diff --git a/README.md b/README.md index 667c2871..7ad6a72f 100644 --- a/README.md +++ b/README.md @@ -26,14 +26,19 @@ > [0.2.x](https://github.com/agentscope-ai/ReMe/tree/v0.2.0.6) · > [MemoryScope](https://github.com/agentscope-ai/ReMe/tree/memoryscope_branch) -🧠 ReMe is a memory management toolkit for **AI agents**. It turns conversations and resources into readable, editable, and searchable file-based long-term memory. +🧠 ReMe is a memory management toolkit for **AI agents**. It turns conversations and resources into readable, editable, +and searchable file-based long-term memory. ## ✨ Core Ideas -- **Memory as File**: Markdown files with frontmatter and wikilinks serve as memory nodes that both users and agents can read and write directly. -- **Self-evolving knowledge base**: Auto Memory, Auto Resource, and Auto Dream progressively transform conversations and resources into long-term Markdown memories, while automatically building wikilink relationships. -- **Progressive hybrid search**: ReMe combines wikilinks, BM25, and embeddings for hybrid retrieval across keyword matching, semantic recall, and relationship expansion. -- **Agent-friendly integration**: SKILL.md + CLI integration makes it easy for different agents to read, write, maintain, and reuse memory. +- **Memory as File**: Markdown files with frontmatter and wikilinks serve as memory nodes that both users and agents can + read and write directly. +- **Self-evolving knowledge base**: Auto Memory, Auto Resource, and Auto Dream progressively transform conversations and + resources into long-term memories, while automatically building wikilink relationships. +- **Progressive hybrid search**: ReMe combines wikilinks, BM25, and embeddings for hybrid retrieval across keyword + matching, semantic recall, and relationship expansion. +- **Agent-friendly integration**: SKILL.md + CLI integration makes it easy for different agents to read, write, + maintain, and reuse memory.

ReMe Design Philosophy @@ -44,12 +49,19 @@
-- **Personal assistants**: Provide long-term memory for agents such as [QwenPaw](https://github.com/agentscope-ai/QwenPaw). +- **Personal assistants**: Provide long-term memory for agents such + as [QwenPaw](https://github.com/agentscope-ai/QwenPaw). - **Coding assistants**: Preserve coding style, project background, and workflow experience across sessions. -- **Knowledge QA**: Progressively transform resources and conversations into a searchable, traceable, and linked Markdown knowledge base. -- **Task automation**: Reuse successful paths, lessons from failures, and operation procedures from past tasks. +- **Knowledge QA**: Progressively transform resources and conversations into a searchable, traceable, and linked + Markdown knowledge base. +- **Task automation**: Reuse successful paths, lessons from failures, and operating procedures from past tasks. + +## 📰 News + +- Our paper [Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution](https://aclanthology.org/2026.findings-acl.829/) has been accepted to Findings of ACL 2026. + ## 🚀 Quick Start ### Installation @@ -105,14 +117,45 @@ curl -s http://127.0.0.1:2333/version -H 'Content-Type: application/json' -d '{} ### Agent Integration -ReMe runs as a service and exposes its memory through CLI / MCP jobs. Agents adopt it in whatever way fits them — embedding ReMe directly in their own code, or installing it as a plugin — and wire `auto_memory` / `proactive` into their lifecycle so conversations are consolidated into memory and surfaced at the right time. Indexing (`auto_index`) and resource processing (`auto_resource`) run automatically via file watching, and `auto_dream` consolidates daily memories into long-term digests on a schedule. +ReMe runs as a service and exposes memory through CLI / MCP jobs. Agents can adopt it in whichever way fits them: deep +SDK integration, plugin integration, or a lightweight Skill + CLI integration. They can wire `auto_memory` / `proactive` +into their lifecycle so conversations are consolidated into memory and surfaced at the right time. Indexing ( +`auto_index`) and resource processing (`auto_resource`) run automatically through file watching, and `auto_dream` +consolidates daily memories into long-term digests on a schedule. + +

