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.

EU AI Act requirements for AI agents

The EU AI Act is the first major regulation specifically targeting AI systems. For AI agents that take actions autonomously, the Act imposes requirements around risk management, human oversight, record keeping, and cybersecurity. This guide breaks down what matters for teams building AI agents.

Risk classification

The Act classifies AI systems by risk level:

Unacceptable risk: Banned (social scoring, real-time biometric surveillance)
High risk: Subject to all compliance requirements
Limited risk: Transparency obligations only
Minimal risk: No obligations

AI agents that make decisions affecting people (hiring, credit, medical, legal) are likely classified as high-risk. Agents that operate in critical infrastructure, education, or law enforcement are explicitly listed as high-risk.

Key requirements for high-risk AI agents

Risk management (Article 9): Implement a risk management system that identifies, evaluates, and mitigates risks throughout the AI system's lifecycle. For agents, this means assessing what can go wrong when the agent takes autonomous actions.

Data governance (Article 10): Training and validation data must meet quality criteria. For agents using RAG, this extends to the data sources the agent retrieves from.

Technical documentation (Article 11): Maintain detailed documentation of the system's design, intended purpose, capabilities, and limitations.

Record keeping (Article 12): Automatically log all significant events during the agent's operation. Logs must be retained for the system's lifetime or at least six months.

Human oversight (Article 14): Design the system so humans can effectively oversee it, understand its outputs, and intervene when necessary.

Cybersecurity (Article 15): Implement appropriate security measures to protect against unauthorized access and manipulation.

How Authensor maps to these requirements

| EU AI Act Requirement | Authensor Feature | |----------------------|-------------------| | Risk management | Policy engine, content scanning | | Record keeping | Hash-chained receipt audit trail | | Human oversight | Approval workflows, escalation rules | | Cybersecurity | Prompt injection defense, behavioral monitoring | | Transparency | Receipt-based action logging |

Timeline

The Act entered into force in August 2024. Requirements phase in over time:

August 2025: Bans on unacceptable risk systems
August 2026: Obligations for high-risk systems apply
August 2027: Full enforcement

If you are building AI agents for the EU market, August 2026 is the compliance deadline for high-risk systems.

Getting started with compliance

Start by classifying your AI agent's risk level. If it falls into high-risk, implement the required controls. Authensor provides the technical layer for several of these requirements, but compliance also involves organizational processes, documentation, and governance that go beyond tooling.