PeekAI, a new open-source tool for local-first observability and debugging of Python AI agents, launched on Hacker News. The tool stores traces in SQLite, requires no cloud accounts or API keys, and s…
A developer at a company handling thousands of LLM calls per hour cut their API bill by 30% using semantic caching. By embedding prompts and checking cosine similarity against cached responses, they a…
A team of 40 engineers using Claude Code coding agents saw a 340% increase in AI costs, reaching $20K/month in unexpected spend due to raw API keys without per-developer budgets or team caps. The team…
A platform lead at a 150-person company faces the multi-runtime agent problem, where different teams use different agent runtimes (Claude Managed Agents, Bedrock, Cursor, etc.) and need a unified way …
Buildkite ran a game day that fault-injected OpenAI with 429s and 500s to test whether Bifrost's fallback config would reroute requests for an LLM-backed build-failure summariser. After fixing a retry…
OpenCode, an open-source terminal-first coding agent, now supports self-hosted large language models via OpenAI-compatible APIs, enabling users to connect it to a vLLM server running NVIDIA's Nemotron…
Tirith, a new terminal security tool, intercepts commands and pastes to detect homograph attacks, pipe-to-shell patterns, ANSI injection, credential leaks, and 200+ other threats in under 1ms. It cove…
Alibaba's Qwen3-80B and Qwen3-4B models were successfully co-located on a single NVIDIA DGX Spark using vLLM containers behind a LiteLLM proxy, but the 80B model's inability to emit tool calls in auto…
A developer argues that the industry's focus on LLM gateway latency benchmarks is misguided for agent systems. Production agents require session persistence, cost attribution, model routing, fallback …
The npm account 'ai' publishes seven packages that collectively receive 964 million weekly downloads, yet none have npm provenance attestations. This single-publisher, no-provenance pattern mirrors re…
PyAgent, a new open-source framework, provides a standardized stack for building multi-agent LLM systems, including YAML-based blueprints, 18 named coordination patterns, and built-in observability. I…
Maslul, a new open-source Python library, provides smart LLM routing and provider normalization across Anthropic, Gemini, Grok, and OpenAI, allowing developers to route each request to the right model…
A developer argues that coding agents like Claude Code and Codex require two distinct infrastructure layers: a control plane for agent lifecycle, permissions, and scheduling, and a fast data plane for…
CISA confirmed active exploitation of CVE-2026-42271 in LiteLLM, an open-source AI gateway, and set a June 22 federal remediation deadline. Obsidian Security disclosed a three-vulnerability chain allo…
LiteLLM, a unified proxy for 100+ LLM providers, has been deployed on AWS EKS with GitOps via ArgoCD to handle 500-1000 requests per second. The production-grade system addresses multi-provider chaos,…
Phlox, an open-source self-hosted agentic web chat application, has been released on GitHub. It supports any model provider including AWS Bedrock and OpenAI-compatible endpoints, and features agentic …
A critical vulnerability chain in LiteLLM, a widely deployed open-source AI gateway, allows attackers starting from a default low-privilege account to achieve full server takeover and code execution. …
Coding agent sandboxes address host compromise but not credential authorization, leaving agents with high-scope tokens that can push to protected branches, deploy infrastructure, or read secrets. The …
A developer built a unified AI gateway using LiteLLM and Ollama, enabling a single OpenAI-compatible API endpoint for both local and cloud LLMs. The setup provides load balancing, cost tracking, rate …
A developer built Arcwise, an open-source AI-powered system design coach that provides structured feedback on design exercises. The tool uses LiteLLM to support multiple AI models including Claude, GP…