NeuronLens
Browse the documentation
Start

NeuronLens documentation

How NeuronLens checks AI answers, agents and models from the inside, and how to connect it.

Start in five minutes

Products

Guides

Reference


NeuronLens checks AI from the model's internals: the activations an answer produces and the weights a model is made of. A text-only check sees what a model says. NeuronLens reads what the model represents while it says it.

ProductYou sendYou get back
Agent LensYour app's answers, or each step your agent is about to takeA risk per failure mode (deception, goal drift, data leak, reasoning error, failed check, omission, …) and a verdict: allow, escalate or deny
Integrity LensA Hugging Face model, public or privateWhether the model's safety training has been stripped (no issue, review, tampered), whether it is still the version you approved, and a signed report

Make your first call

  1. Sign in at neuronlens.com and create a key under Profile → API keys.
  2. Score an answer:
curl https://api.neuronlens.com/v1/score \
  -H "Authorization: Bearer $NEURONLENS_API_KEY" -H "Content-Type: application/json" \
  -d '{"prompt": "What is our refund window?",
       "response": "Refunds are available within 14 days of purchase with a receipt.",
       "agent": "support-bot"}'
  1. Read verdict and probes, then open Monitor in the console to see the answer. The Agent Lens quickstart takes five minutes.

Connect your agent

Where your agent runsStart here
Your own codeCheck agent steps: one HTTP call before each tool
Claude CodeClaude Code hook
MCP toolsMCP gateway
LiteLLM proxyLiteLLM guardrail
LangGraph, LangChain, Google ADKFramework middleware
Already traced with OpenTelemetryOpenTelemetry

How it works

  • Agent Lens reads your conversation through an open-weight model (gpt-oss-20b) and runs a probe per failure mode on its internal activations. A model that writes a misleading answer, or an agent about to act against a failed check, represents it differently inside, even when the text reads well.
  • Integrity Lens compares a model's weights and late-layer refusal signal with the clean base it was built from. Abliteration and similar edits leave a measurable gap. Your organization approves a version of each model, and every later scan is checked against it.

Where it runs

  • API: https://api.neuronlens.com, with your key as Authorization: Bearer or X-API-Key. See Authentication.
  • Console: app.neuronlens.com: Agent Lens's Connect, Monitor, Eval and Settings (Pro), and Integrity Lens scans, approvals and reports for your organization.

Scans in the web app count toward the same daily allowance as the API. See Limits and usage.