Microsoft released VS Code 1.135 on August 26, introducing the open, MIT-licensed Agent Host Protocol (AHP) that turns the editor into a universal agent runtime, external session continuity for pickin…
Anthropic's Claude Code Auto Mode, marketed as a protective layer against prompt injection attacks, can be bypassed and even blocks the agent's own cleanup commands, according to research by Johann Re…
Runnrr, a new macOS app, converts action items from Granola meeting notes into to-do cards that can be executed by Claude Code or Codex, with all data stored locally as markdown and SQLite files. The …
Anthropic announced that starting September 14, standard weekly limits in Claude Code will be permanently raised by 25% for Pro, Max, Team, and seat-based Enterprise plans, replacing the current tempo…
A developer's blog post identifies seven recurring design patterns in agentic AI, including ReAct, planner-executor, reflection, tool use, and orchestrator-worker, arguing that these patterns underlie…
Cursor, the AI-powered IDE, is losing its edge for heavy coding workflows due to degraded context handling, causing hallucinations and disconnected responses, according to a developer's account. The i…
Envault, a new open-source tool from developer MildyNora, provides a local, encrypted vault that lets coding agents like Claude Code, Codex, and opencode use API keys and secrets without ever seeing t…
Viktorinkov released SHOOK, a plugin that enforces ASD-STE100 Simplified Technical English across every Claude Code reply, with hooks that load rules at session start, remind on each prompt, and lint-…
A developer detailed five custom skills for Claude Code that reportedly saved 10 hours a week, including test-driven development workflows, schema-first API design, adversarial self-review, hybrid RAG…
Anthropic is increasing standard weekly usage limits for Claude by 25% starting September 14, giving paying subscribers more capacity before hitting caps. The company has not disclosed exact token cou…
AI pins failed because they ignored basic latency and hardware constraints, according to a technical analysis. The devices suffered from 3-5 second response delays, inadequate thermal management, and …
Towards Data Science published a guide comparing Anthropic's Claude Code and OpenAI's Codex coding agents, outlining the strengths and ideal use cases for each tool. The article advises developers on …
A developer has open-sourced DeployProof, a Python pre-push verification tool that uses diff-scoped AST mutation testing to catch hollow test suites, hallucinated dependencies, and security traps in A…
A developer built a local, dependency-free system for searching AI coding-assistant chat transcripts without a vector database, using compact per-chat extracts, IDF keyword ranking with first-message …
A developer at Skyblue Soft, Cor, argues that recent reports of AI agents engaging in 'turf wars' and creating self-replicating malware are not evidence of emergent malice but rather classic distribut…
Model Peer v0.8.1, an open-source tool from makedirectory, enables cross-model peer review for coding agents by letting Claude Code, OpenAI Codex CLI, and Google Gemini CLI consult each other as read-…
OpenChamber, a free, MIT-licensed graphical front-end for the OpenCode AI agent, reached the Hacker News front page with 103 points and 54 comments, offering a multi-run feature that runs up to five m…
A developer measured the context cost of AI coding agents reading an entire Obsidian vault and found that a generated index map reduced context usage by roughly 150x. The approach uses a script to cre…
AgentBridge, an open-source local developer tool by Rayson Meng, enables bidirectional collaboration between Claude Code and Codex in the same working session, allowing cross-review, task splits, and …
Toolchestrator, a new tool showcased on Hacker News, enables teams to run locally built AI-generated apps in any browser without migration or rewriting, keeping the software on the original machine. I…