Stop untrusted context becoming executable authority.
Trust context. Verify authority. Interdict unsafe action. AgentInterdict sits at the runtime boundary of your autonomous agent — blocking memory poisoning, tracking provenance, and revalidating every action before it executes.
Untrusted context is becoming executable authority.
Autonomous agents act on context. When that context is poisoned, spoofed, or carries forged authority, the agent executes actions it was never authorised to take — silently, across every future session.
Instructions hidden in data
Malicious instructions embedded in documents, emails or web pages override the agent's system prompt.
Credentials written to memory
API keys, tokens and private keys get persisted into long-term memory, where they can be exfiltrated.
False facts that persist
Injected "facts" become permanent memory, corrupting every future decision the agent makes.
Fake authority to act
Content that claims to be from a trusted source gains unwarranted power over the agent's actions.
Every action passes through the interdict.
AgentInterdict sits at the runtime boundary of your agent. Nothing executes without passing provenance, trust, and authority verification.
Injection is deflected.
Obfuscated, encoded and split attacks are detected and knocked out of the stream before they can persist.
Secrets are masked.
Credential-shaped content is redacted to a hash — the secret itself never reaches memory.
Poison is contained.
Suspicious memories are quarantined and their entire derivation chain is contained atomically.
Authority is bound to origin.
Derived content can never outrank its source. High-risk actions require sealed, action-scoped human authorization.
A transparent pipeline, not a black box.
AgentInterdict is a local, auditable runtime. It never sends your agent's context to the cloud, and every decision is logged and verifiable.
Your agent's context never leaves your machine.
AgentInterdict runs entirely on your hardware. No cloud, no telemetry, no data exfiltration — by construction.
- ✓ Fully local — no cloud dependency
- ✓ Open and auditable
- ✓ Fail-closed by default
- ✓ Operator / runtime privilege separation
Engineered for precision.
{
"memory": "<recalled bundle>",
"action": "send_email",
"authority": "untrusted"
}
→ BLOCKED — high-risk action without sealed human authorization
See the enforcement, live.
Every decision is logged and auditable. The dashboard shows what was scanned, what was blocked, and why.
Enforcement summary
Recent events
Watch an attack get interdicted.
Run a live, reproducible scenario. A malicious instruction embedded in an untrusted document tries to make the agent exfiltrate a credential — AgentInterdict catches it at the runtime boundary.
Drop into your existing stack.
AgentInterdict wires into the agents and frameworks you already use. Enforce at the runtime boundary without rewriting your agent.
Drop-in enforcement layer for Hermes agents. Bind authority to origin on every memory write and tool action.
managed packSkill-based integration for OpenClaw. Guarded retrieval and action-time revalidation out of the box.
skillModel Context Protocol server. Intercept tool calls and memory operations before they reach your tools.
protocolLanguage-agnostic HTTP API — scan, memories, search, action-check, stats. Integrate from any stack.
apiTested. Auditable.
We publish our test suite and its results — passing and failing — so you can run it yourself. A security tool that hides its misses isn't trustworthy.
| Suite | Passed | Failed | Skipped | Status |
|---|---|---|---|---|
| Core enforcement tests | 78 | 0 | 1 | passing |
| Tamper / fail-closed tests | 9 | 0 | 0 | passing |
Run the full suite yourself with pytest tests. The enforcement invariants (origin-bound authority, no derivation amplification, retrieval ≠ permission, action-time re-scoring, credentials-not-memory, fail-closed tampering) are exercised by these tests. We do not publish block-rate percentages we can't reproduce.
Simple, transparent pricing
Community
- ✓ Origin-bound local gateway
- ✓ Static transparent risk rules
- ✓ Single-operator GUI
- ✓ Local audit & integrity verification
- ✓ Basic REST API
Pro
- ✓ Everything in Community
- ✓ Continuously updated threat feed
- ✓ Hosted advanced semantic classifier
- ✓ Hermes / MCP managed integration packs
- ✓ Audit export & reporting
- ✓ Remote policy updates
Business
- ✓ Everything in Pro
- ✓ Multi-agent / multi-namespace management
- ✓ Team accounts & RBAC
- ✓ Central policy packs
- ✓ Organisation dashboards
- ✓ Alerting & webhooks
Enterprise
- ✓ Everything in Business
- ✓ SSO / SAML
- ✓ Private cloud / VPC / on-prem
- ✓ Signed offline leases
- ✓ SIEM integration
- ✓ SLA & priority support
Get early access
Join the waitlist for Community, or get notified when Pro / Business / Enterprise launch.