MiroFish
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物
- 86k
- Python
- AGPL-3.0
- 5 wk ago
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Repo EverMind-AI/EverOS, read from GitHub 1 min ago. EverMind-AI has not joined Take My Repo.
EverMind-AI/EverOS is a public repo on GitHub by EverMind-AI. One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows. It declares the Apache-2.0 license on GitHub. It is written mainly in Python, has 13,958 stars and last changed on 2026-11-20. Nobody has reviewed it on Take My Repo yet, which says nothing about its quality. Read from GitHub on 2026-11-21.
In the maintainer's words. Shown from GitHub; Take My Repo does not keep a copy.
Website · Documentation · Blog · 中文
EverOS is a Python library and local-first memory runtime for agents and makers. It gives one portable memory layer across coding assistants, apps, devices, and workflows from day one. It stores conversations, files, and agent trajectories as readable Markdown, then syncs local SQLite and LanceDB indexes for fast retrieval and self-evolving reuse.
| Title | EverOS | Other Agent Memory Libraries |
|---|---|---|
| Markdown source of truth | ✅ Canonical .md files that are readable, editable, diffable, and Git-versioned |
❌ Usually API, vector, graph, dashboard, or database state |
| Direct file editing | ✅ Edit .md files; cascade watcher syncs |
❌ Usually SDK, API, dashboard, or backend update paths |
| Local three-part stack | ✅ Markdown + SQLite + LanceDB; no MongoDB, Elasticsearch, or Redis required | ❌ Often depends on managed services, vector DBs, graph DBs, or server stacks |
| User + agent tracks | ✅ User episodes/profile and agent cases/skills are separate first-class surfaces |
❌ Usually centered on chat history, profiles, entities, facts, or retrieval records |
| Orthogonal retrieval | ✅ Search by user_id, agent_id, app_id, project_id, and session_id |
❌ Usually app, namespace, tenant, thread, or graph scoped |
| Knowledge Wiki | ✅ Editable, source-backed Markdown knowledge pages with taxonomy, CRUD APIs, and topic search | ❌ Usually separate from memory, trapped in a dashboard, or not tied back to source files |
| Reflection | ✅ Offline memory evolution that merges episode clusters and refines profiles and skills between sessions | ❌ Usually retrieval-only memory with little background consolidation or long-horizon improvement |
| Benchmark | Questions | Accuracy | Answer model |
|---|---|---|---|
| LoCoMo | 1,540 | 94.61%* | openai/gpt-4.1-mini |
| LongMemEval | 500 | 94.00% | google/gemini-3.6-flash |
| EverMemBench | 2,400 | 66.67% | google/gemini-3-flash-preview |
| SubtleMemory | 1,522 | 71.75% | openai/gpt-5.4 |
* Re-judged: the 99 questions whose gold answer the LoCoMo audit disputes are graded against its corrected answers.
On LoCoMo, hybrid search, which calls no LLM, returns in 0.27 s at the median.
Accuracy and search time across models and retrieval methods are in
benchmarks/locomo.md; how to reproduce every number is in
benchmarks/README.md.
EverOS adds durable memory to the agent and workflow platforms below—and comes built into Raven. Choose an integration to open its setup guide.
DeepSeek Harness |
Hermes |
OpenClaw |
Raven |
![]() Dify |
One OpenRouter API key is enough to start EverOS, write durable memories, and retrieve them with keyword search.
uv pip install everos
# or: pip install everosNo API key or server setup required—run one command to quickly experience how EverOS stores and recalls memory:
# If you installed EverOS as a package: everos demo # If you cloned or forked this repository and have not activated .venv: uv run everos demo
Enter something EverOS should remember, then ask a related question to watch the memory move through ingest -> extract -> index -> recall.
everos init
This creates ~/.everos/everos.toml and ~/.everos/ome.toml. Open
~/.everos/everos.toml; it comes pre-filled with a recommended model (see
Recommended models) and the OpenRouter URL, so replace
only the empty api_key:
[llm] model = "openai/gpt-4.1-mini" api_key = "<OPENROUTER_API_KEY>" base_url = "https://openrouter.ai/api/v1"
This is the smallest Tier 1 setup: memory add, flush, Markdown persistence, cascade indexing, and keyword search.
