{"id":51178968,"url":"https://github.com/evermind-ai/everos","last_synced_at":"2026-07-07T12:00:15.955Z","repository":{"id":323442793,"uuid":"1085086903","full_name":"EverMind-AI/EverOS","owner":"EverMind-AI","description":"One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.","archived":false,"fork":false,"pushed_at":"2026-07-03T00:51:19.000Z","size":2337,"stargazers_count":10078,"open_issues_count":41,"forks_count":831,"subscribers_count":109,"default_branch":"main","last_synced_at":"2026-07-03T02:24:53.566Z","etag":null,"topics":["agent-memory","agentic-ai","ai","chats","clawdbot","clawdbot-skill","llm","long-term-memory","mcp","memory","memory-management","python3","rag","skills"],"latest_commit_sha":null,"homepage":"https://evermind.ai/everos","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/EverMind-AI.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":"CITATION.md","codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":"NOTICE","maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-10-28T15:09:32.000Z","updated_at":"2026-07-03T02:24:10.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/EverMind-AI/EverOS","commit_stats":null,"previous_names":["evermind-ai/evermemos","evermind-ai/everos"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/EverMind-AI/EverOS","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EverMind-AI%2FEverOS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EverMind-AI%2FEverOS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EverMind-AI%2FEverOS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EverMind-AI%2FEverOS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EverMind-AI","download_url":"https://codeload.github.com/EverMind-AI/EverOS/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EverMind-AI%2FEverOS/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35226918,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-07T02:00:07.222Z","response_time":90,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-memory","agentic-ai","ai","chats","clawdbot","clawdbot-skill","llm","long-term-memory","mcp","memory","memory-management","python3","rag","skills"],"created_at":"2026-06-27T06:00:38.603Z","updated_at":"2026-07-07T12:00:15.947Z","avatar_url":"https://github.com/EverMind-AI.png","language":"Python","funding_links":[],"categories":["The latest additions 🎉"],"sub_categories":["Usage"],"readme":"\u003cdiv align=\"center\" id=\"readme-top\"\u003e\n\n![EverOS banner](https://github.com/user-attachments/assets/8e217d39-5d15-4c6c-9b54-3e83add4e0f2)\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://x.com/evermind\"\u003e\u003cimg src=\"https://img.shields.io/badge/EverMind-000000?labelColor=gray\u0026style=for-the-badge\u0026logo=x\u0026logoColor=white\" alt=\"X\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://huggingface.co/EverMind-AI\"\u003e\u003cimg src=\"https://img.shields.io/badge/🤗_HuggingFace-EverMind-F5C842?labelColor=gray\u0026style=for-the-badge\" alt=\"HuggingFace\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://discord.gg/gYep5nQRZJ\"\u003e\u003cimg src=\"https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Fv10%2Finvites%2FgYep5nQRZJ%3Fwith_counts%3Dtrue\u0026query=%24.approximate_presence_count\u0026suffix=%20online\u0026label=Discord\u0026color=404EED\u0026labelColor=gray\u0026style=for-the-badge\u0026logo=discord\u0026logoColor=white\" alt=\"Discord\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/EverMind-AI/EverOS/discussions/67\"\u003e\u003cimg src=\"https://img.shields.io/badge/WeCom-EverMind_社区-07C160?labelColor=gray\u0026style=for-the-badge\u0026logo=wechat\u0026logoColor=white\" alt=\"WeChat\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n[Website](https://evermind.ai) · [Documentation](https://docs.evermind.ai) · [Blog](https://evermind.ai/blogs) · [中文](README.zh-CN.md)\n\n\u003c/div\u003e\n\n\n\u003cbr\u003e\n\n\u003cdetails\u003e\n  \u003csummary\u003e\u003ckbd\u003eTable of Contents\u003c/kbd\u003e\u003c/summary\u003e\n\n\u003cbr\u003e\n\n- [Why Ever OS](#why-ever-os)\n- [Quick Start](#quick-start)\n- [Use Cases](#use-cases)\n- [Documentation](#documentation)\n- [Star Us](#star-us)\n- [EverMind Ecosystems](#evermind-ecosystems)\n- [Contributing](#contributing)\n\n\u003cbr\u003e\n\n\u003c/details\u003e\n\n\n## Why Ever OS\n\nEverOS is a Python library and local-first memory runtime for agents and\nmakers. It gives one portable memory layer across coding assistants, apps,\ndevices, and workflows from day one. It stores conversations, files, and agent\ntrajectories as readable Markdown, then syncs local SQLite and LanceDB indexes\nfor fast retrieval and self-evolving reuse.\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003cth width=\"28%\"\u003eTitle\u003c/th\u003e\n\u003cth width=\"36%\"\u003eEverOS\u003c/th\u003e\n\u003cth width=\"36%\"\u003eOther Agent Memory Libraries\u003c/th\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eMarkdown source of truth\u003c/strong\u003e\u003c/td\u003e\n\u003ctd\u003e✅ Canonical \u003ccode\u003e.md\u003c/code\u003e files that are readable, editable, diffable, and Git-versioned\u003c/td\u003e\n\u003ctd\u003e❌ Usually API, vector, graph, dashboard, or database state\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eDirect file editing\u003c/strong\u003e\u003c/td\u003e\n\u003ctd\u003e✅ Edit \u003ccode\u003e.md\u003c/code\u003e files; cascade watcher syncs\u003c/td\u003e\n\u003ctd\u003e❌ Usually SDK, API, dashboard, or backend update paths\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eLocal three-part stack\u003c/strong\u003e\u003c/td\u003e\n\u003ctd\u003e✅ Markdown + SQLite + LanceDB; no MongoDB, Elasticsearch, or Redis required\u003c/td\u003e\n\u003ctd\u003e❌ Often depends on managed services, vector DBs, graph DBs, or server stacks\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eUser + agent tracks\u003c/strong\u003e\u003c/td\u003e\n\u003ctd\u003e✅ User \u003ccode\u003eepisodes/profile\u003c/code\u003e and agent \u003ccode\u003ecases/skills\u003c/code\u003e are separate first-class surfaces\u003c/td\u003e\n\u003ctd\u003e❌ Usually centered on chat history, profiles, entities, facts, or retrieval records\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eOrthogonal retrieval\u003c/strong\u003e\u003c/td\u003e\n\u003ctd\u003e✅ Search by \u003ccode\u003euser_id\u003c/code\u003e, \u003ccode\u003eagent_id\u003c/code\u003e, \u003ccode\u003eapp_id\u003c/code\u003e, \u003ccode\u003eproject_id\u003c/code\u003e, and \u003ccode\u003esession_id\u003c/code\u003e\u003c/td\u003e\n\u003ctd\u003e❌ Usually app, namespace, tenant, thread, or graph scoped\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eKnowledge Wiki\u003c/strong\u003e\u003c/td\u003e\n\u003ctd\u003e✅ Editable, source-backed Markdown knowledge pages with taxonomy, CRUD APIs, and topic search\u003c/td\u003e\n\u003ctd\u003e❌ Usually separate from memory, trapped in a dashboard, or not tied back to source files\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eReflection\u003c/strong\u003e\u003c/td\u003e\n\u003ctd\u003e✅ Offline memory evolution that merges episode clusters and refines profiles and skills between sessions\u003c/td\u003e\n\u003ctd\u003e❌ Usually retrieval-only memory with little background consolidation or long-horizon improvement\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n\u003cbr\u003e\n\n## Quick Start\n\n\u003e Goal: play with the memory visualizer first, then start EverOS, write one\n\u003e real memory, and search it back.\n\n### 0. Prerequisites\n\n- Python 3.12+\n- No API keys are needed for `everos demo`.