Read original ↗
newsHacker NewsTrust 52 · CommunityPublished 1mo agoLive · 1mo ago

Show HN: ContextVault – Shared memory layer for your AI and your team

Hi HN, I'm Kevin. I built ContextVault because I kept running into the same problem with AI tools. Every project accumulated prompts, coding conventions, architectural decisions, examples, and other pieces of context that made the models significantly more useful. The problem was that this information quickly became fragmented. Some lived in ChatGPT Projects, some in Claude, some in Markdown files, some in internal documentation, and some only existed in previous conversations. Late las

Open SourceHacker Newsverified

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

Covers

repobasicmachines-co/basic-memorypaperShared Selective Persistent Memory for Agentic LLM SystemspaperLLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via a Proprioceptive Dashboardrepobonigarcia/context-engineeringrepoFrappucc1no/recall-loom

Covers (incoming)

paperReconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long Contextreposopaco/deepwiki-rspaperLongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budgetrepomaquina-app/recuerd0paperHandover of In-Context Learning State Across Session Boundaries

Related across the graph

repobasicmachines-co/basic-memoryrepomaquina-app/recuerd0repobonigarcia/context-engineeringpaperLLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via a Proprioceptive DashboardpaperReconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long ContextrepoFrappucc1no/recall-loompaperHandover of In-Context Learning State Across Session BoundariespaperShared Selective Persistent Memory for Agentic LLM Systemsreposopaco/deepwiki-rspaperLongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget