Radar / AI security / Agent Gateway
Agent Gateway — policy enforcement point for AI agent tool calls
Open demo repo for a gateway that sits between AI agents and real-world APIs: SSO (OIDC) delegations, short-lived audience-scoped tokens, spend caps with auto-approval, single-use human approvals for high-risk actions, OPA/Rego policies, instant revocation, immutable audit trail.
Why it matters
Least-privilege control plane for agents that touch money, deployments, and data exports — 'trust me, the agent knows what it's doing' is not a control an auditor accepts.
What you could build with it
A fintech startup could place the gateway between its support agents and payment/refund APIs so routine refunds auto-approve under a spend cap while large payouts pause for a named human's single-use approval, with every allow/hold/deny decision in an immutable audit log.
Does it hold up?
Too early to judge — repo created hours ago with 0 stars; the demo stack is fully scripted and runnable via Docker Compose, but no independent deployments or reviews exist yet.
Built with Agent Gateway
- Show HN: Beta Agent Gateway — Anyone want to try it out?Hacker News · Launch discussion thread for the project.
Learn more
First spotted on github: source.
More AI security
iFixAi: independent auditing of AI agentsIndependent AI-agent auditor: 250+ inspections across 69 misalignment categories (red teaming + operational assurance)…security · JEV 0.76OpenAI, Anthropic and Google DeepMind jointly unveil cyber-focused safety models and safeguardsThe three rival labs disclosed weeks of behind-the-scenes coordination and jointly released a set of cyber-focused AI…security · JEV 0.73OpenAI textGrain watermarking for ChatGPT and Codex in the EUOpenAI will roll out its invisible textGrain watermarking system to ChatGPT/Codex users in the EU over the coming…security · JEV 0.65Cloudflare security-audit-skill: multi-phase security audits for coding agentsA coding-agent skill that runs multi-phase security audits with independently verified, machine-checkable findings.security · JEV 0.63LiveNerf: a pre-registered benchmark for post-release model driftOpen-source, pre-registered 30-day benchmark that detects whether Claude Opus 5.5 quietly gets worse after launch.security · JEV 0.61Sandlock 0.8.8: deferred commit for agent sandboxesThe process-based Linux AI sandbox (no container, no VM) ships deferred commit: every run returns a changeset of what…security · JEV 0.58
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.