A security researcher warns users to stop using OpenCode, the most popular open-source AI coding agent with 161k GitHub stars, citing severe security flaws and poor design. The tool, described as fund…
Anthropic's Model Context Protocol (MCP), adopted by OpenAI, Google, and Microsoft through 2025 and donated to a Linux Foundation body, has become the standard for connecting AI agents to external too…
Anthropic donated its Model Context Protocol (MCP) to the Linux Foundation's new Agentic AI Foundation, while Google handed its Agent2Agent (A2A) protocol to the Linux Foundation with AWS, Cisco, Micr…
Anthropic, Google, and OpenAI are donating key AI protocols to open-source foundations, not out of generosity but to commoditize one layer of the AI stack and compete on higher-value services, followi…
Bilibili showcased its open-source 'Catgirl Plan' AI digital-life ecosystem at WAIC 2026 in Shanghai on July 18, featuring Project N.E.K.O., a proactive multimodal AI companion that observes computer …
Microsoft forked its Windows Terminal into a separate Intelligent Terminal to keep AI experiments out of the stable command-line experience, shipping bug-fix-only releases for the mainline while the f…
OpenAI reverted the Codex context window for GPT-5.6 Sol from 372k to 272k tokens after discovering the larger window silently double-billed long sessions, causing ChatGPT subscribers' plans to drain …
Construct, a vendor-neutral AI workspace, offers cross-application execution for jobs spanning multiple SaaS tools, while Microsoft Copilot and Google Workspace AI are strongest inside their native su…
A cost-based semantic routing demo combining vLLM Semantic Router (vSR) with agentgateway reduced LLM spend by 35.4% on a 50-prompt Go and Rust coding dataset, according to a developer evaluation publ…
Treena, founded by Camden Hulse and Kollaikal Rupesh, is building a mobile IDE that lets developers start coding agents from scratch on their GitHub repos, with a full workspace including terminal, fi…
AI infrastructure is shifting from token-based measurement to verifiable work units that bundle acceptance conditions, execution evidence, total cost, and accountability boundaries, as signaled by rec…
Anthropic added routines to Claude Code, a feature in research preview that bundles a prompt, GitHub repositories, and connectors into saved configurations running on Anthropic's cloud infrastructure,…
LFortran version 0.61.0 failed to compile the Xfoil aerodynamics code due to a bug in handling the INCLUDE statement in fixed-form Fortran, which has now been fixed in a pull request by LFortran devel…
GitHub has evolved beyond software development into a platform used across medicine, chemistry, religious studies, physics, and biology. Researchers share code for drug discovery, molecular modeling, …
A developer found that a single line of math—10 ** 10 ** 8—can freeze an AI agent built with Hugging Face's smolagents library indefinitely, because CPython's arbitrary-precision exponentiation holds …
A developer introduced Robust-GAP, a hierarchical Retrieval-Augmented Generation (RAG) framework designed to eliminate hallucinations and knowledge drift in multi-document log summarization. The frame…
A technical guide demonstrates the limitations of base language models like GPT-2 for domain-specific tasks and introduces fine-tuning as a solution, showing that GPT-2 produces inconsistent outputs w…
Anthropic's Claude Cowork platform has five core components—skills, connectors, plugins, projects, and artifacts—but most users only leverage one, according to a company guide. Skills are how-to files…
A new online developer profile service automatically pulls contributions from GitHub, Stack Overflow, and other sources, and includes an embedded AI hypeman that lets recruiters ask questions and get …
A developer built tearsheet, an MIT-licensed MCP server that provides local, keyless web scraping for Claude Code. The tool avoids API keys, quotas, and telemetry by running entirely on the user's mac…