Coding Tools
GitHub Copilot Introduces Agent Finder Feature
GitHub Changeloghigh confidence
Why it matters
- →Streamlines the process of finding the right AI tools for developers.
- →Enhances customization and control over AI resource usage.
- →Promotes industry collaboration through the open ARD specification.
GitHub has introduced an Agent Finder feature for its Copilot tool, designed to automatically discover and suggest the best AI resources for specific tasks. This new capability uses the open Agentic Resource Discovery (ARD) specification, developed in collaboration with companies like Google and Microsoft. Developers can point the Agent Finder at a public or private registry, allowing it to rank and suggest tools without automatic installation. This feature is available on all GitHub Copilot plans, enhancing the flexibility and efficiency of AI-driven development.
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 Enhances CLI and Agent Capabilities
GitHub Changelog · June 2, 2026 · Same story
- 2GitHub Copilot SDK Now Generally Available
GitHub Changelog · June 2, 2026 · Same story
- 3GitHub Copilot App Now Supports Any Model Provider
Matt Wolfe · June 10, 2026 · Same story
Follow this story
Open the full story →GitHub Copilot Introduces Agent Finder Feature
3 developments
- Jun 17 · GitHub Changelog
GitHub Copilot Introduces Agent Finder Feature (This article) - Jun 18 · GitHub Changelog
GitHub Copilot Enhances Code Review with AGENTS.md↳ Copilot now integrates AGENTS.md for customized feedback and adds a Request button for draft pull requests. - Jun 25 · GitHub Changelog
GitHub Copilot for Jira Now Generally Available↳ GitHub Copilot for Jira is now generally available with real-time agent monitoring and follow-up instructions directly in Jira issues.
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.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
llama.cpp Releases