\n- To run the real server-backed memory flow, create two provider keys before\n  `everos init`:\n\n| Capability | Provider | Used for | Fill these `.env` slots |\n| --- | --- | --- | --- |\n| Chat + multimodal | [OpenRouter](https://openrouter.ai/) | `LLM` / `MULTIMODAL` | `EVEROS_LLM__API_KEY`, `EVEROS_MULTIMODAL__API_KEY` |\n| Embedding + rerank | [DeepInfra](https://deepinfra.com/) | `EMBEDDING` / `RERANK` | `EVEROS_EMBEDDING__API_KEY`, `EVEROS_RERANK__API_KEY` |\n\nYou can use other OpenAI-compatible providers by changing the matching\n`*__BASE_URL` fields in `.env`.\n\n### 1. Install\n\n```bash\nuv pip install everos\n# or: pip install everos\n```\n\n### 2. Play With The Demo\n\nRun this before configuring API keys or starting the server:\n\n```bash\neveros demo\n```\n\nThe command asks for one memory and one recall question, then opens a\nfull-screen terminal UI. This is an educational visualizer: it is hardcoded,\nlocal to the CLI, and does not connect to the EverOS server. Its job is to make\nthe memory lifecycle visible: conversation -\u003e memory sphere -\u003e recall -\u003e source\nproof -\u003e confetti. See [docs/everos-demo.md](docs/everos-demo.md) for the demo\nscope and TUI source layout.\n\nThe sphere moves through ingest, extraction, indexing, recall, source reveal,\nand a confetti burst after the first memory lands. Press `r` to replay and `q`\nto quit.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://gist.githubusercontent.com/cyfyifanchen/afa2cf40bf138a3ec96d917e8f2791a2/raw/d4ce82a6ddd7b3ebaf221e4825af993aeca5a7ce/everos-demo-tui-animation.svg\" alt=\"Animated EverOS demo preview showing the memory sphere moving through recall and confetti states\" width=\"720\"\u003e\n\u003c/p\u003e\n\nFor the looping showroom view used in README media, run:\n\n```bash\neveros demo --cinematic\n```\n\nIf your shell is not interactive, or you want a copyable preview, use:\n\n```bash\neveros demo --plain\n```\n\n### 3. Configure\n\nGenerate a starter `.env` file, then fill the four API key slots shown in the\ngenerated comments. With the default setup, paste your OpenRouter key into the\n`LLM` / `MULTIMODAL` slots and your DeepInfra key into the `EMBEDDING` /\n`RERANK` slots.\n\n```bash\neveros init\n# or, from a source checkout:\ncp .env.example .env\n```\n\n`everos init` writes `./.env` by default. Use `everos init --xdg` to\nwrite `${XDG_CONFIG_HOME:-~/.config}/everos/.env` instead.\n\n### 4. Start EverOS\n\n```bash\neveros server start\n```\n\nKeep the server running, then open a second terminal and check it:\n\n```bash\ncurl http://127.0.0.1:8000/health\n```\n\nExpected response:\n\n```json\n{\"status\":\"ok\"}\n```\n\n`everos server start` searches for `.env` in this order: `--env-file \u003cpath\u003e` →\n`./.env` (cwd) → `${XDG_CONFIG_HOME:-~/.config}/everos/.env` → `~/.everos/.env`.\nThe endpoint stack is OpenAI-protocol compatible (OpenAI / OpenRouter / vLLM /\nOllama / DeepInfra) - override `*__BASE_URL` in the generated `.env` to point\nat any of them.\n\nNow make the demo real. In the second terminal, run:\n\n```bash\neveros demo --live\n```\n\nLive demo mode connects to the running server and performs the real\n`/health` -\u003e `/api/v1/memory/add` -\u003e `/api/v1/memory/flush` -\u003e\n`/api/v1/memory/search` flow before opening the same memory sphere UI. Use\n`--server-url \u003curl\u003e` if your server is not on `http://127.0.0.1:8000`.\n\n### 5. Try Your First Memory\n\nAdd a tiny conversation:\n\n```bash\nTS=$(($(date +%s)*1000))\n\ncurl -X POST http://127.0.0.1:8000/api/v1/memory/add \\\n  -H 'Content-Type: application/json' \\\n  -d \"{\n    \\\"session_id\\\": \\\"demo-001\\\",\n    \\\"app_id\\\": \\\"default\\\",\n    \\\"project_id\\\": \\\"default\\\",\n    \\\"messages\\\": [\n      {\\\"sender_id\\\": \\\"alice\\\", \\\"role\\\": \\\"user\\\", \\\"timestamp\\\": $TS, \\\"content\\\": \\\"I love climbing in Yosemite every spring.\\\"},\n      {\\\"sender_id\\\": \\\"alice\\\", \\\"role\\\": \\\"user\\\", \\\"timestamp\\\": $((TS+10000)), \\\"content\\\": \\\"My favorite coffee shop is Blue Bottle in SOMA.