QwenPaw Auto Memory / Auto Dream demo

+ + + + + + + + + + +
Auto MemoryAuto Dream
+ QwenPaw Auto Memory demo + + QwenPaw Auto Dream demo +
Integration status across agents: -| Agent | Status | How it integrates | -|------------------------------------------------------------|----------------|-----------------------------------------------------------------------------------------------------------| -| [QwenPaw](https://github.com/agentscope-ai/QwenPaw) | ✅ Available | [Deep SDK integration](https://github.com/agentscope-ai/QwenPaw/blob/main/src/qwenpaw/agents/memory/reme_light_memory_manager.py) — embeds the ReMe app in-process and drives `search` / `auto_memory` / `auto_dream` jobs via `run_job`, reusing the agent's own model (no separate server). | -| [Claude Code](plugins/reme) | ✅ Available | Plugin: HTTP MCP server for recall, a `reme-memory` skill, and a Stop hook that records each session via `auto_memory_cc`. | +| Agent | Status | How it integrates | +|-----------------------------------------------------|-------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| [QwenPaw](https://github.com/agentscope-ai/QwenPaw) | ✅ Available | [Deep SDK integration](https://github.com/agentscope-ai/QwenPaw/blob/main/src/qwenpaw/agents/memory/reme_light_memory_manager.py) — embeds the ReMe app in-process, drives `search` / `auto_memory` / `auto_dream` jobs via `run_job`, and reuses the agent's own model (no separate server). | +| [Claude Code](plugins/reme) | ✅ Available | Plugin: HTTP MCP server for recall, a `reme-memory` skill, and a Stop hook that records each session via `auto_memory_cc`. | +| Other agents | ✅ Available | [Skill + CLI](skills/reme_memory/SKILL.md): install or copy the `reme_memory` skill, then call the `reme` CLI directly for health checks, search, read, write, and memory jobs. | + +Minimal CLI examples for Skill + CLI integration: + +```bash +reme version +reme health_check +reme search query="" limit=5 +reme auto_memory session_id="" messages='[{"role":"user","content":"..."},{"role":"assistant","content":"..."}]' +``` For more details, see the [Quick Start](docs/zh/quick_start.md). @@ -120,7 +163,8 @@ For more details, see the [Quick Start](docs/zh/quick_start.md). > Memory as File, File as Memory. -ReMe treats **memory as files**, progressively processing raw conversations and external resources from `session/` and `resource/` into `daily/`, then consolidating them into reusable long-term knowledge nodes under `digest/`. +ReMe treats **memory as files**, progressively processing raw conversations and external resources from `session/` and +`resource/` into `daily/`, then consolidating them into reusable long-term knowledge nodes under `digest/`. ### Directory Structure @@ -138,13 +182,16 @@ ReMe treats **memory as files**, progressively processing raw conversations and ├── daily/ # Lightly processed memory: daily facts, conversation summaries, resource readings │ ├── YYYY-MM-DD.md │ └── YYYY-MM-DD/ -│ ├── .md +│ ├── .md │ ├── .md │ └── interests.yaml └── digest/ # Long-term memory: personal facts, procedural experience, knowledge nodes ├── personal/ + │ └── {topic/event}.md ├── procedure/ + │ └── {topic/event}.md └── wiki/ + └── {topic/event}.md ```

@@ -153,84 +200,96 @@ ReMe treats **memory as files**, progressively processing raw conversations and ### Automatic Memory Flow -ReMe's automatic memory flow gradually turns raw conversations and resources into searchable, traceable, and reusable file-based memory. During normal operation, background watchers maintain indexes and process resources, agent hooks trigger conversation memory, and long-term consolidation plus proactive reminders run through scheduled tasks or on-demand calls. +ReMe's automatic memory flow gradually turns raw conversations and resources into searchable, traceable, and reusable +file-based memory. During normal operation, background watchers maintain indexes and process resources, agent hooks +trigger conversation memory, and long-term consolidation plus proactive reminders run through scheduled tasks or +on-demand calls.

