GITHUB
30 days · UTC
Synchronizing with global intelligence nodes...
Claude Code adds live Artifacts; GitHub Action v1.0 cleans up CI
Anthropic added live, shareable Artifacts to Claude Code and shipped a cleaner v1.0 GitHub Action for CI. Artifacts turn a Claude Code session into a...
AWS DevOps Agent adds AI release readiness gates (preview)
AWS DevOps Agent now pre-screens code changes with AI-built, change-aware tests and isolated runs before they hit your pipeline. In preview, AWS’ Dev...
Copilot SDK adds session memory and lazy tool loading
GitHub Copilot SDK now supports persistent session memory and lazy tool loading that leans on model tool search. In [v1.0.2](https://github.com/githu...
Claude Code v2.1.181: in-session /config, reliability fixes, and safer writes
Anthropic shipped Claude Code v2.1.181 with mid-session configuration and fixes for data-loss and flaky startups. The new release adds a simple /conf...
Claude Code grows up: plugins + marketplaces make it team-ready
Claude Code’s plugin and marketplace model is solidifying into a team-ready platform for standardized skills, hooks, and multi-agent workflows. A dee...
APIs become the execution layer as agents emerge as the UI — and Microsoft’s marketplace is leaning in
SaaS consumption is shifting from dashboards to API-first systems driven by AI agents, with Microsoft’s marketplace pushing agents as sellable apps. ...
GitHub Copilot switches all plans to usage-based billing with temporary caps
GitHub Copilot changed all plans to usage-based billing and will pause Copilot features when you hit spending limits. GitHub announced the shift to u...
LLM-aware supply-chain malware hits Python and Microsoft repos; Spring tightens defenses
LLM-aware supply-chain malware is abusing open source packages, AI code agents, and cloud identity to spread and steal secrets. Researchers detailed ...
Agents got safer: Antigravity patches skill security; WindsurfAPI fixes WebFetch completion semantics
Antigravity hardened its popular skill library against path traversal and unsafe plugin behaviors, and related agent stacks tightened up tool-call han...
Claude Code gets native installers; treat it like a production agent
Anthropic made Claude Code much easier to roll out with native installers, and teams should now treat it like a real production agent. Anthropic’s te...
Copilot goes metered: usage-based billing lands as GitHub ships an agent desktop and Microsoft swaps in a new coding model
GitHub Copilot switched to usage-based billing across all plans. GitHub says Copilot now runs on AI Credits with spend caps and plan-based limits; ov...
Windsurf becomes Devin Desktop, with smarter local context and honest rate‑limit signaling
Windsurf rebranded to Devin Desktop and shipped updates that change agent context handling and how clients back off under rate limits. Per the [chang...
OpenSpec v1.4.1 restores `openspec update` for workspace.yaml projects (e.g., Dagster)
OpenSpec v1.4.1 fixes the broken openspec update command for projects that maintain their own workspace.yaml, including Dagster setups. The [v1.4.1 r...
AI agents are forcing a real trust and cost layer
Teams are running into agent reliability and cost spikes while vendors add partial governance features. Engineers reported GitHub Copilot Agent Mode ...
Microsoft makes Copilot agent-native: new code model, desktop app, and terminal integration
Microsoft is turning GitHub Copilot into an agent-native stack with a new in-house code model and system-level integrations. Microsoft introduced MAI...
GitHub Copilot switched to usage-priced credits; teams are seeing real cost spikes
GitHub Copilot moved from request-based billing to usage-priced credits, and heavy users are burning through quotas fast. Per GitHub’s rollout, month...
Copilot CLI tightens tool-call safety; GitHub app unblocks agent permission flows
GitHub Copilot CLI changed how tool calls are gated, and the GitHub app fixed permission dialogs that could stall agent runs. In the Copilot CLI pre-...
Antigravity Awesome Skills v11.10 ships AI-readiness SEO checks and YouTube research
Antigravity Awesome Skills v11.10.0 bundles concrete AI-readiness SEO and research skills while new playbooks and tools harden llms.txt and entity sig...
GitHub shifts Copilot and repo defaults toward cost control and trust
GitHub is tightening Copilot defaults and repo trust gates to cut AI noise and token waste. The latest [Copilot CLI 1.0.55](https://github.com/github...
Claude Opus 4.8 and Claude Code add dynamic multi-agent workflows and a cheaper fast mode
Anthropic shipped Claude Opus 4.8 and updated Claude Code with dynamic multi-agent workflows and a cheaper fast mode. Opus 4.8 arrives with higher de...
Copilot CLI/SDK pre-releases make per-session plugins and run visibility first-class
GitHub Copilot CLI pre-releases add per-session plugin mounts and better session visibility, pushing Copilot toward a real programmable agent runtime....
AI bug-hunters are real: Anthropic’s Mythos Preview shows scale, ops must adapt
Anthropic’s Mythos Preview is surfacing hundreds of critical vulnerabilities, showing security-grade AI agents are ready—but ops and remediation workf...
Claude Code v2.1.152: Auto‑fix code reviews, stricter guardrails, safer defaults
Anthropic shipped Claude Code v2.1.152, turning code reviews into applied patches and tightening enterprise guardrails. The release adds /code-review...