Use everos init --root <path> if you want a different memory root. Pass the
same --root <path> to subsequent commands.
everos server start
Keep the server running, then open a second terminal and check it:
curl http://127.0.0.1:8000/health
Look for "status":"ok". With this one-key setup, capabilities.embed and
capabilities.rerank remain false until you configure them.
Note
Business endpoints live under /api/v2. The older /api/v1 prefix still
resolves to the same handlers so existing integrations keep working, but it
is a legacy alias that may be removed in a future major release — write new
code against /api/v2.
Add a tiny conversation:
TS=$(($(date +%s)*1000)) curl -X POST http://127.0.0.1:8000/api/v2/memory/add \ -H 'Content-Type: application/json' \ -d "{ \"session_id\": \"demo-001\", \"app_id\": \"default\", \"project_id\": \"default\", \"messages\": [ {\"sender_id\": \"alice\", \"role\": \"user\", \"timestamp\": $TS, \"content\": \"I love climbing in Yosemite every spring.\"}, {\"sender_id\": \"alice\", \"role\": \"user\", \"timestamp\": $((TS+10000)), \"content\": \"My favorite coffee shop is Blue Bottle in SOMA.\"} ] }"
Flush the memory at the end of the session:
curl -X POST http://127.0.0.1:8000/api/v2/memory/flush \ -H 'Content-Type: application/json' \ -d '{"session_id":"demo-001","app_id":"default","project_id":"default"}'
Search it back:
curl -X POST http://127.0.0.1:8000/api/v2/memory/search \ -H 'Content-Type: application/json' \ -d '{ "user_id": "alice", "app_id": "default", "project_id": "default", "query": "Where do I like to climb?", "method": "keyword", "top_k": 5 }'
You should see the Yosemite memory in the response. Keep
"method": "keyword" in this one-key setup because the API defaults to hybrid
search, which requires an embedding provider.
Tip
First memory unlocked.
You just gave EverOS a fact, flushed it into durable Markdown-backed memory,
and searched it back through the local index. That is the core loop.
Want to see the source of truth? Open ~/.everos and inspect the generated
Markdown files.
For annotated responses and the Markdown files EverOS creates, see QUICKSTART.md.
The OpenRouter one-key setup is EverOS Tier 1. It supports server startup, memory add and flush, durable Markdown storage, cascade indexing, and keyword search. Add optional providers only when you need the features below:
| Configuration | Adds |
|---|---|
[llm] only |
Core memory flow and keyword search |
Add [embedding] |
Vector/user hybrid search, reflection, and skill extraction |
Add [rerank] too |
Agentic search, default agent hybrid search, and Knowledge Wiki |
Add [multimodal] and parser extra |
Image, PDF, audio, and office-file ingestion |
Missing optional capabilities are reported by /health and return a clear
HTTP 422 if you request a feature that needs them.
Note
everos demo --live is different from the standalone demo in step 2: it
connects to a running server and uses the real add/flush/search flow. It uses
hybrid search, so add an embedding provider before you run it.
The generated everos.toml pre-fills these (all but the decider); any
OpenAI-compatible model can replace them.
| Role | Section | Recommended model |
|---|---|---|
| Memory extraction | [llm] |
openai/gpt-4.1-mini |
Retrieval decider for llm_multiround search |
[llm.decider] |
qwen3.6-27B or deepseek/deepseek-v4-flash-0731; left empty, the [llm] model decides |
| Embedding | [embedding] |
Qwen/Qwen3-Embedding-4B |
| Rerank | [rerank] |
Qwen/Qwen3-Reranker-4B |
| Multimodal parsing | [multimodal] |
google/gemini-3.8-flash |
The extraction model and the deciders above produced our published benchmark results; benchmarks/README.md lists which model ran in which role for each benchmark, and how to reproduce them. To choose other models, the LoCoMo results table compares accuracy and search time across models and retrieval methods.
