Jean2, a new AI coding agent, ships with no default system prompt or tools, giving developers full control over agent behavior. Unlike Claude Code, Cursor, and Copilot, which have hidden baked-in prom…
A bug in Claude Code on Windows 11 causes the first click to focus the window to inadvertently submit pending permission prompts, potentially approving or rejecting actions without user intent. The is…
A developer on Windows 11 reported a ~2× frame rate regression in Claude Code between versions 2.1.159 and 2.1.207, with median frame time dropping from 62 ms to 99–109 ms. The issue, documented in Gi…
Anthropic launched the Claude Apps Gateway, a self-hosted control plane for Claude Code on AWS that replaces scattered API credentials with corporate SSO and real-time spend controls. The gateway sits…
Anthropic and OpenAI are accelerating faster than competitors because they extensively use their own AI products internally, creating a compounding feedback loop that improves both models and business…
A developer created a CLI tool called Coder that delegates coding tasks to Codex and Claude engines, enabling Claude Code to spin up Codex agents for individual tasks while keeping context clean and s…
Developer Maneshwar built git-lrc, a micro AI code reviewer, and discovered Tokscale, a Rust-based CLI tool by Junhoye that tracks token usage and costs across multiple AI coding agents like Claude Co…
Alibaba Group launched OpenSandbox, an open-source universal sandbox infrastructure for AI applications, providing isolated environments for running code, browsers, and developer tools. The platform s…
A new website, Curated Collections, offers scenario-driven tool stacks that assemble 5-10 deep-dive tools into complete solutions for specific user scenarios, including AI agent ethics, multi-agent wo…
Local Agent Toolkit, an open-source tool, allows developers to delegate small coding tasks to local Ollama models, reserving cloud tokens for harder decisions. The toolkit filters repository context, …
A developer released a tool called paxel-boosted that intercepts Y Combinator's Paxel coding evaluation pipeline, artificially inflating scores across five axes before uploading results to YC servers.…
Cordless v0.6 introduces a CLI-first redesign that opens a full-screen terminal dashboard with a live pairing QR code upon running `cordless`, eliminating the need for a separate pairing command. The …
OpenClaw shipped a fleet of Claude Code sessions, enabling parallel orchestration of multiple agent instances for large-scale code review and refactoring. The update also includes pinned SSH tunnel ru…
A developer describes how installing five Claude Code plugins transformed the AI assistant from a forgetful tool into a system that functions like an engineering team, eliminating the need to re-expla…
Codex users are reporting three critical bugs in the new GPT-5.6 build, including a tool-call namespace collision that causes valid tool calls to be rejected, a missing workspace tools issue on the Co…
Agentation, a new visual UI annotation tool, enables developers to click on web elements and generate structured context for AI coding agents like Claude Code and Codex, streamlining feedback and debu…
Google released the stitch-skills library, introducing the baton pattern to enable coding agents to autonomously build multi-page websites by persisting state across iterations. The library packages f…
Databricks CTO Matei Zaharia's team built an internal benchmark on their own polyglot codebase to evaluate coding agents, finding that multiple models are now competitive at the top tier, including op…
Developer Tadashi Shigeoka now defaults to lighter reasoning and speed settings on coding agents, running Anthropic's Fable 5 at Low reasoning in Claude Code and OpenAI's Codex 5.6 Sol at Light reason…
A developer built claude-code-notify, a Telegram notification tool for Claude Code sessions, after experiencing productivity losses from long TDD-driven tasks and parallel project management. The tool…