\\\"}\n    ]\n  }\"\n```\n\nForce extraction for the local demo:\n\n```bash\ncurl -X POST http://127.0.0.1:8000/api/v1/memory/flush \\\n  -H 'Content-Type: application/json' \\\n  -d '{\"session_id\":\"demo-001\",\"app_id\":\"default\",\"project_id\":\"default\"}'\n```\n\nSearch it back:\n\n```bash\ncurl -X POST http://127.0.0.1:8000/api/v1/memory/search \\\n  -H 'Content-Type: application/json' \\\n  -d '{\n    \"user_id\": \"alice\",\n    \"app_id\": \"default\",\n    \"project_id\": \"default\",\n    \"query\": \"Where do I like to climb?\",\n    \"top_k\": 5\n  }'\n```\n\nYou should see the Yosemite memory in the response. If the result is empty on\nthe first try, wait a moment and retry; Markdown is written synchronously, while\nthe local index catches up in the background.\n\n\u003e [!TIP]\n\u003e **First memory unlocked.**\n\u003e You just gave EverOS a fact, flushed it into durable Markdown-backed memory,\n\u003e and searched it back through the local index. That is the core loop.\n\u003e Want to see the source of truth? Open `~/.everos` and inspect the generated\n\u003e Markdown files.\n\nFor annotated responses and the Markdown files EverOS creates, see\n[QUICKSTART.md](QUICKSTART.md).\n\n### Optional: Ingest Multimodal Files\n\nTo ingest non-text content (image / pdf / audio / office documents)\nthrough `/api/v1/memory/add` `content` items, install the optional\nextra:\n\n```bash\nuv pip install 'everos[multimodal]'   # or: pip install 'everos[multimodal]'\n```\n\nThis pulls in `everalgo-parser` (with the `[svg]` bundle for SVG\nsupport via cairosvg) and wires up the multimodal LLM client\n(`EVEROS_MULTIMODAL__*` fields in `.env`, defaults to\n`google/gemini-3-flash-preview` via OpenRouter).\n\n**Office document support requires LibreOffice as a system dependency.**\nThe parser shells out to `soffice` (LibreOffice's headless renderer) to\nconvert `.doc` / `.docx` / `.ppt` / `.pptx` / `.xls` / `.xlsx` to PDF\nbefore feeding the result into the multimodal LLM. Without LibreOffice,\noffice uploads return HTTP 415 with a clear error message; PDF / image\n/ audio / HTML / email parsing is unaffected.\n\nInstall on the host before serving office documents:\n\n```bash\nbrew install --cask libreoffice              # macOS\nsudo apt-get install -y libreoffice          # Debian / Ubuntu\n```\n\n### For Contributors\n\n```bash\ngit clone https://github.com/EverMind-AI/EverOS.git\ncd EverOS\nuv sync                              # creates ./.venv and installs deps\nsource .venv/bin/activate            # or prefix commands with `uv run`\neveros demo --plain                  # try the local educational demo; no API keys needed\neveros init                          # paste OpenRouter + DeepInfra keys into .env\n\neveros --help\nmake test\n```\n\n\u003cbr\u003e\n\u003cdiv align=\"right\"\u003e\n\n[![](https://img.shields.io/badge/-Back_to_top-gray?style=flat-square)](#readme-top)\n\n\u003c/div\u003e\n\n## Use Cases\n\nNow that you have had your first successful EverOS moment, explore what people\nare building with persistent memory across agents, apps, and community\nintegrations.\n\nUse cases show what persistent memory makes possible in real products and\nworkflows. Some examples are packaged in this repository; others point to\nexternal demos or integrations you can study and adapt.\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/840470d7-a838-4c05-8685-dd797d4e9cdf)](https://evermind.ai/usecase_reunite)\n\n#### Reunite - Find With EverOS\n\nParents describe what they remember. Children describe what they recall. Reunite uses semantic memory to surface the connections.