From 42e90a419da4bfb28a671d59dcfcafb963f4d646 Mon Sep 17 00:00:00 2001 From: Elliot Chen Date: Sat, 9 May 2026 11:20:06 +0800 Subject: [PATCH 1/2] docs: restructure README and add subdirectory guides Move the directory tree from the main README to new dedicated README files for each top-level folder (use-cases, methods, benchmarks). Add detailed introductions and tables to guide users to the appropriate subprojects. This improves navigation and provides clear entry points for different use cases. --- README.md | 16 ---------------- benchmarks/README.md | 16 ++++++++++++++++ methods/EverCore/README.md | 31 +++++++++++++++++++++++++++++++ methods/README.md | 16 ++++++++++++++++ use-cases/README.md | 12 +++++++++++- 5 files changed, 74 insertions(+), 17 deletions(-) create mode 100644 benchmarks/README.md create mode 100644 methods/EverCore/README.md create mode 100644 methods/README.md diff --git a/README.md b/README.md index ce97d6da..6799e48e 100644 --- a/README.md +++ b/README.md @@ -53,22 +53,6 @@ At the center of EverOS is **EverCore**, a long-term memory operating system for agents. If you are new to the project, scan the use cases first to see what memory enables, then follow the [Quick Start](#quick-start) to run EverCore locally. The architecture and benchmark sections below give you the deeper reference material when you are ready to compare systems or reproduce results. -``` -EverOS/ -├── benchmarks/ -│ ├── EverMemBench/ -│ └── EvoAgentBench/ -├── methods/ -│ ├── EverCore/ -│ └── HyperMem/ -└── use-cases/ - ├── claude-code-plugin/ - ├── game-of-throne-demo/ - ├── openher/ - ├── ... - └── ... -``` -
## Use Cases diff --git a/benchmarks/README.md b/benchmarks/README.md new file mode 100644 index 00000000..27a28d07 --- /dev/null +++ b/benchmarks/README.md @@ -0,0 +1,16 @@ +# Benchmarks + +This folder contains the evaluation suites used by EverOS to measure memory quality and agent self-evolution. Use these benchmarks to reproduce reported results, compare memory systems, or evaluate new agent learning methods. + +## Included Benchmarks + +| Benchmark | What it measures | Start here | +| :--- | :--- | :--- | +| **EverMemBench** | Long-term memory quality in multi-person group conversations, including factual recall, applied reasoning, and personalized generalization. | [EverMemBench/](EverMemBench/) | +| **EvoAgentBench** | Agent self-evolution across information retrieval, reasoning, software engineering, code implementation, and knowledge-work tasks. | [EvoAgentBench/](EvoAgentBench/) | + +## How to Use This Folder + +- Start with [EverMemBench/](EverMemBench/) to evaluate memory retrieval and answer quality. +- Start with [EvoAgentBench/](EvoAgentBench/) to evaluate whether agents improve from past experience. +- Use the top-level [Benchmarks](../README.md#benchmarks) and [Evaluation](../README.md#evaluation) sections for the project-level benchmark overview. diff --git a/methods/EverCore/README.md b/methods/EverCore/README.md new file mode 100644 index 00000000..f90fef06 --- /dev/null +++ b/methods/EverCore/README.md @@ -0,0 +1,31 @@ +# EverCore + +EverCore is the long-term memory operating system at the center of EverOS. It extracts, structures, and retrieves durable knowledge from conversations so agents can remember across sessions and adapt over time. + +## Start Here + +| Goal | Link | +| :--- | :--- | +| Install and run EverCore locally | [Setup Guide](docs/installation/SETUP.md) | +| Browse the documentation index | [Documentation](docs/) | +| Try usage examples and demos | [Usage Examples](docs/usage/USAGE_EXAMPLES.md) | +| Review the architecture | [Architecture](docs/ARCHITECTURE.md) | +| Run evaluations | [Evaluation Guide](evaluation/) | + +## Quick Start + +```bash +docker compose up -d +uv sync +uv run python src/run.py +``` + +The