Open-source safety stack for AI agents.
Gate every tool call. Scan every input. Monitor every session. Audit everything.
npx @authensor/create-authensor my-agent
cd my-agent && npm install && npm run demoQuickstart · Packages · Architecture · Why Authensor · Red Teaming · Research · Work With Us
Authensor audits the infrastructure the AI safety field uses to measure itself, and files every finding upstream in public.
- 99 defect reports across 46 organizations in evaluation, guardrail, and training infrastructure
- 16 landed fixes, including 7 in UK AI Security Institute repos (
inspect_ai,inspect_evals,inspect_cyber,control-arena), plus Meridian Labs, Databricks, NVIDIA and Presidio - 76 of those defects are a single class: the evaluator trusts an artifact the evaluated system controls
The stack is hardened against what that audit found.
Red-team engagements, evaluator and scorer audits, and adversarial testing for teams shipping AI agents.
authensor.com · john@authensor.com
| Architecture | How the pieces fit: engine, control plane, scanners, receipts |
| Packages | All 18 packages, framework adapters, companion tools |
| Quickstart | Self-hosted setup, TypeScript and Python integration, framework adapters, CLI |
| Why Authensor | The problem, the five layers, why the stack is free |
| Features | Aegis content safety, session rules, budgets, Sentinel monitoring, shadow policies |
| Red teaming | The adversarial harness, what gets tested, how it runs |
| API reference | Control-plane endpoints |
| Deployment | Self-hosted vs hosted, production deployment |
| Development | Building and testing the monorepo |
| OWASP Agentic Top 10 | Coverage mapping, 10/10 |
| EU AI Act | Article-by-article alignment |
We welcome contributions! See CONTRIBUTING.md for guidelines.
Authensor is built on the belief that safety tooling should not have a paywall. We open-source every line of safety code because the more people who use these tools, the safer agents get for everyone.
MIT. Use it however you want.