\n\n[Learn more](https://evermind.ai/usecase_reunite)\n\n\u003c/td\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/7282b38b-56bf-4356-aa7b-06a845e7683d)](https://github.com/tt-a1i/hive)\n\n#### Hive Orchestrator\n\nBrowser-native hive-mind for CLI coding agents - Claude Code, Codex, Gemini, and OpenCode collaborate as real PTY processes via a team protocol.\n\n[Code](https://github.com/tt-a1i/hive)\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/867d9329-ce9a-496f-ab1e-15c77974e5fa)](https://github.com/tt-a1i/evermemos-mcp)\n\n#### AI Coding Assistants With EverOS\n\nUniversal long-term memory layer for AI coding assistants, powered by EverOS.\n\n[Code](https://github.com/tt-a1i/evermemos-mcp)\n\n\u003c/td\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/a4f0fd86-1c81-4445-bebc-e51eb5e33b30)](https://github.com/yuansui123/AI-Data-Technician-EverMemOS)\n\n#### AI Data Technician\n\nAn agentic AI system that learns from scientist interaction to inspect, analyze, and classify high-dimensional time series data - with persistent memory that improves across sessions.\n\n[Code](https://github.com/yuansui123/AI-Data-Technician-EverMemOS)\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n![banner-gif](https://github.com/user-attachments/assets/650b901b-c9ba-4001-bac7-626b009df830)\n\n#### Rokid AI Assistant With EverOS\n\nConnect to EverOS within Rokid Glasses enabling long-term memory for all of your smart activities.\n\nComing soon\n\n\u003c/td\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n![banner-gif](https://github.com/user-attachments/assets/85b338b2-e48e-4a65-9f30-0bc6998df872)\n\n#### Creative Assistant With Memory\n\nCreative assistant with long-term memory, so your creative context stays available across sessions.\n\nComing soon\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr\u003e\n\u003ctd colspan=\"2\" align=\"right\"\u003e\n\u003ca href=\"#readme-top\"\u003e\u003cimg src=\"https://img.shields.io/badge/-Back_to_top-gray?style=flat-square\" alt=\"Back to top\"\u003e\u003c/a\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/f30617a1-adc0-4271-bc0e-c3a0b28cb903)](https://github.com/xunyud/Earth-Online)\n\n#### Earth Online Memory Game\n\nEarth Online is a memory-aware productivity game that turns everyday planning into a living quest log.\n\n[Code](https://github.com/xunyud/Earth-Online)\n\n\u003c/td\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/57d8cda7-35a5-4561-b794-5520dffc917b)](https://github.com/golutra/golutra)\n\n#### Multi-Agent Orchestration Platform\n\nGolutra presents a multi-agent workforce for engineering teams, extending the IDE model from a single assistant to coordinated agents.\n\n[Code](https://github.com/golutra/golutra)\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/75f19db5-30f6-4eed-9b1e-c9c6a0e6b7de)](https://github.com/Yangtze-Seventh/taste-verse)\n\n#### Your Personal Tasting Universe\n\nRecord, visualize, and explore your tasting journey through an immersive 3D star map.\n\n[Code](https://github.com/Yangtze-Seventh/taste-verse)\n\n\u003c/td\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/93ac2a68-4f18-4fcb-8d87-80aeb00a9d7c)](https://github.com/kellyvv/OpenHer)\n\n#### EverOS Open Her\n\nBuild AI that feels. Open-source persona engine - personality emerges from neural drives, not prompts. Inspired by Her.\n\n[Code](https://github.com/kellyvv/OpenHer)\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/550071c1-dc39-4964-9f67-ffdfad792345)](https://chromewebstore.google.com/detail/ruminer-browser-agent/lbccjohfpdpimbhpckljimgolndfmfif)\n\n#### Browser Agent For Personal Memory\n\nRuminer brings persistent memory to a browser agent so it can carry personal context across web tasks.\n\n[Plugin](https://chromewebstore.google.com/detail/ruminer-browser-agent/lbccjohfpdpimbhpckljimgolndfmfif)\n\n\u003c/td\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/c258a6c4-fe70-497a-98d1-3dade4a932f6)](https://github.com/nanxingw/EverMem)\n\n#### EverMem Sync With EverOS\n\nOne command to connect any AI coding CLI to EverMemOS long-term memory.