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.

Authensor vs AWS Bedrock Guardrails

AWS Bedrock Guardrails and Authensor both add safety controls to AI systems, but they operate at different layers and serve different purposes. This comparison helps you understand when to use each.

Architecture

AWS Bedrock Guardrails is a managed service that filters content going to and from foundation models hosted on Bedrock. It runs as part of the Bedrock API call, intercepting prompts and responses. Configuration is done through the AWS console or SDK.

Authensor is an open-source safety stack that you self-host. It includes a policy engine, content scanner, behavioral monitor, approval workflows, and audit trail. It runs wherever your agent runs: on your servers, in containers, or at the edge.

Comparison

| Feature | Authensor | Bedrock Guardrails | |---------|-----------|-------------------| | Deployment | Self-hosted (open source) | AWS managed service | | Tool call enforcement | Yes (policy engine) | No | | Content filtering | Yes (Aegis) | Yes (topics, content, PII) | | Approval workflows | Yes | No | | Audit trail | Hash-chained receipts | CloudWatch logs | | Behavioral monitoring | Yes (Sentinel) | No | | MCP support | Yes (gateway) | No | | Model lock-in | Works with any model | Bedrock models only | | Pricing | Free (self-hosted) | Per-request pricing |

Content filtering

Bedrock Guardrails provides strong content filtering with categories like hate speech, violence, sexual content, and custom denied topics. It uses AWS's models for classification.

Aegis focuses on prompt injection detection, PII detection, and credential exposure. It uses pattern matching rather than model-based classification, which makes it faster and deterministic.

For content category filtering (hate, violence), Bedrock Guardrails has more coverage. For prompt injection defense, Aegis provides specialized detection.

Tool call control

Bedrock Guardrails does not control which tools an agent can call. It filters content, not actions. If your agent has access to 20 tools, Bedrock Guardrails cannot restrict which ones it uses.

Authensor's policy engine is specifically designed for tool call control. Every tool call is evaluated against YAML rules that match on tool names, arguments, and context.

Vendor independence

Bedrock Guardrails only works with models hosted on AWS Bedrock. If you use OpenAI, Anthropic's API directly, or self-hosted models, Bedrock Guardrails is not an option.

Authensor works with any model provider because it operates at the tool call layer, not the model API layer. It does not care which model generated the tool call.

When to use which

Use Bedrock Guardrails if you are already on Bedrock, need content category filtering, and your agents do not need tool-level control.

Use Authensor if you need tool call enforcement, approval workflows, compliance-grade audit trails, or work with multiple model providers.

Use both if you are on Bedrock: Bedrock Guardrails for content category filtering at the model layer, Authensor for tool call enforcement at the agent layer.