Codex is Open Sourcing AI models
…This is a great step toward smarter AI coding agents. The ability to validate datasets, monitor training with Trackio, and deploy models directly through Codex sounds incredibly practical for developers. For users…
Search
All sources
xda-developers.com
36
huggingface.co
12
github.blog
12
developer.nvidia.com
8
docker.com
5
aws.amazon.com
4
amd.com
4
neowin.net
4
theverge.com
3
pcworld.com
3
bleepingcomputer.com
2
about.gitlab.com
2
Top stories
Agentic coding ruined normal IDEs like VS Code, Zed, and PyCharm for me, and I don’t think I can go back
…Google Antigravity, which started as a VS Code fork , has turned into an agentic tool with version 2.0 . Cursor, a popular VS Code alternative, is also headed in the same direction…
Security validation for third-party coding agents - GitHub Changelog
Back to changelog Security validation for third-party coding agents is now generally available. GitHub supports third-party coding agents (including Claude and OpenAI Codex) that work directly within your repositories to…
I love my new Codex AI pet — and now I want one in every app
…Codex coding app, I prefer that my AI agents check back with me before making high-stakes decisions. But while that makes for a safer setup, it also means my agents are…
Discussions and forums
How to setup a local coding agent on macOS
How to setup a local coding agent on macOS
498
120
Show HN: Isolade, a local-first coding agent workbench with secretless microVMs
I built Isolade because I could not find an open-source, local-first workbench that runs coding agents in microVMs.The two pieces already exist individually. There are plenty of options for both agent management (Conduct…
3
4
Show HN: testmagic.link – Zero-setup magic link testing for coding agents
I built testmagic.link because Claude Code kept using my personal Gmail when testing magic-link authentication, filling my inbox with test emails.I know there are existing email testing services, but the ones I found req…
3
Show HN: OpenRig – a control plane for multi-agent coding topologies
Hi HN, I’m Mike, the founder of OpenRig.I built this because my Claude Code + Codex setup kept forming little "topologies" of long-lived agents that worked well together, but the terminal sprawl was intense. So I built a…
5
3
Ask HN: Line by Line Agentic Coding
I've been suckered into running claude code and codex independently and vaguely scanning the output before moving on. I don't love the code-base familiarity that produces.Anybody figure out a neat harness setup where one…
6
4
I built repeatable agentic AI workflows that code without me, and the results surprised me
…Just as Ansible orchestrates the setup of my home lab , Archon is the orchestrator for Claude Code and its agents. It's a project manager for when I have other tasks to…
My favorite AI coding tool isn't OpenCode: it's something way better (and cooler)
…Related I replaced Cursor and Antigravity with a completely local VS Code setup, and I missed less than I expected My self-hosted setup holds up pretty well for my coding tasks…
I spent a month with Cursor, Google Antigravity, and Windsurf – and there is a clear winner
…This is a deep dive into 30 days of agentic coding, parallel task management, and the search for the IDE that actually lets me build faster without losing my mind. Related 4…
The best productivity tool I set up this month is built for developers, and I should have done it sooner
…I can't think of a more perfect setup - using an agent-first coding platform for organizing files, wrangling notes, and building small personal tools, none of which involves writing code. The…
I made these 4 changes to my Claude Code setup, and now it runs circles around the defaults
…A review agent always looks for issues in the implementation. A documentation agent always focuses on explaining what has changed. Connect relevant MCP servers Give Claude Code access to updated info I…
Paper page - Multi-Agent Computer Use
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Computer use agents (CUAs) today are primarily deployed as single serial agents. This setup is suboptimal for complex long-horizon tasks that benefit from…