[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:memory-os":3},"\u003Ch1>Memory OS — Hermes Agent Memory Operating System\u003C\u002Fh1>\n\u003Cp>\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002FClaudioDrews\u002Fmemory-os\u002FHEAD\u002Fassets\u002Fbanner.jpg\" alt=\"Memory OS Banner\" \u002F>\u003C\u002Fp>\n\u003Cblockquote>\n\u003Cp>\u003Cstrong>Your agent finally stops forgetting.\u003C\u002Fstrong>  \u003Cbr \u002F>Permanent memory. Local memory infrastructure. API-provider agnostic. Surgically token-efficient.\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Cp>Seven memory layers. Automatic, intelligent context injection. Structured facts with trust scoring. A self-curating wiki pipeline. Semantic search across \u003Cstrong>every conversation you've ever had\u003C\u002Fstrong>.\u003C\u002Fp>\n\u003Cp>Memory OS turns Hermes Agent into a real long-term collaborator — one that remembers your projects, your decisions, your reasoning, and brings exactly the right context back at exactly the right moment. Like talking to a colleague who was there for every session.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Memory infrastructure runs entirely on your machine. Works with any LLM provider — OpenRouter, OpenAI, Anthropic, Ollama, or local models. No memory subscription. No vendor lock-in.\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Chr \u002F>\n\u003Ch2>What's New in v0.2.0\u003C\u002Fh2>\n\u003Cp>\u003Cstrong>One-command install.\u003C\u002Fstrong> \u003Ccode>curl -sSL https:\u002F\u002Fraw.githubusercontent.com\u002FClaudioDrews\u002Fmemory-os\u002Fmain\u002Fsetup.sh | bash\u003C\u002Fcode> sets up the entire stack — Docker services, SQLite databases, Icarus plugin, environment — in one shot. The 10-step manual guide is now a fallback for troubleshooting.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Community infrastructure.\u003C\u002Fstrong> Issue templates (bug report + feature request), PR checklist, and contributing guide. Project is ready for external contributors — and already has them.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>20+ fixes from systematic audit.\u003C\u002Fstrong> Community-driven review across setup, configuration, performance, and resilience. Highlights: provider-agnostic LLM extraction, O(1) path lookups, FTS5-powered session search, semantic dedup at scale, and idempotent database initialization.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Installation verified on real hardware.\u003C\u002Fstrong> Smoke tests and ingestion tests ship with the repo. The automated installer has been tested end-to-end — including on modest machines where Docker build times exposed UX gaps that are now handled gracefully.\u003C\u002Fp>\n\u003Chr \u002F>\n\u003Ch2>The problem every serious Hermes user knows\u003C\u002Fh2>\n\u003Cp>You spend hours configuring the agent, teaching it your preferences, solving hard problems together — and in the next session it acts like it's meeting you for the first time.\u003C\u002Fp>\n\u003Cul>\n\u003Cli>Repeating context at the start of every conversation\u003C\u002Fli>\n\u003Cli>Losing the thread of important decisions made weeks ago\u003C\u002Fli>\n\u003Cli>Structured facts — your stack, your projects, your patterns — with nowhere to live\u003C\u002Fli>\n\u003Cli>Every memory solution you've tried is either cloud-locked or too shallow to matter\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>After months of hitting these walls in production, I built something that actually works.\u003C\u002Fp>\n\u003Chr \u002F>\n\u003Ch2>What Memory OS is\u003C\u002Fh2>\n\u003Cp>Not just another plugin. A complete \u003Cstrong>memory operating system\u003C\u002Fstrong> — 7 layers working in concert, from flat files to a vector database, with surgical context injection, a knowledge pipeline that organizes itself, \u003Cstrong>and an explicit Ground Truth hierarchy that tells the agent to actually use the injected memory\u003C\u002Fstrong>.\u003C\u002Fp>\n\u003Cp>Designed and refined by someone who ran headfirst into every limitation of stock Hermes and every existing memory solution.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Requirements:\u003C\u002Fstrong> Hermes Agent + Docker (Qdrant + Redis + ARQ Worker) + Python 3.11+.\u003Cbr \u002F>Compatible with any LLM provider Hermes supports — OpenRouter, OpenAI, Anthropic, Ollama, and more.\u003C\u002Fp>\n\u003Chr \u002F>\n\u003Ch2>Architecture: 7 memory layers\u003C\u002Fh2>\n\u003Cpre>\u003Ccode>┌──────────────────────────────────────────────────────────────────┐\n│  LAYER 1 · WORKSPACE                                              │\n│  MEMORY.md · USER.md · CREATIVE.md                               │\n│  → Injected into the system prompt every single turn             │\n├──────────────────────────────────────────────────────────────────┤\n│  LAYER 2 · SESSIONS                                               │\n│  state.db (SQLite + FTS5)                                         │\n│  → Full-text search across your entire conversation history       │\n├──────────────────────────────────────────────────────────────────┤\n│  LAYER 3 · STRUCTURED FACTS                                       │\n│  memory_store.db (SQLite + HRR + FTS5 + trust scoring)            │\n│  → Durable facts\n\u003C\u002Fcode>\u003C\u002Fpre>\n",1784240407596]