Help Scout users can now manage their customer support workflows from the command line with Hscli, a new scriptable CLI tool designed for terminals, CI pipelines, and AI agents. The tool outputs JSON …
Block's open-source AI coding agent Goose has been transferred to the Linux Foundation, making its vendor-neutral architecture a structural reality rather than just a marketing claim. The tool operate…
Phylax, a new OS-level security tool, prevents AI coding agents like Claude Code and Cursor from reading, writing, or deleting private files by enforcing Windows kernel-level access controls. The tool…
With Angular v22, the MCP server and Angular Skills stack enables deterministic, verifiable agent-assisted development. The setup requires configuring MCP servers for Angular CLI and Chrome DevTools, …
A developer has released Memory Sidecar v3.1.0, an open-source tool that gives AI coding assistants persistent memory across sessions without modifying the agent's internal code. The sidecar runs as a…
A developer found that 87% of Claude Code's context window was wasted on conversation history, with tool I/O like file reads and bash output consuming 80% of tokens. To solve this, they built Throughl…
Jack Kao, developer of the MCP-native QA toolkit mk-qa-master, demonstrated a new edge AI testing capability by pointing a YOLOv8 object detection model at his laptop webcam through an RTSP stream. Th…
A developer open-sourced agmsg, a 500-line Bash and SQLite tool that enables direct messaging between CLI AI agents, and saw it grow from 5 to 320 GitHub stars in a week. The project, built to elimina…
Hugging Face redesigned its `hf` command-line interface to optimize it for AI coding agents, which now account for significant traffic on the Hub. The new CLI auto-detects when an agent is driving it …
Anthropic's Claude Code terminal tool now supports multi-agent workflows that let users deploy multiple AI personas with distinct roles to debate and reach consensus on strategy and analysis. The feat…
A developer describes a multi-model agentic coding setup where Claude Code delegates implementation tasks to OpenAI's Codex in an isolated git worktree, then runs an approval loop requiring human revi…
Anthropic's Claude Code now includes a `/insights` command that generates a 30-day HTML report analyzing developer usage patterns, token consumption, and session behavior. The built-in audit tool surf…
Developer Simon Willison wired OpenAI's Codex into Claude Code as a consulting subagent to get adversarial reviews from a different model family, aiming to catch correlated blind spots in reasoning. T…
Claude Code's /rewind command allows developers to roll back both conversation history and file changes to any earlier checkpoint in a session. The command reverts all file edits Claude made during th…
A 2026 comparison of AI coding assistants Claude Code, GitHub Copilot, and Cursor finds each tool suited to different workflows, with Copilot offering the widest model selection and Claude Code emphas…
A team at Redwood Research developed a proof-of-concept pipeline that transforms benign Claude Code transcripts into synthetic sabotage trajectories for automated red-teaming of AI monitors. The appro…
GitClear's analysis of 211 million lines of code reveals that refactoring is declining while duplicated code is increasing, a pattern the project attributes to agentic tech debt. A developer created a…
Visr, a new open-source tool, transcribes the entire trajectory of terminal sessions—including every command, output, retry, and fix—rather than just the final diff. The tool, installable via Homebrew…
Axiom, a seven-month-old startup, solved all 12 problems on the 2025 Putnam exam, scoring 12/12 within the time limit and outperforming both top undergraduates and other AI systems. The feat demonstra…
Persistia, an open-source tool, now provides Claude Code with persistent memory by scanning entire projects—code, architecture, docs, and configs—on first run and storing the information in small, foc…