server runs at `http://localhost:1995` by default. See the [full setup guide](docs/installation/SETUP.md) for environment variables, service configuration, and troubleshooting. + +## Folder Guide + +- [src/](src/) - application, memory, infrastructure, and API layers. +- [docs/](docs/) - setup, usage, architecture, API, and development documentation. +- [demo/](demo/) - interactive examples and memory extraction demos. +- [evaluation/](evaluation/) - benchmark runners and reports. +- [tests/](tests/) - unit and integration tests. diff --git a/methods/README.md b/methods/README.md new file mode 100644 index 00000000..84e954c3 --- /dev/null +++ b/methods/README.md @@ -0,0 +1,16 @@ +# Architecture Methods + +This folder contains the memory systems and algorithms included in EverOS. Use these projects as runnable systems, research references, or starting points for building an agent memory layer. + +## Included Methods + +| Method | What it is | Start here | +| :--- | :--- | :--- | +| **EverCore** | A long-term memory operating system for agents, with ingestion, structuring, retrieval, APIs, demos, and evaluation tooling. | [EverCore/](EverCore/) | +| **HyperMem** | A hypergraph-based hierarchical memory architecture for long-term conversations, organized around topic, episode, and fact layers. | [HyperMem/](HyperMem/) | + +## How to Use This Folder + +- Start with [EverCore/](EverCore/) if you want to run a memory system locally or integrate memory into an agent application. +- Start with [HyperMem/](HyperMem/) if you want to study or reproduce the hypergraph memory architecture. +- Use the top-level [Architecture Methods](../README.md#architecture-methods) section for a quick comparison of the methods. diff --git a/use-cases/README.md b/use-cases/README.md index d027bdc3..15a4ea75 100644 --- a/use-cases/README.md +++ b/use-cases/README.md @@ -1,6 +1,16 @@ # Use Cases -Community-contributed examples demonstrating EverMem integrations and applications. +This folder contains apps, demos, and integrations that show what persistent memory enables in real products and workflows. Some examples are complete local projects; others are focused integrations that can be adapted into your own agent stack. + +## Included Use Cases + +| Use case | What it shows | Start here | +| :--- | :--- | :--- | +| **Claude Code Plugin** | Persistent memory for Claude Code, including hooks, commands, local services, and memory recall. | [claude-code-plugin/](claude-code-plugin/) | +| **Game of Thrones Memories** | An interactive Q&A demo over long-form story memory. | [game-of-throne-demo/](game-of-throne-demo/) | +| **OpenHER** | Memory-oriented app and integration examples. | [openher/](openher/) | + +Use the top-level [Use Cases](../README.md#use-cases) section for the visual catalogue of demos and external integrations. ## Contributing Guidelines From eb0962af276d1677d20755272608da90dad1e9cb Mon Sep 17 00:00:00 2001 From: Elliot Chen Date: Sat, 9 May 2026 17:55:22 +0800 Subject: [PATCH 2/2] docs: expand showcase section with new projects and links Add six new project entries to the README showcase, each with a banner image, description, and code/plugin link. Also update an existing benchmark entry to include a dataset link. This enhances the repository's demonstration of real-world applications and available resources. --- README.md | 110 ++++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 107 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 6799e48e..d434cfcf 100644 --- a/README.md +++ b/README.md @@ -63,23 +63,127 @@ Use cases show what persistent memory makes possible in real products and workfl -![banner-gif](https://github.com/user-attachments/assets/9dcb3dd4-4402-45fa-ae13-e6782f42c7ea) +[![banner-gif](https://github.com/user-attachments/assets/f30617a1-adc0-4271-bc0e-c3a0b28cb903)](https://github.com/xunyud/Earth-Online) #### Earth