diff --git a/README.md b/README.md index 933031c1..a51f2f75 100644 --- a/README.md +++ b/README.md @@ -25,7 +25,7 @@ - [Quick Start](#quick-start) - [Use Cases](#use-cases) - [Documentation](#documentation) -- [EverMind Ecosystems](#evermind-ecosystems) +- [EverMind Ecosystem](#evermind-ecosystem) - [Contributing](#contributing)
@@ -641,50 +641,78 @@ Explore stored entities and relationships in a graph interface. Frontend demo; b -## EverMind Ecosystems +## EverMind Ecosystem -EverMind is an open-source ecosystem for long-term memory, self-evolving -agents, AI-native interfaces, and memory evaluation. +EverMind connects memory research, production-ready products, and practical +integrations into one open-source ecosystem. - + - - + + - - + + - - + + - - + - - + + - - + + - - + + - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
EverMind Open-Source EcosystemProducts
Memory RuntimeEverOS - the local memory operating system and research-backed runtime for agent and user memory.EverOSA local-first, Markdown-native long-term memory runtime for agents and users.
Self-Improving Agent HarnessRaven - the self-improving agent harness that brings memory, proactivity, context control, and skill evolution into terminal-native agents.RavenA memory-first, self-improving agent harness with proactivity, context control, and skill evolution.
Algorithm EngineEverAlgo - stateless extraction, ranking, parsing, and memory operators that power EverOS.EverMe (CLI)A CLI and agent plugin suite for cross-device, cross-agent personal memory.
Hypergraph MemoryHyperMem - hypergraph memory for long-term conversations, with its own benchmark-backed topic -> episode -> fact retrieval method.Research & Evaluation
BenchmarksEverMemBench · EvoAgentBench - evaluation suites for conversational memory and agent self-evolution.SkillCorpusCurated, retrieval-ready agent skill corpora with retrieval and evaluation tooling.
Long-Context ResearchMSA - Memory Sparse Attention for scalable latent memory and 100M-token contexts.EverAlgoStateless extraction, ranking, parsing, and memory operators that power EverOS.
Personal Memory LayerEverMe - CLI and agent plugin suite for cross-device, cross-agent personal memory.HyperMemHypergraph-based hierarchical memory for coarse-to-fine long-term conversation retrieval.
Developer Integrationsevermem-claude-code · everos-plugins - plugins, skills, and migration tooling for AI coding agents.MSAMemory Sparse Attention for scalable latent memory and 100M-token contexts.
EverMemBenchEvaluation of factual recall, applied reasoning, and personalized generalization in memory systems.
EvoAgentBenchLongitudinal evaluation of agent self-evolution, transfer efficiency, error avoidance, and skill use.
Integrations
OpenClawOpenClaw plugin for automatic recall, capture, and session-memory lifecycle management.
Hermes AgentHermes plugin for persistent memory across Hermes sessions.
DeepSeek HarnessDSH plugin for memory-aware DeepSeek Harness agents.
DifySelf-hosted and cloud tools for explicit memory search and storage in workflows and agents.
-Together, these repositories form EverMind's research-to-runtime stack: new memory methods, reusable algorithms, benchmark evidence, and practical agent integrations. +Together, these projects form EverMind's research-to-runtime stack: methods +and benchmarks become reusable memory infrastructure, products, and agent +integrations.
diff --git a/README.zh-CN.md b/README.zh-CN.md index c1d3ea18..45d599ef 100644 --- a/README.zh-CN.md +++ b/README.zh-CN.md @@ -642,48 +642,74 @@ Claude Code 的持久记忆插件。自动保存并回忆过去 coding sessions ## EverMind 生态 -EverMind 是一个面向长期记忆、自进化 Agent、AI-native interfaces 和记忆评测的开源生态。 +EverMind 将记忆研究、可直接使用的产品与实际集成连接为一个开源生态。 - + - - + + - - + + - - + + - - + - - + + - - + + - - + + - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
EverMind 开源生态产品
Memory RuntimeEverOS - 本地记忆操作系统，以及有研究支撑的 Agent 和用户记忆 runtime。EverOS本地优先、Markdown 原生的 Agent 与用户长期记忆运行时。
Self-Improving Agent HarnessRaven - The Self-Improving Agent Harness，把记忆、主动性、上下文控制和 skill evolution 带进终端原生 Agent。Raven以记忆为核心的自进化 Agent Harness，具备主动性、上下文控制与 Skill 进化能力。
算法引擎EverAlgo - stateless extraction、ranking、parsing 和 memory operators，为 EverOS 提供算法能力。EverMe（CLI）面向跨设备、跨 Agent 个人记忆的 CLI 与 Agent 插件套件。
Hypergraph MemoryHyperMem - 面向长期对话的 hypergraph memory，拥有独立的 benchmark-backed topic -> episode -> fact 检索方法。研究与评测
BenchmarksEverMemBench · EvoAgentBench - conversational memory 和 Agent self-evolution 的评测套件。SkillCorpus将分散的 Agent Skill 整理为可检索语料库，并提供检索与评测工具。
Long-Context ResearchMSA - Memory Sparse Attention，用于可扩展 latent memory 和 100M-token contexts。EverAlgo为 EverOS 提供无状态的提取、排序、解析与记忆算法。
个人记忆层EverMe - CLI 和 Agent plugin suite，用于跨设备、跨 Agent 的个人记忆。HyperMem基于超图的分层记忆架构，用于由粗到细的长期对话检索。
开发者集成evermem-claude-code · everos-plugins - AI coding agents 的 plugins、skills 和 migration tooling。MSA面向可扩展潜在记忆与一亿 Token 上下文的 Memory Sparse Attention。
EverMemBench从事实召回、应用推理和个性化泛化三个层面评测记忆系统。
EvoAgentBench纵向评测 Agent 自进化、迁移效率、错误规避和 Skill 使用能力。
插件与集成
OpenClawOpenClaw 插件，自动管理召回、写入与会话记忆生命周期。
Hermes AgentHermes 插件，为 Hermes 会话提供持久记忆。
DeepSeek HarnessDSH 插件，让 DeepSeek Harness Agent 使用长期记忆。
Dify本地版与云端版工具，在工作流和 Agent 中显式搜索与写入记忆。
-这些仓库共同构成 EverMind 的 research-to-runtime stack：新的记忆方法、 -可复用算法、benchmark evidence，以及可落地的 Agent 集成。 +这些项目共同构成 EverMind 从研究到运行时的完整链路：将方法与评测转化为 +可复用的记忆基础设施、产品和 Agent 集成。