Suvra
Action Layer Active

Suvra — the action layer for AI agents

Stop your AI agents from destroying things.

Your agents now have real shell, database, and cloud access. Suvra sits between them and the real world — blocking catastrophic actions, gating risky ones for a human, and recording every decision. Deterministic, sub-millisecond, no LLM in the path.

Apache-2.0 open source · pip install suvra · Works with Claude Code, Codex, OpenClaw, Hermes & any MCP server

suvra demo
$ suvra demo
Suvra — agent action firewall
No policy file. No setup. Just the built-in guardrail classifier.

[1/4] rm -rf / --no-preserve-root              BLOCKED  (catastrophic: destructive shell)
[2/4] DROP TABLE customers;                    BLOCKED  (catastrophic: destructive SQL)
[3/4] rm -rf build/                            NEEDS APPROVAL  (risky: destructive shell)
[4/4] fs.write_file workspace/notes.txt        ALLOWED  (safe)

Protected in five minutes

$ pip install suvra
$ suvra demo # watch it block catastrophic actions
$ suvra init claude-code # protect Claude Code with a PreToolUse hook

$ suvra mcp wrap -- npx -y @modelcontextprotocol/server-filesystem .
Claude CodeOpenAI CodexOpenClawHermesAny MCP server

All four runtimes verified end-to-end against the real agent binaries — not mocks.

What it catches

A deterministic, zero-config classifier runs before any policy engine — no LLM, no network call, sub-millisecond.

Destructive shell

Blocked

rm -rf, mkfs, dd of=/dev/*, fork bombs, chmod -R 777, curl | bash

Destructive SQL

Blocked

DROP TABLE, TRUNCATE, DELETE/UPDATE without WHERE (incl. via psql/mysql -e)

Force-push / history rewrite

Blocked

git push --force to protected branches, git reset --hard

Infra destroy

Blocked

kubectl delete, terraform destroy / -auto-approve

Secret-file access

Gated for approval

.env, private keys, credential files

Mass deletes

Gated for approval

bulk file/record deletion above a safe threshold

No LLM in the decision path
No network calls
Sub-millisecond decisions
Every decision explainable

Every action becomes an asset

Suvra sits in the action path, not observing from outside. The same stream that blocks catastrophic actions also powers audit, compliance, evals, and analytics.

Control

Block catastrophic actions, gate risky ones for a human, allow safe ones through. Zero-config classifier, deny-by-default policy engine, 60+ rule library, simulator, and human approvals in Slack.

Record

Nothing passes through invisibly. Every decision lands in an explainable audit trail that rolls up into SOC 2, NIST AI RMF, and ISO 27001 compliance reports — and into durable institutional memory.

Compound

The record becomes signal. Evals catch quality drift, the Learning Loop turns every block into a lesson, and Analytics tracks pass/deny rates and cost-to-outcome.

Why Suvra

Deterministic, not another ML classifier

Regex/parser decisions, reproducible, sub-millisecond, you see exactly which rule fired.

In the action path, not watching from outside

It can actually stop an action, and every action becomes an audit, compliance, and eval asset.

Works when the agent's own guardrails don't

Verified live: blocked a real rm -rf under Codex running with --dangerously-bypass-approvals.

Zero-config to start, full policy engine when you need it

And Apache-2.0 open source, free including production.

How it scales

Enforcement Nodes

Fail-closed, offline-capable, deployed near your agents.

A2A delegation

Agent-to-agent delegation, policy-gated through the same engine.

Runtime & Gateway

Preview

Workflow engine, MCP server registry, deployment templates.

Pricing

Free

$0

CLI, local firewall, local dashboard, 1 agent.

Apache-2.0 · self-hosted forever

Team

$199/mo

Up to 10 agents, Slack approvals, shared control plane, Evals + Learning Loop + Analytics.

Managed from inside the app

Enterprise

Custom

SSO-ready + RBAC, compliance report packs, enforcement nodes, priority support.

sales@suvra.io

Put a firewall between your agents and the real world.

pip install suvra

Or email sales@suvra.io