Automatic Memory Capabilities
-| Capability | How it runs | Purpose | Main parameters | -|-----------------------------------------------|--------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------| -| [`auto_index`](docs/zh/memory_search.md) | Background maintenance via `index_update_loop` | Scans on startup and continuously watches Markdown/JSONL changes in `daily/`, `digest/`, and `resource/`; updates chunk, BM25, embedding, and wikilink graph indexes. | Config: `watch_dirs`, `watch_suffixes` | -| [`auto_memory`](docs/zh/auto_memory.md) | Agent after-reply hook; also callable on demand | Saves raw conversation text and turns long-term valuable information into `daily//.md` memory cards. | Required: `messages`; optional: `session_id`, `memory_hint` | -| [`auto_resource`](docs/zh/auto_resource.md) | Automatically triggered by resource watching; also callable on demand | Reads resource changes under `resource//` and creates or updates LLM-named daily resource cards linked by `source_resource`. | Required: `changes`; each item may include `path`, `file_path`, `change` | -| [`auto_dream`](docs/zh/auto_dream.md) | Scheduled by `dream_cron`; also callable on demand | Scans daily input for a given date, extracts long-term memory units, integrates them into `digest/`, and writes `daily//interests.yaml`. | `date`, `hint`, `topic_count`, `topic_diversity_days` | -| [`proactive`](docs/zh/proactive.md) | Read on demand before agent proactive reminders | Reads `interests.yaml` generated by `auto_dream` and exposes topics worth attention to the upper-level agent; the caller decides whether to remind the user. | `date`, `include_content` | +| Capability | How it runs | Purpose | Main parameters | +|---------------------------------------------|-----------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------| +| [`auto_index`](docs/zh/memory_search.md) | Background maintenance via `index_update_loop` | Scans on startup and continuously watches Markdown/JSONL changes in `daily/`, `digest/`, and `resource/`; updates chunk, BM25, embedding, and wikilink graph indexes. | Config: `watch_dirs`, `watch_suffixes` | +| [`auto_memory`](docs/zh/auto_memory.md) | Agent after-reply hook; also callable on demand | Saves raw conversation text and turns long-term valuable information into `daily//.md` memory cards. | Required: `messages`; optional: `session_id`, `memory_hint` | +| [`auto_resource`](docs/zh/auto_resource.md) | Automatically triggered by resource watching; also callable on demand | Reads resource changes under `resource//` and creates or updates LLM-named daily resource cards linked by `source_resource`. | Required: `changes`; each item may include `path`, `file_path`, `change` | +| [`auto_dream`](docs/zh/auto_dream.md) | Scheduled by `dream_cron`; also callable on demand | Scans daily input for a given date, extracts long-term memory units, integrates them into `digest/`, and writes `daily//interests.yaml`. | `date`, `hint`, `topic_count`, `topic_diversity_days` | +| [`proactive`](docs/zh/proactive.md) | Read on demand before agent proactive reminders | Reads `interests.yaml` generated by `auto_dream` and exposes topics worth attention to the upper-level agent; the caller decides whether to remind the user. | `date`, `include_content` |
- Memory as File + Memory as File - Auto Memory and Resource + Auto Memory and Resource
- Auto Dream and Proactive + Auto Dream and Proactive - Auto Index and Memory Search + Auto Index and Memory Search
-### Workspace Operation Interface +### ReMe Operations -ReMe operates the workspace through a unified CLI / Service Job interface. Agents usually only need retrieval, read, write, edit, and automatic memory commands. Lower-level indexing, frontmatter, and file operation commands are mainly for maintenance, debugging, or advanced integration. +ReMe operates the workspace through a unified CLI / Service Job interface. Agents usually only need retrieval, reading, +writing, editing, and automatic memory commands. Lower-level indexing, frontmatter, and file operation commands are +mainly for maintenance, debugging, or advanced integration.
