Nearly 1 in 10 publicly accessible LiteLLM instances accept a default master key or require no authentication, exposing cloud AI infrastructure to root-level remote code execution and IAM theft, accor…
Sentry's AI security research team, led by Armend Gashi and Redon Gashi, presented at DEF CON 34 a new tool called infreerence that demonstrates how adversaries exploit exposed self-hosted inference s…
OpenHands 1.0, an open-source autonomous coding agent from All Hands AI, shipped this week with a production-grade Docker security sandbox, a built-in LLM-based security analyzer that rates actions LO…
A developer's review of the Model Context Protocol's identity roadmap finds that only one of four proposed specifications has shipped, and it authenticates human employees rather than autonomous agent…
A developer known as entitybtw has released Aurora, a self-hosted AI gateway fork of aurorallm/aurora that claims to be 55x faster than LiteLLM and supports 14 provider types with OpenAI and Anthropic…
Google Threat Intelligence Group (GTIG) reported that in Q2 2026, threat actors compromised a cloud resource and executed an agent-enabled mass credential harvesting campaign in under six hours, highl…
Novus, a self-improving AI agent framework developed by Rex Huang, runs on Android phones and other devices with Node.js, featuring approximately 15,000 lines of TypeScript, 16 built-in tools, and 109…
AI agent retry logic can multiply API costs three to ten times over because retries resend full context, and stacked retries, fallback chains, and self-correction passes compound multiplicatively, acc…
A developer built TraceShrink, an OpenTelemetry Collector processor that replaces random tail sampling with cost-aware rules to cut LLM observability costs. The processor keeps traces based on cost th…
A technical comparison of AI traffic gateways finds that Go-based Bifrost offers microsecond-level overhead for mission-critical workloads, while LiteLLM provides a simpler unified API across provider…
A 2026 comparison of open-source LLM gateways highlights Bifrost, LiteLLM, Kong AI Gateway, Apache APISIX, and Envoy AI Gateway for enterprise AI at scale. The analysis emphasizes choosing a gateway b…
A review of Blake McCarn's Paperless Knowledge Graph finds that while it enables chat with scanned documents and includes evidence-backed retrieval with strict refusal modes, the project lacks public …
A self-hosted LiteLLM gateway for OpenAI's Codex on AWS ECS with Bedrock provides per-team virtual keys, spend caps, and CloudWatch logging, with a reference CDK stack in the guidance-codex repo under…
Amazon Web Services (AWS) published a guide for deploying OpenAI ChatGPT Codex with the open-source LiteLLM gateway on Amazon Elastic Container Service (ECS) and Amazon Bedrock, enabling centralized e…
A technical guide details the production deployment of on-premises large language model inference using vLLM, covering an 8-GPU node running GLM-5.2/5.3 (NVFP4 MoE) and a single L40S running gemma-4-2…
Developer Nelson Lin released Open LLM Gateway, a self-hosted LLM control plane combining a proxy, analytics, and an admin UI, under the Apache 2.0 license with no seat cap. The project, available on …
CISA has added seven vulnerabilities to its Known Exploited Vulnerabilities catalog, affecting AI infrastructure and web frameworks including LiteLLM, Starlette, Kestra, JFrog Artifactory, Sangoma Swi…
On September 2, 2026, CISA added seven vulnerabilities to its Known Exploited Vulnerabilities catalog, with three targeting AI infrastructure: CVE-2026-59822 in LiteLLM (CVSS 8.8, affects versions pri…
A developer demonstrates how to self-host a bring-your-own-key (BYOK) LLM gateway using the open-source LiteLLM proxy, which routes OpenAI-compatible requests to configured providers with minimal over…
A developer compared managed multi-provider routers, self-hosted gateways, and thin in-app adapters for property-management moderation, concluding that raw token rates alone cannot determine the cheap…