Tabby – sleeps tabs based on RAM pressure, not fixed timers
Memory-pressure detection beats timer-based tab sleepers, but the category is saturated.
An experimental memory-pressure signal for Windows
Memory-pressure detection beats timer-based tab sleepers, but the category is saturated.
Using Linux PSI signals to prune KV cache is genuinely clever for edge inference.
Enterprise Windows 11 hardening with privilege separation, but O&O ShutUp++ exists.
Context condensing under memory pressure solves the actual pain of edge AI agents.
Putting the memory layer on-disk as a .afs/ tree is a gutsy, practical move — you get searchable JSON, FTS5 for text queries, HNSW vectors for similarity, and msgpack edges for relationships without running a separate DB service. It feels like a thoughtful toolkit for agents that must persist thinking artifacts (observations → reflections → knowledge), though I want to see details on concurrency, index portability, and how this performs at scale before betting production workloads on it.
Windows optimizer claiming to fix Wi-Fi stutters that Windows already manages.