-Workspace Operation Interface +ReMe Operations
-| Category | name | Description | Parameters | -|----------------|--------------------------------------|-----------------------------------------------------------------------------|--------------------------------------------------------| -| System status | `version` | Returns the ReMe package version. | None | -| System status | `health_check` | Returns a health-check summary for ReMe components. | None | -| System status | `help` | Lists registered jobs and their metadata. | None | -| Retrieval/read | [`search`](docs/zh/memory_search.md) | Performs hybrid retrieval in the workspace with vector recall, BM25, and RRF fusion. | Required: `query`; optional: `limit`, `min_score` | -| Retrieval/read | `node_search` | Recalls similar digest nodes by candidate abstraction name and description, mainly for `auto_dream` deduplication or association. | Required: `query`; optional: `limit` | -| Retrieval/read | `traverse` | Traverses the wikilink graph from a specified path. | Required: `path`; optional: `depth`, `direction` | -| Retrieval/read | `read` | Reads a Markdown file under the workspace. | Required: `path`; optional: `start_line`, `end_line` | -| Retrieval/read | `read_image` | Reads an image file under the workspace and returns base64. | Required: `path` | -| Index | `reindex` | Clears file-store indexes and rebuilds indexes from existing files. | Config: `watch_dirs`, `watch_suffixes` | -| Daily | `daily_list` | Lists notes for a day. | `date` | -| Daily | `daily_reindex` | Rebuilds the day-index page `daily/.md`. | `date` | -| Metadata | `frontmatter_read` | Reads file frontmatter. | Required: `path` | -| Metadata | `frontmatter_update` | Merges key-values into file frontmatter. | Required: `path`, `metadata` | -| Metadata | `frontmatter_delete` | Deletes specified keys from file frontmatter. | Required: `path`, `keys` | -| File operation | `stat` | Gets workspace path status, including size, mtime, existence, and file/directory type. | Required: `path` | -| File operation | `list` | Lists files under a workspace path. | `path`, `recursive`, `limit` | -| File operation | `write` | Creates or overwrites a Markdown file and writes name/description frontmatter. | Required: `path`, `name`, `description`, `content`; optional: `metadata` | -| File operation | `edit` | Performs full-text find-and-replace on a Markdown file. | Required: `path`, `old`, `new` | -| File operation | `move` | Moves or renames a workspace file and rewrites inbound wikilinks by default. | Required: `src_path`, `dst_path`; optional: `overwrite`, `retarget` | -| File operation | `delete` | Deletes a workspace file or folder and returns inbound wikilinks that still exist. | Required: `path` | +| Category | Command | Description | Parameters | +|----------------|-------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------| +| System status | `reme version` | Returns the ReMe package version. | None | +| System status | `reme health_check` | Returns a health-check summary for ReMe components. | None | +| System status | `reme help` | Lists registered jobs and their metadata. | None | +| Retrieval/read | [`reme search`](docs/zh/memory_search.md) | Performs hybrid retrieval in the workspace with vector recall, BM25, and RRF fusion. | Required: `query`; optional: `limit`, `min_score` | +| Retrieval/read | `reme node_search` | Recalls similar digest nodes by candidate abstraction name and description, mainly for `auto_dream` deduplication or association. | Required: `query`; optional: `limit` | +| Retrieval/read | `reme traverse` | Traverses the wikilink graph from a specified path. | Required: `path`; optional: `depth`, `direction` | +| Retrieval/read | `reme read` | Reads a Markdown file under the workspace. | Required: `path`; optional: `start_line`, `end_line` | +| Retrieval/read | `reme read_image` | Reads an image file under the workspace and returns base64. | Required: `path` | +| Index | `reme reindex` | Clears file-store indexes and rebuilds indexes from existing files. | Config: `watch_dirs`, `watch_suffixes` | +| Daily | `reme daily_list` | Lists notes for a day. | `date` | +| Daily | `reme daily_reindex` | Rebuilds the day-index page `daily/.md`. | `date` | +| Metadata | `reme frontmatter_read` | Reads file frontmatter. | Required: `path` | +| Metadata | `reme frontmatter_update` | Merges key-values into file frontmatter. | Required: `path`, `metadata` | +| Metadata | `reme frontmatter_delete` | Deletes specified keys from file frontmatter. | Required: `path`, `keys` | +| File operation | `reme stat` | Gets workspace path status, including size, mtime, existence, and file/directory type. | Required: `path` | +| File operation | `reme list` | Lists files under a workspace path. | `path`, `recursive`, `limit` | +| File operation | `reme write` | Creates or overwrites a Markdown file and writes name/description frontmatter. | Required: `path`, `name`, `description`, `content`; optional: `metadata` | +| File operation | `reme edit` | Performs full-text find-and-replace on a Markdown file. | Required: `path`, `old`, `new` | +| File operation | `reme move` | Moves or renames a workspace file and rewrites inbound wikilinks by default. | Required: `src_path`, `dst_path`; optional: `overwrite`, `retarget` | +| File operation | `reme delete` | Deletes a workspace file or folder and returns inbound wikilinks that still exist. | Required: `path` |
## 🤝 Community and Support -- **Issues and requests**: Check [Open Issues](https://github.com/agentscope-ai/ReMe/issues) first. If there is no related discussion, open a new issue with background, expected behavior, and impact scope. -- **Code contributions**: Before making changes, read the [contribution guide](docs/zh/contributing.md) and [code framework](docs/zh/framework.md), and follow the CLI / Service / Application / Job / Step / Component layering. -- **Documentation contributions**: For user-visible installation, configuration, invocation, or behavior changes, update `docs/zh/` or `README.md` accordingly. -- **Commit convention**: Conventional Commits are recommended, for example `feat(search): add link expansion option` or `docs(zh): update quick start`. -- **Pre-submit checks**: Before submitting a PR, try to run `pre-commit run --all-files` and `pytest`. If tests depending on LLMs, embeddings, or external services cannot run, explain that in the PR. -- **Get help**: Use [GitHub Issues](https://github.com/agentscope-ai/ReMe/issues) for bugs and feature requests. Project documentation is available at [https://reme.agentscope.io/](https://reme.agentscope.io/). +- **Issues and requests**: Check [Open Issues](https://github.com/agentscope-ai/ReMe/issues) first. If there is no + related discussion, open a new issue with background, expected behavior, and impact scope. +- **Code contributions**: Before making changes, read the [contribution guide](docs/zh/contributing.md) + and [code framework](docs/zh/framework.md), and follow the CLI / Service / Application / Job / Step / Component + layering. +- **Documentation contributions**: For user-visible installation, configuration, invocation, or behavior changes, update + `docs/zh/` or `README.md` accordingly. +- **Commit convention**: Conventional Commits are recommended, for example `feat(search): add link expansion option` or + `docs(zh): update