\n\n[Code](https://github.com/nanxingw/EverMem)\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr\u003e\n\u003ctd colspan=\"2\" align=\"right\"\u003e\n\u003ca href=\"#readme-top\"\u003e\u003cimg src=\"https://img.shields.io/badge/-Back_to_top-gray?style=flat-square\" alt=\"Back to top\"\u003e\u003c/a\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/39274473-ceb3-48fb-a031-e22230decbe2)](https://github.com/mco-org/mco)\n\n#### MCO - Orchestrate AI Coding Agents\n\nMCO equips your primary agent with an agent team that can work together to solve complex tasks.\n\n[Code](https://github.com/mco-org/mco)\n\n\u003c/td\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/314c9126-8e08-4688-bbbb-8555ad58cf67)](https://github.com/onenewborn/StudyBuddy-public)\n\n#### Study Buddy With Self-Evolving Memory\n\nStudy proactively with an agent that has self-evolving memory.\n\n[Code](https://github.com/onenewborn/StudyBuddy-public)\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/21da76aa-9a8b-48e0-9134-42429d7390e7)](https://github.com/TonyLiangDesign/MemoCare)\n\n#### Alzheimer's Memory Assistant\n\nEmpowering individuals with advanced memory support and daily assistance.\n\n[Code](https://github.com/TonyLiangDesign/MemoCare)\n\n\u003c/td\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/e2428df3-ea11-4e88-8f9c-dad437dd8998)](https://github.com/AlexL1024/NeuralConnect)\n\n#### Memory-Driven Multi-Agent NPC Experience\n\nAn iOS sci-fi mystery game where players explore and uncover the truth.\n\n[Code](https://github.com/AlexL1024/NeuralConnect)\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/e6eaf308-a874-483f-8874-6934bf95a78f)](https://github.com/elontusk5219-prog/Mobi)\n\n#### Mobi Companion\n\nAn iOS app where users create, nurture, and live with a personalized AI companion called Mobi.\n\n[Code](https://github.com/elontusk5219-prog/Mobi)\n\n\u003c/td\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/9aabcaa9-f97a-49d2-9109-0b5bb696ed41)](https://github.com/JaMesLiMers/EvermemCompetition-Spiro)\n\n#### AI Wearable With Memory\n\nA context-native AI wearable that listens to everyday life and converts conversations into memory.\n\n[Code](https://github.com/JaMesLiMers/EvermemCompetition-Spiro)\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr\u003e\n\u003ctd colspan=\"2\" align=\"right\"\u003e\n\u003ca href=\"#readme-top\"\u003e\u003cimg src=\"https://img.shields.io/badge/-Back_to_top-gray?style=flat-square\" alt=\"Back to top\"\u003e\u003c/a\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/df9677ec-386f-4c56-a428-08bca25c54dc)](docs/migration-to-1.0.0.md)\n\n#### Legacy OpenClaw Agent Memory\n\nArchived pre-1.0.0 plugin reference. New integrations should use the current EverOS API.\n\n[Learn more](docs/migration-to-1.0.0.md)\n\n\u003c/td\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/3a2357a1-c0c3-464a-8979-0d1cdfc9b0d4)](https://github.com/TEN-framework/ten-framework/tree/04cb80601374fa9e35b4e544b2dbd23286ca7763/ai_agents/agents/examples/voice-assistant-with-EverMemOS)\n\n#### Live2D Character With Memory\n\nAdd long-term memory to a real-time Live2D character, powered by [TEN Framework](https://github.com/TEN-framework/ten-framework).\n\n[Code](https://github.com/TEN-framework/ten-framework/tree/04cb80601374fa9e35b4e544b2dbd23286ca7763/ai_agents/agents/examples/voice-assistant-with-EverMemOS)\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/c36bdc04-97d3-4fe9-97d9-4b93b475595a)](https://screenshot-analysis-vercel.vercel.app/)\n\n#### Computer-Use With Memory\n\nRun screenshot-based analysis with computer-use and store the results in memory.\n\n[Live Demo](https://screenshot-analysis-vercel.vercel.app/)\n\n\u003c/td\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/54a7cf8f-62c4-4fbc-9d50-b214d034e051)](use-cases/game-of-throne-demo)\n\n#### Game Of Thrones Memories\n\nA demonstration of AI memory infrastructure through an interactive Q\u0026A experience with *A Game of Thrones*.