Tagged "context-management"
-
LLM Memory Doesn't Only Get Written Wrong, It Goes Wrong Later
-
The Interesting Part of an Agent Harness is What You Add on Top
-
Show HN: Trace – Open-source, Self-organizing Memory for LLM Agents
-
Meet Memory OS: A 6-Layer Open-Source Memory Stack Built on Hermes Agent
-
The Infrastructure Behind Making Local LLM Agents Actually Useful
-
Local LLM Setup: How to Use RAG and an Embedding Model to Stop Wasting Context
-
Local LLM Persistent Context Prevents Repetitive Mistakes
-
Microsoft Researchers Find AI Models and Agents Can't Handle Long-Running Tasks
-
One LM Studio Setting Makes Local LLMs Competitive With Cloud Models
-
0ctx – Local-First Project Memory for AI Workflows
-
Show HN: A Local-First Agentic Knowledge Manager
-
Ask HN: Real life autonomous AI Agents
-
Show HN: Kit – Editor, Browser, Terminal, Mail with AI Agents Sharing Context
-
Xmemory: Benchmarking Structured AI Memory Against RAG and Hybrid RAG
-
Externalization in LLM Agents: Unified Review of Memory and Harness Engineering
-
ChatMCP – Connect your AI browser chats to your coding agents
-
Learn LLM Internals
-
Show HN: Memsearch – Persistent, Cross-Agent, Cross-Session Memory for AI Agents
-
Building a Production AI Receptionist: Practical Local LLM Deployment Case Study
-
AI Playground for Developers Built in Vite and Python
-
Community Converges on Optimal KV Cache Quantization Strategies for Qwen 3.5 Models
-
AI's Impact on Mathematics Analogous to Car's Impact on Cities
-
Mamba 3: State Space Model Architecture Optimized for Inference
-
Running Qwen3.5-27B Across Multiple GPUs Over LAN Achieves Practical Speed for Local Inference
-
Memory Should Decay: Implementing Temporal Memory Decay in Local LLM Systems
-
Llama.cpp Celebrates Major Milestone: From Leak to Industry Standard
-
Mnemos: Persistent Memory System for Local AI Agents
-
Qwen 3.5 Family Benchmark Comparison Shows Strong Performance Across Smaller Models
-
ETH Zurich Research Challenges Context-Length Assumptions in LLM Agents
-
Analysis Reveals Claude Code Sends 62,600 Characters of Tool Definitions Per Turn
-
Apple Unveils MacBook Pro With M5 Pro and M5 Max for On-Device AI
-
C7: Pipe Up-to-Date Library Docs Into Any LLM From the Terminal
-
Critical: Qwen 3.5 Requires BF16 KV Cache, Not FP16 for Accurate Inference
-
Qwen 3.5 MoE Delivers 100K Context Window at 40+ TPS on RTX 5060 Ti
-
Every agent framework has the same bug – prompt decay. Here's a fix
-
Show HN: A Human-Curated, CLI-Driven Context Layer for AI Agents
-
Qwen3.5-27B Identified as Sweet Spot for Mid-Range Local Deployment
-
O-TITANS: Orthogonal LoRA Framework for Gemma 3 with Google TITANS Memory Architecture
-
TemplateFlow – Build AI Workflows, Not Prompts
-
Qwen3 Coder Next 8FP Demonstrates Exceptional Long-Context Performance on 128GB System
-
The Path to Ubiquitous AI (17k tokens/sec)
-
Why AI Models Fail at Iterative Reasoning and What Could Fix It
-
GLM-5 Technical Report: DSA Innovation Reduces Training and Inference Costs
-
InitRunner: YAML-Based AI Agent Framework with RAG and Memory
-
NVIDIA's Dynamic Memory Sparsification Cuts LLM Inference Costs by 8x
-
GPT-OSS 120B Uncensored Model Released in Native MXFP4 Precision
-
SnowBall Technique Addresses Context Window Limitations in Local LLMs
-
Context Management Identified as Real Bottleneck in AI-Assisted Coding
-
Heaps Do Lie: Debugging a Memory Leak in vLLM
-
Use Recursive Language Models to address huge contexts for local LLM
-
DeepSeek Launches Model Update with 1M Context Window