quick start`. +- **Pre-submit checks**: Before submitting a PR, try to run `pre-commit run --all-files` and `pytest`. If tests that + depend on LLMs, embeddings, or external services cannot run, explain that in the PR. +- **Get help**: Use [GitHub Issues](https://github.com/agentscope-ai/ReMe/issues) for bugs and feature requests. Project + documentation is available at [https://reme.agentscope.io/](https://reme.agentscope.io/). ### Contributors @@ -249,6 +308,22 @@ Thanks to everyone who has contributed to ReMe: url = {https://reme.agentscope.io}, year = {2026} } + +@inproceedings{cao-etal-2026-remember, + title = "Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution", + author = "Cao, Zouying and + Deng, Jiaji and + Yu, Li and + Zhou, Weikang and + Liu, Zhaoyang and + Ding, Bolin and + Zhao, Hai", + booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026", + year = "2026", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2026.findings-acl.829/", + pages = "16803--16822" +} ``` ## ⚖️ License diff --git a/README_ZH.md b/README_ZH.md index 698fe7d3..79b20f99 100644 --- a/README_ZH.md +++ b/README_ZH.md @@ -31,7 +31,7 @@ ## ✨ 核心创新 - **Memory as File**：以带 frontmatter 和 wikilink 的 Markdown 作为记忆节点，让用户和 Agent 都能直接读写。 -- **自进化知识库**：通过 Auto Memory、Auto Resource 和 Auto Dream，把对话与资料逐步加工为长期 Markdown 记忆，并自动建立 wikilink 关系。 +- **自进化知识库**：通过 Auto Memory、Auto Resource 和 Auto Dream，把对话与资料逐步加工为长期记忆，并自动建立 wikilink 关系。 - **渐进式混合搜索**：融合 wikilink、BM25 和 embedding，支持从关键词匹配到语义召回、关系扩展的混合检索。 - **Agent 友好集成**：通过 SKILL.md + CLI 接入，方便不同 Agent 读写、维护与复用记忆。 @@ -43,12 +43,21 @@ 适用场景
+ - **个人助理**：为 [QwenPaw](https://github.com/agentscope-ai/QwenPaw) 等 Agent 提供长期记忆。 - **编程助手**：沉淀代码风格、项目背景和流程经验，跨会话保持一致。 - **知识问答**：把资料和对话渐进加工成可检索、可追溯、可链接的 Markdown 知识库。 - **任务自动化**：复用历史任务中的成功路径、失败教训和操作流程。 + +## 📰 新闻 + +- + +我们的论文 [Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution](https://aclanthology.org/2026.findings-acl.829/) +已被 Findings of ACL 2026 接收。 + ## 🚀 快速开始 ### 安装 @@ -104,14 +113,43 @@ curl -s http://127.0.0.1:2333/version -H 'Content-Type: application/json' -d '{} ### 快速接入 -ReMe 以服务形式运行，通过 CLI / MCP job 对外暴露记忆。各 Agent 按各自合适的方式接入——可以把 ReMe 直接嵌进自己的代码,也可以作为 plugin 安装——并把 `auto_memory` / `proactive` 接入自身生命周期,让对话沉淀为记忆并在合适时机浮现。索引(`auto_index`)与资源加工(`auto_resource`)由文件监控自动触发,`auto_dream` 则按计划把 daily 记忆整理为可长期复用的 digest。 +ReMe 以服务形式运行，通过 CLI / MCP job 对外暴露记忆。各 Agent 可以按适合自身的方式接入：SDK 深度集成、plugin 集成，或轻量的 +Skill + CLI 集成。它们可以把 `auto_memory` / `proactive` 接入自身生命周期，让对话沉淀为记忆并在合适时机浮现。索引（ +`auto_index`）与资源加工（`auto_resource`）由文件监控自动触发，`auto_dream` 则按计划把 daily 记忆整理为可长期复用的 digest。 -各 Agent 接入状态: +

QwenPaw Auto Memory / Auto Dream 演示

-| Agent | 状态 | 接入方式 | -|------------------------------------------------------|-------------|----------------------------------------------------------------------------------------------| -| [QwenPaw](https://github.com/agentscope-ai/QwenPaw) | ✅ 已支持 | [SDK 深度集成](https://github.com/agentscope-ai/QwenPaw/blob/main/src/qwenpaw/agents/memory/reme_light_memory_manager.py)——进程内嵌入 ReMe 应用,通过 `run_job` 驱动 `search` / `auto_memory` / `auto_dream`,并复用 Agent 自身模型(无需独立 server)。 | -| [Claude Code](plugins/reme) | ✅ 已支持 | Plugin:HTTP MCP server 做召回、`reme-memory` skill,外加在会话结束时经 `auto_memory_cc` 录入的 Stop hook。 | + + + + + + + + + +
Auto MemoryAuto Dream
+ QwenPaw Auto Memory 演示 + + QwenPaw Auto Dream 演示 +