To ingest non-text content (image / pdf / audio / office documents)
through /api/v2/memory/add content items, install the optional
extra:
uv pip install 'everos[multimodal]' # or: pip install 'everos[multimodal]'
This adds the parser's [svg] bundle for SVG support via cairosvg; the base
parser is already required by knowledge ingestion. Configure the [multimodal]
section in everos.toml; it comes pre-filled with the recommended model,
google/gemini-3.8-flash via OpenRouter.
Office document support requires LibreOffice as a system dependency.
The parser shells out to soffice (LibreOffice's headless renderer) to
convert .doc / .docx / .ppt / .pptx / .xls / .xlsx to PDF
before feeding the result into the multimodal LLM. Without LibreOffice,
office uploads return HTTP 415 with a clear error message; PDF / image
/ audio / HTML / email parsing is unaffected.
Install on the host before serving office documents:
brew install --cask libreoffice # macOS sudo apt-get install -y libreoffice # Debian / Ubuntu
git clone https://github.com/EverMind-AI/EverOS.git cd EverOS uv sync # creates ./.venv and installs deps uv run everos demo --plain # try the local educational demo; no API keys needed uv run everos init # add one OpenRouter key to ~/.everos/everos.toml uv run everos --help make test
Now that you have had your first successful EverOS moment, explore what people are building with persistent memory across agents, apps, and community integrations.
Use cases show what persistent memory makes possible in real products and workflows. Some examples are packaged in this repository; others point to external demos or integrations you can study and adapt.
AIUI Sports AgentsSports agents for smart glasses, covering running, cycling, and indoor rowing. AISmartRun includes an optional memory-backend contract for post-run summaries; connecting it to EverOS requires a separately configured backend. |
Reunite - Find With EverOSParents describe what they remember. Children describe what they recall. Reunite uses semantic memory to surface the connections. |
Hive OrchestratorBrowser-native hive-mind for CLI coding agents - Claude Code, Codex, Gemini, and OpenCode collaborate as real PTY processes via a team protocol. |
MCP Server for AI Coding AssistantsPlug EverOS memory into Claude Code, Codex, Claude Desktop or Cursor with |
AI Data TechnicianAn 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. |
Rokid AI Assistant With EverOSConnect to EverOS within Rokid Glasses enabling long-term memory for all of your smart activities. Coming soon |
Creative Assistant With MemoryCreative assistant with long-term memory, so your creative context stays available across sessions. Coming soon |
Earth Online Memory GameEarth Online is a memory-aware productivity game that turns everyday planning into a living quest log. |
Multi-Agent Orchestration PlatformGolutra presents a multi-agent workforce for engineering teams, extending the IDE model from a single assistant to coordinated agents. |
Your Personal Tasting UniverseRecord, visualize, and explore your tasting journey through an immersive 3D star map. |
EverOS Open HerBuild AI that feels. Open-source persona engine - personality emerges from neural drives, not prompts. Inspired by Her. |
Browser Agent For Personal MemoryRuminer brings persistent memory to a browser agent so it can carry personal context across web tasks. |
EverMem Sync With EverOSOne command to connect any AI coding CLI to EverOS (formerly called EverMemOS) for long-term memory. |
MCO - Orchestrate AI Coding AgentsMCO equips your primary agent with an agent team that can work together to solve complex tasks. |
Study Buddy With Self-Evolving MemoryStudy proactively with an agent that has self-evolving memory. |
Alzheimer's Memory AssistantEmpowering individuals with advanced memory support and daily assistance. |
Memory-Driven Multi-Agent NPC ExperienceAn iOS sci-fi mystery game where players explore and uncover the truth. |
Mobi CompanionAn iOS app where users create, nurture, and live with a personalized AI companion called Mobi. |
AI Wearable With MemoryA context-native AI wearable that listens to everyday life and converts conversations into memory. |
Legacy OpenClaw Agent MemoryArchived pre-1.0.0 plugin reference. New integrations should use the current EverOS API. |
Live2D Character With MemoryAdd long-term memory to a real-time Live2D character, powered by TEN Framework. |
Computer-Use With MemoryRun screenshot-based analysis with computer-use and store the results in memory. |
Game Of Thrones MemoriesA demonstration of AI memory infrastructure through an interactive Q&A experience with A Game of Thrones. |
Claude Code PluginPersistent memory for Claude Code. Automatically saves and recalls context from past coding sessions. |
Memory Graph VisualizationExplore stored entities and relationships in a graph interface. Frontend demo; backend integration is in progress. |
EverMind connects memory research, production-ready products, and practical integrations into one open-source ecosystem.
