- closed_world.observed_forbidden
Source: Shop fixture in the README.
ARCHITECTURE GOVERNANCE
Fewer custom architecture gates
Agents can create a growing collection of drift and boundary checks. A shared architecture contract can consolidate overlapping structural rules when their scope and failure cases match.
Runtime behavior, API compatibility and security still need their own tests.
How to consolidate checks safely →EVIDENCE / PYTHON REPLAY
Eight tests still pass.
One call can no longer be resolved.
A switch to dictionary dispatch keeps eight behavior tests green. Static analysis can no longer resolve the new call. The candidate is rejected for that regression.
before → candidate
# before · sample/work.py
from sample.helpers import credit, debit
def run(key: str, amount: int) -> int:
if key == 'credit':
return credit(amount)
if key == 'debit':
return debit(amount)
raise KeyError(key)
# candidate · sample/work.py
from sample.helpers import credit, debit
def run(key: str, amount: int) -> int:
handlers = {'credit': credit, 'debit': debit}
return handlers[key](amount)Behavior tests8/8 → 8/8
Unresolved calls0 → 1
Architecture violations0 → 0
archkeel checkFAIL · exit 1
This replay measures static visibility. It does not establish a runtime defect. The source record contains the full conditions and call counts.
Conditions & source ↗Result JSON ↗Reproduce ↗WHY ARCHKEEL?
When would you add ArchKeel
to your architecture checker?
Import Linter and Tach check Python boundaries; ArchUnit tests JVM architecture, including calls and accesses. dependency-cruiser and Nx check dependencies in JavaScript/TypeScript projects.
ArchKeel combines declared-change checks, regression checks on comparable analysis evidence, and focused snapshot queries that retain UNKNOWN. ANMA and code-governance also support agents. Choose ArchKeel when you need this review loop.
Declared change
Compare the candidate with an expectation published before submission.
Detect evidence loss
Fewer findings are insufficient when analysis can see less.
Focused evidence
Query the contract and findings by scope. Keep global results and UNKNOWN.
Compare the tools against the review loop you need.
Compare tools and limitsYOUR FIRST CHECK
Install.
Review the boundaries.
Python 3.11+ and a Git repository with at least one commit. Use a Python version compatible with your project.
Ask your agent to read the architecture docs, propose boundaries, and let you decide which dependencies are allowed.
Read the setup guide ↗local setup
uv tool install archkeel
archkeel skill install codex
# or: archkeel skill install claudeFor a reviewed contract
archkeel validateFor the declared-change gate: archkeel check with the protocol configured. report produces evidence and can exit 0 despite FAIL or UNKNOWN.
ArchKeel 4.0.1 is released. Historical examples use their documented versions. Release notes ↗
ARCHKEEL CHECKS ARCHKEEL
Our architecture. Our findings.
We check our own code with the same tool. The snapshot in the Explorer contains these rule assessments:
126 rules
Completed rules without violations.
0 rules
Rules with recorded violations.
0 rules
Rules whose required evidence is incomplete.
Overall result: UNKNOWN. Passing rules leave the remaining analysis gaps open.
Inspect findings and evidence ↗FAQ
What does ArchKeel check?
What is ArchKeel?
Architecture checks for coding agents. ArchKeel checks declared architecture boundaries and changes in AI-assisted code. The CLI runs locally and deterministically, without an LLM in the checker.
When is another checker enough?
If you only need import or module constraints in your existing stack, your current checker may be sufficient. ArchUnit also offers JVM structural tests.
What can ArchKeel not prove?
Complete runtime correctness or good architecture. Analysis is static and depends on the language profile.
Is Studio available today?
The collaborative Studio interface is planned. The CLI and its reports are available. See the Studio concept on Vision & Roadmap.