Authensor is an open-source safety layer that sits between your AI agent and the tools it uses. It checks every action against a policy before it executes, scans content for threats like prompt injection and PII leaks, and creates a tamper-evident audit trail. It works with any AI framework including LangChain, CrewAI, OpenAI Agents SDK, Claude, and MCP servers.

What is an AI agent safety layer?

An AI agent safety layer is software that intercepts actions an AI agent wants to take and decides whether those actions should be allowed, blocked, or sent to a human for approval. Think of it as a firewall for AI behavior. Without one, agents can delete files, leak credentials, make unauthorized API calls, or send data to the wrong place.

Do I need Authensor if I already use Claude, ChatGPT, or LangChain?

Yes. These tools give your agent capabilities like file access, shell commands, API calls, and web browsing. They don't have built-in policies for what's allowed. Authensor adds that missing safety layer. It works alongside any AI tool or platform you already use.

How is Authensor different from prompt engineering or system prompts?

System prompts are instructions that the AI can be tricked into ignoring through prompt injection. Authensor enforces rules in code, outside the AI model. A policy that blocks 'rm -rf' cannot be overridden by a clever prompt. It is deterministic enforcement, not probabilistic guidance.

Yes. Authensor is MIT licensed and fully open source. You can self-host everything, including the control plane with PostgreSQL, at no cost using Docker Compose. There is an optional hosted tier for teams that want managed infrastructure.

How do I get started with Authensor?

Run 'npx create-authensor' in your terminal. It generates a working project with Authensor wired in. You can choose from five templates: TypeScript agent, Python agent, Claude Code hooks, MCP Gateway, or Docker self-hosted control plane.

What AI frameworks does Authensor work with?

Authensor works with LangChain, LangGraph, CrewAI, OpenAI Agents SDK, Claude Code (via hooks), any MCP server (via the MCP Gateway), and any custom agent through the TypeScript or Python SDK. It is framework-agnostic.

Does Authensor detect prompt injection?

Yes. The Aegis content scanner includes 20+ prompt injection detection patterns covering instruction override, role manipulation, delimiter injection, encoding attacks (base64, hex, unicode), and few-shot poisoning. It runs with zero dependencies and sub-millisecond latency.

Does Authensor help with EU AI Act compliance?

Yes. Authensor maps to EU AI Act requirements for high-risk AI systems including Article 12 (record-keeping via hash-chained receipts), Article 14 (human oversight via approval workflows), Article 9 (risk management via the RedTeam harness), and Article 13 (transparency via decision logging). The EU AI Act high-risk deadline is August 2, 2026.

What is the OWASP Agentic Top 10 for 2026?

The OWASP Top 10 for Agentic Applications (2026) is a risk taxonomy developed by 100+ industry experts. It covers ASI01 Agent Goal Hijacking, ASI02 Tool Misuse, ASI03 Identity & Privilege Abuse, ASI04 Supply Chain Vulnerabilities, ASI05 Unexpected Code Execution, ASI06 Memory & Context Poisoning, ASI07 Insecure Inter-Agent Communication, ASI08 Cascading Failures, ASI09 Human-Agent Trust Exploitation, and ASI10 Rogue Agents. Authensor covers all 10 through its policy engine, Aegis scanner (15+ prompt injection rules, 22 memory poisoning rules), Sentinel behavioral monitor (EWMA/CUSUM anomaly detection), and approval workflows.

What is an MCP Gateway?

An MCP Gateway is a transparent proxy between an MCP client and any MCP server that evaluates every tool call against policies before forwarding. Authensor's MCP Gateway implements the MCP SEP authorization protocol with authorization/propose, authorization/decide, and authorization/receipt message types. It addresses the fact that 32% of MCP servers have critical vulnerabilities.

How does Authensor compare to Galileo Agent Control or NeMo Guardrails?

Authensor is the only open-source framework that provides all four pillars: tool permissions, approval workflows, cryptographic audit trails, and content safety scanning. Galileo Agent Control (Apache 2.0) provides evaluation but lacks approval workflows and receipts. NeMo Guardrails focuses on conversational safety but not tool authorization. AWS AgentCore uses Cedar policies but is AWS-locked. Authensor is cloud-agnostic, self-hostable, and MIT licensed with 924+ tests.

What AI agent frameworks does Authensor integrate with?

Authensor has official adapters for LangChain/LangGraph, OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, and CrewAI. It also integrates with Claude Code via hooks and any MCP server via the MCP Gateway. TypeScript and Python SDKs support any custom agent framework.

What is an AI agent firewall?

An AI agent firewall is a runtime enforcement layer that inspects every action an AI agent attempts and decides whether to allow, block, or escalate it. The analogy to network firewalls is deliberate: just as a network firewall controls what traffic enters and leaves a network, an agent firewall controls what actions enter and leave an agent.

How it works

The firewall sits between the agent and its tools. Every outbound action (tool call) passes through the firewall. Every inbound response (tool result) can also be inspected.

[User Input] → [Agent] → [Firewall] → [Tool]
                            ↑
                     Policy Engine
                     Content Scanner
                     Audit Logger

The firewall applies three types of inspection:

Policy matching: Does this tool call match an allow, block, or escalate rule?
Content scanning: Do the arguments contain prompt injection, PII, or credentials?
Behavioral analysis: Does this action fit the agent's normal behavior pattern?

Inbound vs outbound inspection

Outbound: The agent sends a tool call. The firewall checks it against the policy and scans the arguments before forwarding to the tool.

Inbound: The tool returns a response. The firewall scans the response for injected instructions or sensitive data before returning it to the agent.

Inbound scanning is particularly important for indirect prompt injection. A compromised tool or a document with embedded instructions can attack the agent through tool responses.

Agent firewalls vs network firewalls

| Property | Network Firewall | Agent Firewall | |----------|-----------------|----------------| | Inspects | Network packets | Tool calls and arguments | | Rules based on | IP, port, protocol | Tool name, argument patterns, context | | Actions | Allow, deny, log | Allow, block, escalate, log | | Stateful | Connection tracking | Session behavioral tracking |

Why "firewall" is the right metaphor

The firewall metaphor communicates something important: this is infrastructure, not optional middleware. A production network without a firewall is unacceptable. A production AI agent without an action firewall should be equally unacceptable.

The metaphor also sets the right expectations about what it does and does not do. A firewall does not make the agent smarter or more aligned. It does not fix bad instructions. It enforces boundaries. Everything inside the boundary operates freely; anything that tries to cross the boundary is inspected.

Deploying an agent firewall

You can deploy an agent firewall in two ways:

In-process: Use the SDK to wrap tool calls in your application code. The firewall runs in the same process as the agent with zero network latency.

As a gateway: Run the firewall as a proxy (MCP gateway) between the agent and its tools. This works with any MCP client without code changes.

Both approaches use the same policy engine, content scanner, and receipt system.