--- title: "memory-os" type: "tool" slug: "claudiodrews-memory-os" canonical_url: "https://www.graphcanon.com/tools/claudiodrews-memory-os" github_url: "https://github.com/ClaudioDrews/memory-os" homepage_url: null stars: 1232 forks: 117 primary_language: "Python" license: "MIT" categories: ["data-retrieval", "ai-agents"] tags: ["context-injection", "hermes-agent", "persistent-memory", "ground-truth", "docker", "local-first", "ai-memory", "open-source"] updated_at: "2026-07-07T18:47:33.386247+00:00" --- # memory-os > A 7-layer memory operating system for Hermes Agent memory-os is a local-first, persistent-memory infrastructure for AI agents like Hermes Agent. It includes seven memory layers with automatic context injection and supports various LLM providers. ## Facts - Repository: https://github.com/ClaudioDrews/memory-os - Stars: 1,232 · Forks: 117 · Open issues: 7 · Watchers: 14 - Primary language: Python - License: MIT - Last pushed: 2026-06-10T10:40:43+00:00 ## Categories - [Data & Retrieval](/categories/data-retrieval.md) - [AI Agents](/categories/ai-agents.md) ## Tags context-injection, hermes-agent, persistent-memory, ground-truth, docker, local-first, ai-memory, open-source ## Related tools - [ECC](/tools/affaan-m-ecc.md) - The agent harness performance optimization system (★ 226,962) - [hermes-agent](/tools/nousresearch-hermes-agent.md) - The self-improving AI agent built by Nous Research (★ 210,880) - [AutoGPT](/tools/significant-gravitas-autogpt.md) - AutoGPT: Build, Deploy, and Run AI Agents (★ 185,417) - [ollama](/tools/ollama-ollama.md) - Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. (★ 175,659) - [transformers](/tools/huggingface-transformers.md) - 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models (★ 162,347) - [langflow](/tools/langflow-ai-langflow.md) - Langflow is a powerful platform for building and deploying AI-powered agents and workflows. (★ 151,298) - [dify](/tools/langgenius-dify.md) - Production-ready platform for agentic workflow development (★ 148,070) - [firecrawl](/tools/firecrawl-firecrawl.md) - The API to search, scrape, and interact with the web at scale. (★ 147,117) ## README (excerpt) ```text # Memory OS — Hermes Agent Memory Operating System > **Your agent finally stops forgetting.** \ > Permanent memory. Local memory infrastructure. API-provider agnostic. Surgically token-efficient. Seven memory layers. Automatic, intelligent context injection. Structured facts with trust scoring. A self-curating wiki pipeline. Semantic search across **every conversation you've ever had**. 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. **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.** --- ## What's New in v0.2.0 **One-command install.** `curl -sSL https://raw.githubusercontent.com/ClaudioDrews/memory-os/main/setup.sh | bash` 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. **Community infrastructure.** Issue templates (bug report + feature request), PR checklist, and contributing guide. Project is ready for external contributors — and already has them. **20+ fixes from systematic audit.** 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. **Installation verified on real hardware.** 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. --- ## The problem every serious Hermes user knows 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. - Repeating context at the start of every conversation - Losing the thread of important decisions made weeks ago - Structured facts — your stack, your projects, your patterns — with nowhere to live - Every memory solution you've tried is either cloud-locked or too shallow to matter After months of hitting these walls in production, I built something that actually works. --- ## What Memory OS is Not just another plugin. A complete **memory operating system** — 7 layers working in concert, from flat files to a vector database, with surgical context injection, a knowledge pipeline that organizes itself, **and an explicit Ground Truth hierarchy that tells the agent to actually use the injected memory**. Designed and refined by someone who ran headfirst into every limitation of stock Hermes and every existing memory solution. **Requirements:** Hermes Agent + Docker (Qdrant + Redis + ARQ Worker) + Python 3.11+. Compatible with any LLM provider Hermes supports — OpenRouter, OpenAI, Anthropic, Ollama, and more. --- ## Architecture: 7 memory layers ``` ┌──────────────────────────────────────────────────────────────────┐ │ LAYER 1 · WORKSPACE │ │ MEMORY.md · USER.md · CREATIVE.md │ │ → Injected into the system prompt every single turn │ ├──────────────────────────────────────────────────────────────────┤ │ LAYER 2 · SESSIONS │ │ state.db (SQLite + FTS5) │ │ → Full-text search across your entire conversation history │ ├──────────────────────────────────────────────────────────────────┤ │ LAYER 3 · STRUCTURED FACTS │ │ memory_store.db (SQLite + HRR + FTS5 + trust scoring) │ │ → Durable facts with entity resolution and an automat ``` --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/tools/claudiodrews-memory-os`](/api/graphcanon/tools/claudiodrews-memory-os) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_