Coding Tools
GitHub Copilot adds server-to-server auth for orgs
GitHub Changeloghigh confidence
Why it matters
- →Enables autonomous agents to use Copilot without relying on human credentials or quotas.
- →Shifts billing and governance from individual users to the organization level.
- →Allows enterprises to audit and control AI usage by specific applications via app_client_id.
GitHub has added server-to-server authentication for GitHub Copilot, enabling GitHub Apps to make API requests on behalf of an organization without requiring a signed-in user. Available in public preview, this feature allows services built with the Copilot SDK to use short-lived installation access tokens, attributing usage and billing directly to the organization. Organization owners can now manage access via read-only permissions, monitor app-attributed usage through AI usage CSV reports, and enforce model policies and spending controls independently of individual user accounts.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1GitHub Copilot Code Review adds org billing controls
GitHub Changelog · October 8, 2026 · Same story
What happened next
- 2GitHub Copilot Automations go team-shared
GitHub Changelog · October 28, 2026 · Same story
Follow this story
Open the full story →More in Coding Tools
Coding Toolscoding
Claude Code v2.1.316: Subagents and Gateway Budgets
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
Claude Code Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.