Coding Tools
GitHub Copilot Memory GA and Dreaming Preview
GitHub Changeloghigh confidence
Why it matters
- →Persistent memory reduces the friction of re-explaining team conventions in every new session.
- →Autonomous 'Dreaming' allows the agent to self-correct and update its own knowledge base over time.
- →Cross-repo search enables agents to trace dependencies across services without manual context assembly.
GitHub has made Copilot Memory generally available for paid plans, allowing the AI to retain personal preferences and repository conventions across sessions. Alongside this, GitHub introduced 'Dreaming' in public preview, an autonomous feature that reflects on past interactions to update memories and propose changes to skills or instructions via pull requests. The update also includes cross-repository code search capabilities, enabling agents to inspect implementations and callers across multiple projects without requiring local clones. These features aim to reduce repetitive guidance and help agents understand broader system contexts.
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 Agents Gain Slack and Teams Context
GitHub Changelog · September 25, 2026 · Same story
- 2Copilot Agentic Autofix Now Uses Memory
GitHub Changelog · September 25, 2026 · Same 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.
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