Fresh stories
Anthropic launches Claude Platform on AWS with native billing, IAM, and Managed Agents
Anthropic made Claude Platform on AWS generally available, exposing the native Claude API with AWS authentication, billing, CloudTrail, and commitment retirement. It lets teams use Managed Agents and related Claude features inside existing AWS governance workflows.
Files SDK launches unified storage API with 18 providers and OpenAI, Vercel AI, and Claude tools
Files SDK launched a unified storage API across 18 backends including S3, R2, Vercel Blob, and Google Drive. It also ships tool bindings for OpenAI, Vercel AI, and Claude agent SDKs across Node, Bun, Deno, edge runtimes, and browsers.
TanStack reports npm supply-chain attack across 42 packages with credential-stealing payload
TanStack disclosed a supply-chain attack that pushed two malicious npm versions across 42 packages in a 10-minute window. The payload targeted cloud keys, GitHub tokens, npm credentials, and SSH material, so teams should audit installs and rotate secrets.
Claude Code 2.1.139 adds `claude agents` view and `/goal` runs with live turn counters
Claude Code 2.1.139 shipped a research-preview agent view plus a `/goal` mode that keeps working across turns while showing elapsed time, turns, and token counts. The update turns parallel Claude sessions into a built-in control plane, so teams can drop tmux-and-scripts workarounds.
Anthropic launches Claude Platform on AWS with native billing, IAM, and Managed Agents
Anthropic made Claude Platform on AWS generally available, exposing the native Claude API with AWS authentication, billing, CloudTrail, and commitment retirement. It lets teams use Managed Agents and related Claude features inside existing AWS governance workflows.
Developers launch Agent FM, Mate, and ntm for multi-session Claude Code and Codex control
Independent developers shipped new control-plane tools for long-running coding agents, including Agent FM audio monitoring, Mate phone-first remote control, and ntm for provider-agnostic multi-agent workflows. It matters because teams running many Claude Code and Codex sessions still need better visibility, handoff, and checkpointing than a single built-in session list provides.
Artificial Analysis launches Coding Agent Index: Cursor plus Opus 4.7 scores 61, Codex plus GPT-5.5 60
Artificial Analysis launched a Coding Agent Index for model-and-harness pairs, while OpenHands refreshed its model leaderboard. The results show harness choice matters, with cost varying over 30x and task time over 7x across stacks.
Files SDK launches unified storage API with 18 providers and OpenAI, Vercel AI, and Claude tools
Nous Research adds CUA computer use to Hermes Agent for desktop control
Developers launch Markdown Experience Guidelines and HTML explainer tools for agent output
TanStack reports npm supply-chain attack across 42 packages with credential-stealing payload
Briefs forMay 11
Top storiesthis week
Codex app adds /goal for long-running React Doctor and iOS runs
OpenAI staff said /goal is now available in the Codex app, and users posted long-running runs that fixed React Doctor scores, built iOS features, and queued weekend tasks. The update moves Codex from CLI-only planning to persistent, steerable work sessions.
OpenCode adds Ring 2.6 1T with 256K context and free limited-time access
OpenCode made Ring 2.6 1T available in the editor with reasoning enabled and free access for a limited period. Follow-on posts from Kilo and others claim frontier-level results on AIME 26, ClawEval, Gaia2-search, and Tau2-Bench Telecom.
Amp Neo reports scaling issues as remote Mac-mini beta reaches airplane Wi-Fi users
Amp paused wider Neo rollout after hitting scaling issues, but beta users still showed remote sessions running from a home Mac mini through the web UI, including over airplane Wi-Fi. That makes Neo notable as a local-hosted coding-agent model, even if the control plane is not yet stable enough for broader access.
Claude Code guide fixes hallucinated SHAs with adaptive thinking off and effort=high
A Claude Code guide tied hallucinated package names, API versions, and SHAs to zero-thinking turns and recommended config changes to force fixed reasoning budgets and higher effort. HN discussion and user reports suggest the workaround is being used against a broader reliability regression, not just one bad prompt.
GPT-5.5 vs Opus 4.7: users compare plan mode, frontend output, and 120K-context use
User posts and HN threads compared GPT-5.5 and Opus 4.7 across plan mode, frontend work, and 120K-context sessions. The split results mean token burn and instruction discipline matter as much as raw benchmark scores.
Daily AI Digest
Get the best stories delivered
to your inbox
Skills Spotlighttop by stars
comfyui
Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.
hyperframes
Create HTML-based video compositions, animated title cards, social overlays, captioned talking-head videos, audio-reactive visuals, and shader transitions using HyperFrames. HTML is the source of truth for video. Use when the user wants a rendered MP4/WebM from an HTML composition, wants to animate text/logos/charts over media, needs captions synced to audio, wants TTS narration, or wants to convert a website into a video.
kanban-orchestrator
Decomposition playbook + specialist-roster conventions + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.