Onepilot and Secure ShellFish offer contrasting approaches to AI agent management, with Onepilot focusing on deploying and supervising a fleet of AI coding agents on user-owned servers, while Secure S…
Onepilot and Blink Shell are iOS apps for managing servers, but they serve different purposes. Blink Shell is an open-source, Mosh-native terminal for manual SSH work, while Onepilot is an operations …
Researchers demonstrated indirect prompt injection attacks against Anthropic's Claude Code, achieving remote code execution in 10 out of 10 experiments using a model downgrade attack and inspection fa…
A developer released mlx-serve, a native Zig server for MLX-format language models on Apple Silicon, enabling local, free, and private use of AI coding assistants like Claude Code. The server exposes …
Brick, a Mixture-of-Models routing gateway, reads each prompt's capability and complexity to route queries to the best backend LLM, matching top model quality at lower cost. It offers a drop-in OpenAI…
Developer Joe Swell built flar, a tool to sandbox AI agents using bubblewrap, and discovered that each agent CLI implements history and resume differently, requiring custom backends. He let each agent…
A developer argues that the real cost of switching AI coding models is not the model itself but the loss of accumulated context, rules, and decisions. They identify the lack of a persistent workspace …
Termi Protocol launches a 3D visualization platform for AI coding agents, allowing developers to watch every file read, command, and change in real time. The tool supports agents like Claude Code and …
Anthropic's Claude Code now writes 90% of the company's own codebase, boosting engineer output by 200% and shifting bottlenecks to code review. The tool's Code Review product increased substantive pul…
Alibaba banned employees from using Anthropic's Claude Code after security researchers discovered hidden steganographic code that tracked Chinese users by timezone and proxy settings. The ban follows …
Anthropic released the Claude apps gateway on June 29, 2026, a self-hosted control plane that lets enterprises run Claude Code through Amazon Bedrock, Google Cloud, or Microsoft Foundry with corporate…
Simon Willison reported that instructing Claude Code to delegate coding tasks to lower-power subagents using its own judgment significantly improved efficiency and reduced token usage. The approach, i…
Enterprise-grade MCP access control is now available, with EMA (Enterprise MCP Authentication) enabling secure token exchange between clients and servers. The system addresses gaps where clients or se…
Anthropic is blocking Chinese companies like ByteDance and Ant Financial from accessing Claude Code, but they circumvent restrictions via VPNs and overseas subsidiaries. Alibaba banned internal use of…
Software teams are adopting AI coding agents across three maturity stages—autocomplete, prompting agents, and loop engineering—often simultaneously, according to interviews with hundreds of teams. The…
Andrej Karpathy's 'autoresearch' technique lets AI agents optimize any metric overnight by running hundreds of experiments autonomously. One engineer applied the method to file compression, beating of…
Developer Kerlenton released mcpsnoop, an open-source transparent proxy and terminal UI that captures live MCP (Model Context Protocol) traffic between AI clients and servers, enabling debugging of re…
A new open-source proxy tool called pxpipe reduces Claude Code input token costs by up to 60% by converting dense text content such as system prompts, tool documentation, and history into compact PNG …
Meta CEO Mark Zuckerberg admitted that the company's AI agent development has stalled despite massive investment, while its mandatory employee keystroke and mouse-tracking surveillance system worked f…
Towards AI open-sourced its production AI tutor app, used by students to ask questions about AI engineering, RAG, and agents. The release includes the full system for local running and customization, …