An engineer discovered that MCP server schemas consumed 42,000 tokens on a single server, causing a 37% token bill increase. After instrumenting a production agent, they found that schema overhead acc…
OpenAI is investigating Codex quota depletion after Pro plan users exhausted weekly limits in one to two days, revealing that AI coding agent adoption is outpacing capacity forecasts. Engineering lead…
A second-year computer science student built RepoLens, an AI tool that reads GitHub repositories, screens candidates based on their commit history, and operates as a coding agent inside VS Code. The p…
A second-year computer science student at the University of Debrecen built RepoLens, an AI system that scans GitHub repositories for developer onboarding, screens technical candidates by analyzing com…
Hail.so launches an open-source MCP server, CLI, and API that unifies email, SMS, and phone call capabilities under a single interface, packaging Twilio, AWS SES, LiveKit, ElevenLabs, Cartesia, and LL…
Mneme, a new open-source tool, governs AI-generated code by enforcing project decisions before the model writes a line. It reads existing architectural decisions and checks tasks against them, prevent…
HackerRank open-sourced its AI résumé screener, hiring-agent, revealing that the same résumé scores between 66 and 99 across runs due to LLM nondeterminism, not parsing errors. The volatility means a …
A developer building an LLM-based email classifier identified a critical design flaw: the model's self-reported confidence score is used as a gate for autonomous actions, but a confident impersonation…
Developer Maneshwar is building git-lrc, a free and source-available Micro AI code reviewer that runs on every commit. The project highlights the critical need for data privacy in AI systems, warning …
FAME Knowledge Agent Gateway, an open-source external memory and tool-safety gateway for local coding agents, has been released. It combines a graph knowledge net, project memory, tool-call governance…
Mistral launched Vibe, a unified AI agent that replaces Le Chat and combines work assistant and coding agent capabilities under a single license. The agent runs on Mistral's own models and infrastruct…
Mozilla's Zero Day Investigative Network (0DIN) warned that a malicious GitHub repository can compromise a developer's machine via indirect prompt injection targeting AI coding agents like Claude Code…
ZLUDA v6 has been released with improved PhysX support on AMD GPUs and better Windows compatibility, but the project has lost its commercial funding from an unnamed party, reverting to a weekend proje…
A developer with 25+ years of experience in Python, PHP, and LAMP stack is transitioning into AI engineering, focusing on local LLMs, offline AI setups, and practical model deployment. The individual …
Security researchers at Mozilla's 0DIN platform demonstrated that a compromised GitHub repository can infect a developer's machine when an AI coding tool like Claude Code executes its setup, with mali…
Vassiliy Lakhonin's Agenda Intelligence MD project shifts the focus of AI agents from generating answers to assessing whether evidence is ready for human trust. The open-source Python package provides…
SpecManager, a Claude Code plugin that replaces ad-hoc vibe coding with a gated spec-driven development lifecycle, has been released as an MIT-licensed open-source tool. The plugin enforces a PRD-to-w…
Microsoft CEO Satya Nadella calls for AI 2.0, emphasizing lower costs, customer choice, and enterprise control, signaling a shift from expensive frontier models to more accessible and flexible AI. Ope…
Uv, a single-binary Python package manager developed by Astral, has become the go-to tool in 2026, offering 10-100x speed improvements over pip. OpenAI acquired Astral in March 2026 to integrate uv in…
Developer Constantinos Pigiotis released an open-source Agent Skills plugin that teaches AI coding agents how to build hypermedia-driven UIs with htmx. The plugin covers htmx attributes, triggers, tar…