Differential-KV (DKV) is a sparse KV-cache inference runtime designed for high-efficiency, memory-bounded long-context Large Language Model (LLM) inference across Apple Silicon (MLX) and CUDA GPUs.
Tiny Pointers is a C library for space-efficient pointer compression, reducing memory overhead while maintaining fast lookups. Supports SIMPLE, FIXED, and VARIABLE variants with thread safety and resizing (SIMPLE only).
GhostMem (GMlib) is a smart memory management system that extends available RAM through **in-memory compression** rather than traditional disk-based swapping.
4304MB -> 1569MB - ReviOS-grade Windows 11 RAM optimizer for 8GB PCs. 1.6GB idle, memory compression, RAM watchdog, telemetry debloat & NZXT CAM 50MB. One-click GUI + CLI.
Agent memory you can trust: governed context selection, drift control via retract/heal, deterministic replay.
Experimental Vulkan GPU memory research: allocation telemetry, capacity probes, and lossless managed-buffer compression.
LLM inference with 7x KV cache compression. Combines llama.cpp (production inference engine) with TurboQuant (KV quantization). Run 131K token context on 16GB VRAM. OpenAI-compatible API server. Supports 100+ model architectures.
Hermes + Yume (夢): sleep-time memory consolidation for Hermes Agent. Replays sessions from state.db and consolidates MEMORY.md / USER.md like a sleeping brain (NREM → REM → Dream Log).
Task Manager says Memory 62% and that number tells you almost nothing. Shows the hard page faults that actually cause stutter, commit charge against the real limit, how much of your RAM is reclaimable cache, and what memory compression is hiding. Read-only, zero dependencies. Not a hardware memory tester.
金融长文本智能问答系统：检索·判定·记忆·归因四层全链（BM25F 逐选项检索 + 选项级证据隔离 + 分层记忆压缩 + 引用观测归因），自建五域评测集（法规/财报/保险/合同/研报，50 题含 193 页募集说明书），791 例测试。场景口径对齐 AFAC2026 赛题四公开题面，无参赛成绩/官方关联。
A protocol for computational exhalation: reducing redundant output, compressing stale traces, and preserving reusable intelligence in AI systems.
Research on task-utility-aware episodic memory compression for long-horizon egocentric robotic agents under bounded memory.
A memory compression engine built for AI — modular, dual-mode (Compact or Expressive), and part of Nova OS in development. Designed for scalable memory and token efficiency while preserving meaning.
Low-rank eligibility traces for memory-efficient delayed credit assignment.
AI agent evaluation system for testing Claude, Gemini & iFlow under memory compression — FastAPI, PostgreSQL, Redis
Compiler-inspired long conversation memory compression: dead memory elimination, fact folding, temporal compression, knapsack pruning
To associate your repository with the memory-compression topic, visit your repo's landing page and select "manage topics."