Orchestrating AI Code Review at scale
…promptText }], agent: input.agent, model: { providerID, modelID }, }, }); Each sub-reviewer runs in its own OpenCode session with its own agent prompt. The coordinator doesn't see or control what tools the sub…
Search
All sources
xda-developers.com
35
anthropic.com
18
theregister.com
9
wired.com
6
developer.nvidia.com
5
pcworld.com
5
9to5mac.com
4
theverge.com
4
blog.cloudflare.com
3
engadget.com
2
tweakers.net
2
bleepingcomputer.com
2
Claude in your browser is a security risk, and this year proved it
…a browser agent fits the description by default. The risks aren't theoretical either, which is the part that bothers me most… Related I added this open-source tool to my local…
I switched from Claude Code to Codex for a week, and the trade-offs surprised me
…Codex's key deployment advantage is its cloud-based parallel agent execution model. Unlike tools that work inline in your editor one task at a time, Codex can handle multiple sandboxed workstreams…
Claude in Chrome is the only AI browser extension actually worth keeping
…You can use it alongside Claude Code and Cowork, allowing these agentic tools to actually plug into your browser without breaking your flow! For instance, I was vibe-coding a Chrome extension…
Discussions and forums
Arch-Decision – A multi-agent architecture tool for Claude Code
Arch-Decision – A multi-agent architecture tool for Claude Code
3
Show HN: Agentcad – Claude Code's favorite CAD tool
Think of it as CAD software for your agent. Allows your agent to "see" what it's designing and iterate on it before it hands it back to you.
1
Show HN: Lazarus, a coding agent for long-horizon tasks
I have been interested in long-horizon coding tasks for a while, especially with benchmarks like FrontierSWE, where even the best coding agents like Codex and Claude Code struggle to complete tasks.These agents come with…
1
Show HN: I threw away my analytics dashboard and replaced it with 42 MCP tools
Back in October, I built a web analytics tool. It had two distinguishing features: it was cheap, and it had a weekly AI email summary so you wouldn't have to check your dashboards. Turned out that cheap made no differenc…
3
4
Show HN: Jsonl-tools – secure paste bin for agent run traces
Hey, I've built a small tool and OSS repo allowing users to view/transform/share JSONL traces.There's also a CLI you can use to upload traces from sandboxes and/or share them with Claude/Codex for analysis.Zero Knowledge…
3
Claude Code routines promise mildly clever cron jobs
…An AI agent would be an ongoing process that maintains state and involves AI model interactions with various tools and data sources. So a routine could be thought of as a dynamic…
Google Antigravity 2.0 beats Claude Code and Codex at their own game
…a dedicated Agent Manager that looks and feels a lot like Claude Code and Codex and an Antigravity IDE tool which feels like VS Code with the Gemini add-on. The best…
I tested Gemini Notebooks and Claude Projects side by side, and one didn't make the cut
…This is what separates agentic tools from simple chat-based assistants. Not quite. When a tool is described as 'agentic,' it means it can autonomously plan and execute sequences of actions end…
Rubber Duck in GitHub Copilot CLI now supports more models - GitHub Changelog
…permission controls client apps copilot enterprise management tools Jun.17 Release Auto mode in Copilot Chat available for all users copilot Jun.17 Release Agent finder for GitHub Copilot now available copilot…
Anthropic debuts Code Review for teams, enterprises
Devops Anthropic debuts pricey and sluggish automated Code Review tool First vibe coding, now vibe reviewing ... but the buzz is good as it finds worthy issues Anthropic has introduced a more extensive…
Opera now has an MCP server that lets Claude and ChatGPT control your browser
…third-party AI tools like Claude, ChatGPT, n8n, Lovable and even OpenClaw to connect directly to its Neon browser. Though it's currently only available for its agentic browser Neon, the company…