\n\n[Code](use-cases/game-of-throne-demo)\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/af37c1f6-7ba5-430c-b99d-2a7e7eac618f)](use-cases/claude-code-plugin)\n\n#### Claude Code Plugin\n\nPersistent memory for Claude Code. Automatically saves and recalls context from past coding sessions.\n\n[Code](use-cases/claude-code-plugin)\n\n\u003c/td\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n[![banner-gif](https://github.com/user-attachments/assets/d521d28c-0ccd-44ff-aecc-828245e2f973)](https://main.d2j21qxnymu6wl.amplifyapp.com/graph.html)\n\n#### Memory Graph Visualization\n\nExplore stored entities and relationships in a graph interface. Frontend demo; backend integration is in progress.\n\n[Live Demo](https://main.d2j21qxnymu6wl.amplifyapp.com/graph.html)\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n\u003cbr\u003e\n\u003cdiv align=\"right\"\u003e\n\n[![](https://img.shields.io/badge/-Back_to_top-gray?style=flat-square)](#readme-top)\n\n\u003c/div\u003e\n\n## Documentation\n\n- [docs/everos-demo.md](docs/everos-demo.md) — Demo scope and TUI source layout\n- [docs/how-memory-works.md](docs/how-memory-works.md) — Markdown, SQLite, LanceDB, and recall flow\n- [docs/use-cases.md](docs/use-cases.md) — Full use-case gallery and integration examples\n- [docs/engineering.md](docs/engineering.md) — Contributor engineering reference: build, test, CI, conventions\n- [docs/migration-to-1.0.0.md](docs/migration-to-1.0.0.md) — Legacy API migration notes\n- [CHANGELOG.md](CHANGELOG.md) — Release notes\n- [CONTRIBUTING.md](CONTRIBUTING.md) — How to contribute\n\n\u003cbr\u003e\n\u003cdiv align=\"right\"\u003e\n\n[![](https://img.shields.io/badge/-Back_to_top-gray?style=flat-square)](#readme-top)\n\n\u003c/div\u003e\n\n## Star Us\n\nIf EverOS is useful to your agent stack, please star the repo. It helps more\nbuilders discover the project and gives the memory ecosystem a stronger signal\nto keep improving.\n\n### Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=EverMind-AI/EverOS\u0026type=Date)](https://www.star-history.com/#EverMind-AI/EverOS\u0026Date)\n\n\u003cbr\u003e\n\u003cdiv align=\"right\"\u003e\n\n[![](https://img.shields.io/badge/-Back_to_top-gray?style=flat-square)](#readme-top)\n\n\u003c/div\u003e\n\n## EverMind Ecosystems\n\nEverMind is an open-source ecosystem for long-term memory, self-evolving\nagents, AI-native interfaces, and memory evaluation.\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003cth colspan=\"2\"\u003eEverMind Open-Source Ecosystem\u003c/th\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eMemory Runtime\u003c/strong\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ca href=\"https://github.com/EverMind-AI/EverOS\"\u003eEverOS\u003c/a\u003e - the local memory operating system and research-backed runtime for agent and user memory.\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eSelf-Improving Agent Harness\u003c/strong\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ca href=\"https://github.com/EverMind-AI/Raven\"\u003eRaven\u003c/a\u003e - the self-improving agent harness that brings memory, proactivity, context control, and skill evolution into terminal-native agents.\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eAlgorithm Engine\u003c/strong\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ca href=\"https://github.com/EverMind-AI/EverAlgo\"\u003eEverAlgo\u003c/a\u003e - stateless extraction, ranking, parsing, and memory operators that power EverOS.\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eHypergraph Memory\u003c/strong\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ca href=\"https://github.com/EverMind-AI/HyperMem\"\u003eHyperMem\u003c/a\u003e - hypergraph memory for long-term conversations, with its own benchmark-backed topic -\u003e episode -\u003e fact retrieval method.