Radar / AI security / AI Agent Gateway (Tuskira)
AI Agent Gateway (Tuskira): open-source security gateway for MCP and LLM traffic
One Go binary that sits between AI agents and everything they call — MCP tool servers and LLM providers — authenticating requests, injecting per-request credentials from an encrypted store, scoping tools per agent profile, and logging every call behind an admin console.
Why it matters
Credentials never reach the agent: the gateway injects them at call time from an encrypted store, so a compromised agent or a leaked config file cannot expose API keys — plus built-in SSRF egress guards and per-profile skill serving over MCP.
What you could build with it
A startup building multi-tenant AI features could put this gateway in front of all agent traffic: each tenant gets a scoped agent profile with per-request credential injection, so customer API keys stay in one encrypted store while per-tenant usage and cost are logged and audited from a single console.
Does it hold up?
Too early to judge: pre-1.0 alpha with 74 stars, 12 commits, and no verified third-party deployments yet; the docs themselves warn that APIs and config flags may still change between minor versions.
Learn more
First spotted on github: source.
More AI security
OpenAI, 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 0.58Microsoft Execution Containers (MXC) goes GA on Windows 11At its Oct 7 Windows AI event with NVIDIA, Microsoft announced general availability of Microsoft Execution Containers…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.