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.

Agent Onboarding Safety Checklist

Adding a new AI agent to your infrastructure is similar to onboarding a new employee with system access. The agent needs credentials, permissions, policies, and monitoring. Skipping these steps creates security debt that compounds over time.

Identity and Access

[ ] The agent has a unique identifier in your system
[ ] API keys are generated specifically for this agent (not shared with other agents)
[ ] Keys are scoped to the minimum required role (not admin)
[ ] Credentials are stored in a secrets manager
[ ] A credential rotation schedule is established

Policy Definition

[ ] A YAML policy is written specifically for this agent's use case
[ ] The policy uses deny-by-default rules
[ ] Every tool the agent needs is explicitly permitted with parameter constraints
[ ] High-risk actions are gated behind approval workflows
[ ] The policy has been reviewed by someone other than the author

Content Safety

[ ] Aegis scanning is enabled for input and output
[ ] Detection rules are appropriate for the agent's domain
[ ] Scanning thresholds are tuned (not just defaults)
[ ] PII detection is enabled if the agent handles personal data

Monitoring

[ ] Sentinel behavioral monitoring is enabled
[ ] Baseline behavior is established during a shadow-mode period
[ ] Alert rules are configured for anomalous behavior
[ ] The agent is added to the monitoring dashboard

Testing

[ ] The policy is tested with legitimate use case inputs
[ ] The policy is tested with adversarial inputs
[ ] Approval workflows are tested end to end
[ ] The kill switch is tested and verified
[ ] Shadow mode evaluation matches expected allow/deny patterns

Documentation

[ ] The agent's purpose and scope are documented
[ ] The agent's tool access is documented
[ ] The agent's owner and responsible team are documented
[ ] Incident response contacts are identified

Shadow Mode Period

[ ] The agent runs in shadow mode for at least one week
[ ] Shadow mode results are reviewed and anomalies are investigated
[ ] Policy adjustments are made based on shadow mode findings
[ ] A go-live decision is made and documented

Do not skip the shadow mode period. Running the agent in evaluate-only mode before enabling execution catches policy gaps, unexpected tool usage patterns, and configuration errors without risk.