ToolsGitHub Models retired — impacts on Actions-based AI workflowsGitHub Models has been retired, disrupting workflows that relied on its unified API and the convenience of using GitHub Actions' built-in API key for LLM calls.2 min read
ToolsHermes Agent runnable with Vercel AI Gateway and Vercel SandboxHermes Agent is now usable with the Vercel AI Gateway and Vercel Sandbox services: the AI Gateway key can provide access to all models and give full visibility into spending, while the Sandbox runs…1 min read
ToolsAnthropic makes Claude Code’s auto mode the default for paid tiersAnthropic will set auto mode as the default for Claude Code on Pro, Max, and Team accounts beginning August 14.2 min read
ToolsT3 Code reduces agents' management burden and restores focusThe T3 Code tool, after months of parallel agent use, resolves problems caused by threads, half-finished worktrees and the “who does what?” issue; workflows can be created, tracked, merged and…1 min read
ToolsT3 Code introduced new “usage” page detailing API costs and token usageT3 Code has introduced a new “usage” page that breaks down API costs and token usage between Claude Code and Codex.1 min read
ToolsVercel eases the hardest part of AI agents in enterprise environmentsThe technical lead of a 55,000+ employee company's AI-agent platform said, "Others make the easy part easier; Vercel makes the hard part." They tried multiple solutions (aisdk, off-the-shelf…1 min read
ToolsGPT-5.6 Sol Ultra (Codex) builds and debugs a new indie game: Moonlight & MayhemA developer tested the same one‑shot game prompt previously used with Claude Fable 5 by running it on Codex Desktop powered by GPT‑5.6 Sol Ultra.2 min read
ToolsTencent releases open-source Team Memory to share agent context — governance for corrections and expiry still missingTencent launched Agent Memory and this week expanded it with Team Memory, an open-source system that lets multiple AI agents read and write against a shared hub of contextual assets.6 min read
ToolsNext.js 16.3: v0 navigations are nearly 3.5× fasterIn Next.js version 16.3, v0 navigations became about 3.5× faster.1 min read
ToolsRippling launches AI Spend Console to track and curb employee token useRippling introduced AI Spend Console, a tool that maps AI token consumption by employees, teams and roles and links spending to measured productivity.4 min read
ToolsCloudflare launches Kitesurf, a cloud-hosted browser built for AI agentsCloudflare unveiled Kitesurf, a headless, cloud-hosted web browser purpose-built for AI agents rather than human users.2 min read
ToolsHSP GRUPPE integrates ChatGPT Enterprise to reshape tax advisory and processesHSP GRUPPE has embedded ChatGPT Enterprise across its network of tax, audit and law firms to speed information processing, improve work quality and free capacity for advisory tasks.4 min read