Online Memory Game Earth Online is a memory-aware productivity game that turns everyday planning into a living quest log. +[Code](https://github.com/xunyud/Earth-Online) + -![banner-gif](https://github.com/user-attachments/assets/57d8cda7-35a5-4561-b794-5520dffc917b) +[![banner-gif](https://github.com/user-attachments/assets/57d8cda7-35a5-4561-b794-5520dffc917b)](https://github.com/golutra/golutra) #### Multi-Agent Orchestration Platform Golutra presents a multi-agent workforce for engineering teams, extending the IDE model from a single assistant to coordinated agents. +[Code](https://github.com/golutra/golutra) + + + + + + +[![banner-gif](https://github.com/user-attachments/assets/75f19db5-30f6-4eed-9b1e-c9c6a0e6b7de)](https://github.com/Yangtze-Seventh/taste-verse) + +#### Your Personal Tasting Universe + +Record, visualize, and explore your tasting journey through an immersive 3D star map. + +[Code](https://github.com/Yangtze-Seventh/taste-verse) + + + + +[![banner-gif](https://github.com/user-attachments/assets/93ac2a68-4f18-4fcb-8d87-80aeb00a9d7c)](https://github.com/kellyvv/OpenHer) + +#### EverOS Open Her + +Build AI that feels. Open-source persona engine — personality emerges from neural drives, not prompts. Inspired by Her. + +[Code](https://github.com/kellyvv/OpenHer) + + + + + + + +[![banner-gif](https://github.com/user-attachments/assets/550071c1-dc39-4964-9f67-ffdfad792345)](https://chromewebstore.google.com/detail/ruminer-browser-agent/lbccjohfpdpimbhpckljimgolndfmfif) + +#### Browser Agent for Personal Memory + +Earth Online is a memory-aware productivity game that turns everyday planning into a living quest log. + +[Plugin](https://chromewebstore.google.com/detail/ruminer-browser-agent/lbccjohfpdpimbhpckljimgolndfmfif) + + + + +[![banner-gif](https://github.com/user-attachments/assets/c258a6c4-fe70-497a-98d1-3dade4a932f6)](https://github.com/nanxingw/EverMem) + +#### EverMem Sync with EverOS + +One command to connect any AI coding CLI to EverMemOS long-term memory. + +[Code](https://github.com/nanxingw/EverMem) + + + + + +[![banner-gif](https://github.com/user-attachments/assets/39274473-ceb3-48fb-a031-e22230decbe2)](https://github.com/mco-org/mco) + +#### MCO - Orchestrate AI Coding Agents + +MCO equips your primary agent with an agent team that can work together to solve complex tasks. + +[Code](https://github.com/mco-org/mco) + + + + +[![banner-gif](https://github.com/user-attachments/assets/314c9126-8e08-4688-bbbb-8555ad58cf67)](https://github.com/onenewborn/StudyBuddy-public) + +#### Study Buddy with Self-Evolving Memory + +Study proactively with an agent that has self-evolving memory. + +[Code](https://github.com/onenewborn/StudyBuddy-public) + + + + + + + +[![banner-gif](https://github.com/user-attachments/assets/21da76aa-9a8b-48e0-9134-42429d7390e7)](https://github.com/TonyLiangDesign/MemoCare) + +#### Alzheimer’s Memory Assistant + +Empowering individuals with advanced memory support and daily assistance. + +[Code](https://github.com/TonyLiangDesign/MemoCare) + + + + +[![banner-gif](https://github.com/user-attachments/assets/e2428df3-ea11-4e88-8f9c-dad437dd8998)](https://github.com/AlexL1024/NeuralConnect) + +#### Memory-Driven Multi-Agent NPC Experience + +An iOS sci-fi mystery game where players explore and uncover the truth. + +[Code](https://github.com/AlexL1024/NeuralConnect) + + + + @@ -336,7 +440,7 @@ Three-layer memory quality evaluation: factual recall, applied reasoning, and pe Agent self-evolution evaluation through longitudinal growth curves, transfer efficiency, error avoidance, and skill-hit quality. -[Docs](benchmarks/EvoAgentBench/) +[Dataset](https://huggingface.co/datasets/EverMind-AI/EvoAgentBench) · [Docs](benchmarks/EvoAgentBench/)