\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eBenchmarks\u003c/strong\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ca href=\"https://github.com/EverMind-AI/EverMemBench\"\u003eEverMemBench\u003c/a\u003e · \u003ca href=\"https://github.com/EverMind-AI/EvoAgentBench\"\u003eEvoAgentBench\u003c/a\u003e - evaluation suites for conversational memory and agent self-evolution.\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eLong-Context Research\u003c/strong\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ca href=\"https://github.com/EverMind-AI/MSA\"\u003eMSA\u003c/a\u003e - Memory Sparse Attention for scalable latent memory and 100M-token contexts.\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003ePersonal Memory Layer\u003c/strong\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ca href=\"https://github.com/EverMind-AI/EverMe\"\u003eEverMe\u003c/a\u003e - CLI and agent plugin suite for cross-device, cross-agent personal memory.\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cstrong\u003eDeveloper Integrations\u003c/strong\u003e\u003c/td\u003e\n\u003ctd\u003e\u003ca href=\"https://github.com/EverMind-AI/evermem-claude-code\"\u003eevermem-claude-code\u003c/a\u003e · \u003ca href=\"https://github.com/EverMind-AI/everos-plugins\"\u003eeveros-plugins\u003c/a\u003e - plugins, skills, and migration tooling for AI coding agents.\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\nTogether, these repositories form EverMind's research-to-runtime stack: new memory methods, reusable algorithms, benchmark evidence, and practical agent integrations.\n\n\u003cbr\u003e\n\u003cdiv align=\"right\"\u003e\n\n[![](https://img.shields.io/badge/-Back_to_top-gray?style=flat-square)](#readme-top)\n\n\u003c/div\u003e\n\n\u003cbr\u003e\n\n## Contributing\n\nContributions are welcome across the whole repository: memory methods, benchmark coverage, use-case examples, documentation, and bug fixes. Browse [Issues](https://github.com/EverMind-AI/EverOS/issues) to find a good entry point, then open a PR when you are ready.\n\n\u003cbr\u003e\n\n\u003e [!TIP]\n\u003e\n\u003e **Welcome all kinds of contributions** 🎉\n\u003e\n\u003e Help make EverOS better. Code, documentation, benchmark reports, use-case write-ups, and integration examples are all valuable. Share your projects on social media to inspire others.\n\u003e\n\u003e Connect with one of the EverOS maintainers [@elliotchen200](https://x.com/elliotchen200) on 𝕏 or [@cyfyifanchen](https://github.com/cyfyifanchen) on GitHub for project updates, discussions, and collaboration opportunities.\n\n![divider](https://github.com/user-attachments/assets/2e2bbcc6-e6d8-4227-83c6-0620fc96f761#gh-light-mode-only)\n![divider](https://github.com/user-attachments/assets/d57fad08-4f49-4a1c-bdfc-f659a5d86150#gh-dark-mode-only)\n\n### Code Contributors\n\n[![EverOS Contributors](https://contrib.rocks/image?repo=EverMind-AI/EverOS)](https://github.com/EverMind-AI/EverOS/graphs/contributors)\n\n![divider](https://github.com/user-attachments/assets/2e2bbcc6-e6d8-4227-83c6-0620fc96f761#gh-light-mode-only)\n![divider](https://github.com/user-attachments/assets/d57fad08-4f49-4a1c-bdfc-f659a5d86150#gh-dark-mode-only)\n\n### License\n\n[Apache License 2.0](LICENSE) — see [NOTICE](NOTICE) for third-party attributions.\n\n### Citation\n\nIf you use EverOS in research, see [CITATION.md](CITATION.md).\n\n\u003cbr\u003e\n\n\u003cdiv align=\"right\"\u003e\n\n[![](https://img.shields.io/badge/-Back_to_top-gray?style=flat-square)](#readme-top)\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fevermind-ai%2Feveros","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fevermind-ai%2Feveros","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fevermind-ai%2Feveros/lists"}