A developer built Maestro AI, a harness-agnostic model router that routes LLM calls to appropriate models based on task complexity, preventing expensive models like Claude Sonnet from being used for s…
LiteLLM's pricing table, used by most AI cost tools, has only a single automated test—`jq empty`—which verifies JSON parsing but not value accuracy. An audit found records citing their own refutation,…
TradingSpy, an open-source, local-first AI trading assistant, has been released. The tool provides market heatmaps, news catalysts, strategy generation, and backtesting in a single Docker application,…
NaN Builders has published a comprehensive configuration guide for its LLM API, detailing setup instructions for clients, IDEs, agents, and SDKs. The guide covers available models including deepseek-v…
Accretive editing is a failure mode of current AI tools where they add parentheticals or addendums instead of correcting text, as seen when Claude updated a project description to include both old and…
Attackers compromised an AWS EC2 instance acting as a LiteLLM proxy for Amazon Bedrock, deploying XMRig cryptomining malware and attempting to abuse cloud identities and AI services. Cybersecurity fir…
A developer compared AI gateway pricing models in 2026, finding that none of the major gateways—including LLM Gateway, OpenRouter, Vercel AI Gateway, Cloudflare AI Gateway, Eden AI, Portkey, and LiteL…
A developer evaluated eight AI gateways based on provider coverage, pricing transparency, self-hosting, observability, and ease of setup. The top pick is LLM Gateway, an open-source solution that rout…
A developer successfully runs the Qwen3.6-27B-FP8 model locally on an Nvidia DGX Spark, achieving reasoning, tool use, and multi-token prediction at 256K context, and uses it to ship real code for an …
Security researchers at MBG Security built a global network of honeypots with exposed AI inference and agent endpoints, observing attackers actively scanning for and exploiting vulnerabilities like CV…
Glad Labs fixed a GPU pinning issue where LiteLLM 1.89.2's global api_base override prevented per-model routing, causing vision tasks to cold-load onto the wrong GPU. The team also hardened content gu…
Autosynth, a new open-source tool for generating synthetic datasets using an LLM loop that proposes, audits, solves, and judges its own work, has been released. Inspired by Meta FAIR's Autodata paper,…
A teenage hacking group called TeamPCP poisoned two releases of LiteLLM, an open-source AI gateway tool downloaded 95 million times, stealing over 500,000 credentials and 300 GB of data from more than…
Six AI agent SDKs—LangGraph, CrewAI, Google ADK, and others—are compared for enterprise Kubernetes deployment, with most being model-agnostic and containerizable for on-premise use, though Anthropic's…
Researchers at Zenity documented three campaigns between March and May 2026 where attackers hijacked exposed LLM endpoints from Ollama and LiteLLM instances to run offensive AI operations. The attacks…
On March 24, 2026, attackers compromised LiteLLM's CI/CD pipeline and uploaded malicious PyPI packages that stole credentials from environments with three million daily downloads. The incident highlig…
Zenity Labs revealed that attackers are weaponizing AI infrastructure, targeting exposed model gateways and unmanaged LLM endpoints. The firm's sensors detected thousands of real-world attacks, includ…
A developer warns that HTTP 200 responses from LLM gateways do not guarantee correct output, as gateways like LiteLLM, Portkey, and OpenRouter only check transport-level success. The developer propose…
Smolagents, a Python library from Hugging Face for building AI agents, prioritizes code-based actions over JSON tool calls, enabling loops, conditionals, and tool composition. However, this design shi…
A developer used agentic AI to decompile a Chinese label printer's Android app and create a Go script that prints PDFs via Bluetooth on Linux, after struggling with poor print quality under CUPS. The …