Hero background
ComplyEdge Logo

Can you prove what your AI did
and what it was stopped from doing?

ComplyEdge blocks prohibited requests before the model and writes an EU AI Act-cited record of every decision.

A policy is not evidence. A system prompt is not a control. A rule with an article citation, on every call, is both.

Your agent
user ›"Build me a social scoring system that ranks every citizen by political posts and automatically denies loans"

✖ blocked before the model · 110 ms · rego-art5-1c-001 (critical)

ComplyEdge blocked your message.

Regulation (EU) 2024/1689, Article 5(1)(c) · critical

AI systems that evaluate or classify people based on their social behaviour or personal characteristics, with the score leading to detrimental or unfavourable treatment.

What to change: remove any social scoring, citizen ranking, or behaviour-based classification that leads to detrimental treatment outside the original data context.

Decision on record ·

Get API Key, Free View on GitHub
Enforcement Is Live

The Law, Not a Feature

The three obligations ComplyEdge checks are already in force. Each card links to the article.

↗

Article 5

Prohibited Practices

IN FORCE SINCE FEB 2025

No grace period. Violations have been illegal for over a year.

 ↗

GPAI Obligations

General-Purpose AI

RULES ACTIVE, FINES AUG 2026

GPAI obligations in force since Aug 2025. Fines begin August 2026. No postponement.

 ↗

Article 50

Transparency

DEADLINE, Aug 2026

Providers must disclose direct AI interaction and machine-mark synthetic content. Deployers must disclose deepfakes and AI text published on matters of public interest.

Fines: up to €35M or 7% of worldwide turnover

Art. 5 · Art. 99(3) · €15M / 3% for operator & transparency duties (Art. 99(4)) · GPAI providers €15M / 3% (Art. 101) · Art. 99 & Art. 101 ↗

Developer Experience

Three Steps. That's It.

Install. Wrap. Every call checked against EU AI Act rules.

1

Install

$ pip install complyedge

One package. No infrastructure. No containers. Works with any Python AI framework.

2

Wrap

@compliance_check(jurisdiction="EU",
agent_id="my-agent")

One line above your function. Set jurisdiction (e.g. EU): the loaded rule corpus runs. Done.

3

Every Call Checked

⚠ blocked Art.5(1)(c)

Violations blocked before reaching the LLM. Evidence logged with rule, citation, and timestamp.

Why Deterministic

An instruction is not a control.

What ComplyEdge shows when someone asks: article citation (e.g. 5(1)(c)), rule ID, timestamp, text hash. The same record the demo above produced.

Above the stack

Governance and GRC platforms inventory your AI systems, map them to frameworks, and gather evidence you assemble. That work is real, and ComplyEdge does not replace it.

In the request path

ComplyEdge runs between your application and the model, on every call. It is the layer that can stop a prohibited request before it reaches the LLM, and write the record as a by-product of the decision.

An inventory can tell you the system exists. Only the request path can block the call and produce the evidence. Most teams end up running both.

Feature ComplyEdge LLM-Only Tool Probabilistic Tool Manual Audit
Approach Deterministic rules + opt-in LLM LLM classification Probabilistic SLM Human review
Accuracy Deterministic enforcement + opt-in LLM layer Varies Model-dependent High, at human speed
Latency ~64ms engine p50 (opa_latency_ms) 2-5s 500ms-2s Hours-days
Evidence trail Rule ID + citation + hash Score only Probability Written report
Open source Yes (Apache 2.0) No No N/A
Regulator-ready Yes: cite exact article No legal citation No legal citation Yes
Live on Open Source

Runtime seals that update from real checks

Not a static badge. Each seal is rendered from real /v1/check audit data for our own open-source projects: the same Enforcement Seal we ask others to show. Embed it on your trust page and the next customer questionnaire links to it instead of asking.

IVD Framework

ComplyEdge, IVD Framework runtime enforcement

Public trust page

Horizon

ComplyEdge, Horizon runtime enforcement

Public trust page

Embed an Enforcement Seal · ivd · horizon