● Runtime trust layer for agentic AI

Let your AI agents act — with proof they're safe.

KEEL is the vendor-neutral system-of-record for AI accountability. It verifies every autonomous agent action before it executes — blocking catastrophes, catching fabrications, and earning trust from evidence — then signs tamper-proof proof your auditor, insurer, and regulator now require.

Works with any agent framework — LangChain, OpenAI SDK, CrewAI, Claude Code, Cursor, custom. Deterministic checks in ~2ms. Every decision signed & logged.

AI AGENT
proposes an action
KEEL GATEWAY
verify before execute
⛔ BLOCK
catastrophe / fabrication
·
⏸ ESCALATE
human approval queue
·
✅ ALLOW
+ signed certificate

Companies are liable for what their AI does — and can't prove they control it.

AI agents now act: they send messages, move money, run commands, change data. When they act wrongly, the company pays. Yet nothing stands at the moment of action with a guarantee — and no standard proof of control exists.

40%+
of agentic-AI projects forecast cancelled by 2027
Gartner, 2025
95%
of enterprise GenAI pilots deliver no measurable P&L
MIT / NANDA, 2025
700+
organizations breached through one AI integration
Salesloft / Drift, 2025
$0
proof a permission prompt leaves for your auditor or insurer
the accountability gap

Four layers decide every action — in milliseconds.

1

Tripwires — block the irreversible, without asking

Database drops, funds transfers, recursive deletes, credential exports, mass sends are refused unconditionally — even in shadow mode, even for a trusted agent. A human can't be tricked into approving what's never offered.

2

Policy & grounding — enforce rules and catch fabrication

Scope, budget, and rate limits per action class. Every claim is checked against its cited evidence: invented numbers and out-of-context quotes are stopped deterministically.

3

Calibrated autonomy — trust earned from evidence, not vibes

Per agent and action class, KEEL computes an anytime-valid lower bound on success from externally-verified outcomes, with drift detection and conformal risk control. Routine work earns its way to auto-approval; risky or novel actions go to a human.

4

Signed record — tamper-proof proof of everything

Every decision becomes an Ed25519-signed certificate in an append-only Merkle log. Export a standards-mapped evidence pack in one click.

Not another permission prompt. The trust layer underneath all of them.

Non-bypassable enforcement

Deploy as an MCP proxy that holds the tools: the agent physically cannot act without a decision. Or drop in the SDK / REST call. Fails closed.

Frontier statistics

Anytime-valid confidence sequences (valid under continuous monitoring), conformal risk control that self-tightens on harm, Page-Hinkley drift, behavioral anomaly detection.

Cryptographic audit trail

Signed, Merkle-anchored, independently verifiable. The evidence auditors and AI insurers sample — mapped to EU AI Act, ISO 42001, and NIST AI RMF.

Vendor-neutral & universal

Any framework, any language, any field. One policy and one log across every agent you run — coding assistants to customer-service bots to back-office automation.

Compounding trust

Every certified action is a labeled outcome. Your calibration corpus grows and can't be copied — the longer it runs, the more autonomy you safely unlock.

Honest by design

Abstention is a first-class answer. Guarantees state their exact scope on the certificate. A system that tells you when it doesn't know is one you can build on.

Three lines. Any agent. Zero-regression start.

New agents begin in shadow mode: KEEL signs and records everything, blocks only catastrophes. Flip enforcement on when you trust what you see.

# pip install keel  ·  keel serve
from keel.sdk import KeelGuard

guard = KeelGuard("http://localhost:8347", agent_id="my-agent")
guard.register(name="My Agent", action_classes={
    "issue_refund": {"risk": "high", "budget_per_day": 500, "requires_evidence": True}})

@guard.protect("issue_refund", cost=lambda amount, **kw: amount)
def issue_refund(customer_id, amount):
    ...  # runs only if KEEL allows — or a human approves

Wherever an AI agent touches the real world.

Coding & DevOps

Guard AI coding assistants

Claude Code, Cursor, Copilot agents run commands and edit files. KEEL blocks the Replit-class database wipe and Gemini-class file destruction — before they execute.

Customer operations

Autonomous support & refunds

Bots that issue refunds and change accounts have no built-in approval prompt. KEEL is the only thing between them and real money — with budgets, evidence checks, and a signed trail.

Finance & back office

Agents that move money

Payments, reconciliation, procurement. Velocity caps and earned autonomy stop the trust-farming attack that escalated a $500K limit into $5M of fraud.

Regulated industries

Provable human oversight

Healthcare, finance, public sector. Risk-tiered escalation with recorded approver identity — the Article 14 human-oversight evidence your regulator asks for.

The evidence pack your auditor and insurer already ask for.

One click produces a self-verifying bundle: uniform-randomly sampled signed decisions with Merkle inclusion proofs, per-agent calibration tables, the human-oversight record, and control mappings. It proves itself from the log root.

EU AI Act · Art 12 & 14 ISO/IEC 42001 NIST AI RMF SOC 2 evidence Cyber-insurance controls

Open core. Start free, scale when it's load-bearing.

The engine and SDK are open and self-hostable. Paid tiers add managed hosting, hardened key custody, and the compliance evidence workflow.

Open Source

Free
self-hosted, MIT-style
  • Full gateway & SDK
  • All checkers & calibration
  • Signed transparency log
  • MCP proxy & REST API
  • Community support
Read the docs

Team

$10 / week
managed cloud
  • Everything in Open Source
  • Managed, HA hosting
  • HSM-backed signing keys
  • Approval queue integrations (Slack, ticketing)
  • Evidence-pack export & scheduling
  • Email & chat support
Upgrade — $10/week

Enterprise

Custom
regulated & at scale
  • Everything in Team
  • SSO, RBAC, private deployment
  • WORM retention & SCITT export
  • Auditor & insurer evidence workflow
  • Custom tripwire & policy sets
  • SLA & solution engineering
Contact us