| Products | |
|---|---|
| EverOS | A local-first, Markdown-native long-term memory runtime for agents and users. |
| Raven | A memory-first, self-improving agent harness with proactivity, context control, and skill evolution. |
| EverMe (CLI) | A CLI and agent plugin suite for cross-device, cross-agent personal memory. |
| Research & Evaluation | |
| SkillCorpus | Curated, retrieval-ready agent skill corpora with retrieval and evaluation tooling. |
| EverAlgo | Stateless extraction, ranking, parsing, and memory operators that power EverOS. |
| HyperMem | Hypergraph-based hierarchical memory for coarse-to-fine long-term conversation retrieval. |
| MSA | Memory Sparse Attention for scalable latent memory and 100M-token contexts. |
| EverMemBench | Evaluation of factual recall, applied reasoning, and personalized generalization in memory systems. |
| EvoAgentBench | Longitudinal evaluation of agent self-evolution, transfer efficiency, error avoidance, and skill use. |
| Integrations | |
| OpenClaw | OpenClaw plugin for automatic recall, capture, and session-memory lifecycle management. |
| Hermes Agent | Hermes plugin for persistent memory across Hermes sessions. |
| DeepSeek Harness | DSH plugin for memory-aware DeepSeek Harness agents. |
| Dify | Self-hosted and cloud tools for explicit memory search and storage in workflows and agents. |
Together, these projects form EverMind's research-to-runtime stack: methods and benchmarks become reusable memory infrastructure, products, and agent integrations.
Contributions are welcome across the whole repository: memory methods, benchmark coverage, use-case examples, documentation, and bug fixes. Browse Issues to find a good entry point, then open a PR when you are ready.
Tip
Welcome all kinds of contributions 🎉
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.
Connect with one of the EverOS maintainers @ElliotChen on 𝕏 or @cyfyifanchen on GitHub for project updates, discussions, and collaboration opportunities.
Apache License 2.0 — see NOTICE for third-party attributions.
If you use EverOS in research, see CITATION.md.
EverMind-AI/EverOS is a public repo on GitHub by EverMind-AI. One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
It declares the Apache-2.0 license on GitHub.
Its maker has not tagged a system, so it is unknown here. Its README says what it needs.
Open "Take it" on its page: Take My Repo writes an install plan for your machine and hands it to your AI agent (Claude Code, Codex or Cursor), which asks you before each step. Take My Repo has not tested it on any machine.
Its last change on GitHub was on 2026-11-20. Take My Repo does not judge from that whether it is maintained.
Nobody has reviewed it on Take My Repo yet, which says nothing about its quality.
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞


The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
The Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.

Memory Sparse Attention - A scalable, end-to-end trainable latent-memory framework for 100M-token contexts.
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
Open-source CLI and Agent plugin suite for EverMe — cross-device, cross-Agent personal memory for AI Agents.
Persistent memory for Claude Code. Automatically saves and recalls context from past coding sessions.
Agent self-evolution evaluation — not static snapshots, but longitudinal growth curves. Measures transfer efficiency, error avoidance, and skill-hit quality through controlled experiments with and without evolution.
This page is also available as structured data, with the same sources and dates.
/api/v1/resources/gh/EverMind-AI/EverOSTake My Repo has not tested this on your machine. Requirements come from the project's own documentation.