+ +各 Agent 接入状态： + +| Agent | 状态 | 接入方式 | +|-----------------------------------------------------|-------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| [QwenPaw](https://github.com/agentscope-ai/QwenPaw) | ✅ 已支持 | [SDK 深度集成](https://github.com/agentscope-ai/QwenPaw/blob/main/src/qwenpaw/agents/memory/reme_light_memory_manager.py)：进程内嵌入 ReMe 应用，通过 `run_job` 驱动 `search` / `auto_memory` / `auto_dream`，并复用 Agent 自身模型（无需独立 server）。 | +| [Claude Code](plugins/reme) | ✅ 已支持 | Plugin：通过 HTTP MCP server 做召回，提供 `reme-memory` skill，并用 Stop hook 在会话结束时经 `auto_memory_cc` 录入记忆。 | +| 其他 Agent | ✅ 已支持 | [Skill + CLI](skills/reme_memory/SKILL.md)：安装或复制 `reme_memory` skill 后，直接调用 `reme` CLI 完成健康检查、搜索、读取、写入和记忆任务。 | + +Skill + CLI 集成的最小命令示例： + +```bash +reme version +reme health_check +reme search query="" limit=5 +reme auto_memory session_id="" messages='[{"role":"user","content":"..."},{"role":"assistant","content":"..."}]' +``` 更多细节见 [快速开始](docs/zh/quick_start.md)。 @@ -138,13 +176,16 @@ ReMe 将**记忆视为文件**，让原始对话和外部资料从 `session/`、 ├── daily/ # 浅加工记忆：当天事实、对话摘要、资源解读 │ ├── YYYY-MM-DD.md │ └── YYYY-MM-DD/ -│ ├── .md +│ ├── .md │ ├── .md │ └── interests.yaml └── digest/ # 长期记忆：个人事实、流程经验、知识节点 ├── personal/ + │ └── {topic/event}.md ├── procedure/ + │ └── {topic/event}.md └── wiki/ + └── {topic/event}.md ```

@@ -174,54 +215,54 @@ hook 负责触发对话记忆，长期整理与主动提醒则通过定时任务
- Memory as File + Memory as File - Auto Memory and Resource + Auto Memory and Resource
- Auto Dream and Proactive + Auto Dream and Proactive - Auto Index and Memory Search + Auto Index and Memory Search
-### Workspace 操作接口 +### ReMe Operations ReMe 通过统一的 CLI / Service Job 接口操作 workspace。Agent 通常只需要使用检索、读取、写入、编辑和自动记忆相关命令；更底层的索引、frontmatter 和文件操作接口主要用于维护、调试或高级集成。

-查看 Workspace 操作接口表 +查看 ReMe Operations 表
-| 分类 | name | 描述 | 参数 | -|-------|--------------------------------------|---------------------------------------------------------------------------|--------------------------------------------------------| -| 系统状态 | `version` | 返回 ReMe 包版本。 | 无 | -| 系统状态 | `health_check` | 返回 ReMe 组件健康检查摘要。 | 无 | -| 系统状态 | `help` | 列出已注册 jobs 及其 metadata。 | 无 | -| 检索读取 | [`search`](docs/zh/memory_search.md) | 在 workspace 中执行混合检索，结合向量召回、BM25 和 RRF 融合。 | 必填：`query`；可选：`limit`、`min_score` | -| 检索读取 | `node_search` | 根据候选抽象的名称与描述召回相似 digest 节点，主要用于 `auto_dream` 去重或关联。 | 必填：`query`；可选：`limit` | -| 检索读取 | `traverse` | 从指定路径出发遍历 wikilink 图谱。 | 必填：`path`；可选：`depth`、`direction` | -| 检索读取 | `read` | 读取 workspace 下的 Markdown 文件。 | 必填：`path`；可选：`start_line`、`end_line` | -| 检索读取 | `read_image` | 读取 workspace 下的图片文件并返回 base64。 | 必填：`path` | -| 索引维护 | `reindex` | 清空文件存储索引，并基于现有文件重建索引。 | 配置项：`watch_dirs`、`watch_suffixes` | -| Daily | `daily_list` | 列出某一天的 notes。 | `date` | -| Daily | `daily_reindex` | 重建 day-index 页面 `daily/.md`。 | `date` | -| 元数据 | `frontmatter_read` | 读取文件 frontmatter。 | 必填：`path` | -| 元数据 | `frontmatter_update` | 合并 key-values 到文件 frontmatter。 | 必填：`path`、`metadata` | -| 元数据 | `frontmatter_delete` | 删除文件 frontmatter 中的指定 keys。 | 必填：`path`、`keys` | -| 文件操作 | `stat` | 获取 workspace 路径状态，包括大小、mtime、是否存在、是否目录或文件。 | 必填：`path` | -| 文件操作 | `list` | 列出 workspace 路径下的文件。 | `path`、`recursive`、`limit` | -| 文件操作 | `write` | 创建或覆盖 Markdown 文件，并写入 name/description frontmatter。 | 必填：`path`、`name`、`description`、`content`；可选：`metadata` | -| 文件操作 | `edit` | 对 Markdown 文件执行全文 find-and-replace。 | 必填：`path`、`old`、`new` | -| 文件操作 | `move` | 移动或重命名 workspace 文件，并默认重写入站 wikilink。 | 必填：`src_path`、`dst_path`；可选：`overwrite`、`retarget` | -| 文件操作 | `delete` | 删除 workspace 文件或文件夹，并返回仍存在的入站 wikilink。 | 必填：`path` | +| 分类 | 命令 | 描述 | 参数 | +|-------|-------------------------------------------|-----------------------------------------------------|--------------------------------------------------------| +| 系统状态 | `reme version` | 返回 ReMe 包版本。 | 无 | +| 系统状态 | `reme health_check` | 返回 ReMe 组件健康检查摘要。 | 无 | +| 系统状态 | `reme help` | 列出已注册 jobs 及其 metadata。 | 无 | +| 检索读取 | [`reme search`](docs/zh/memory_search.md) | 在 workspace 中执行混合检索，结合向量召回、BM25 和 RRF 融合。 | 必填：`query`；可选：`limit`、`min_score` | +| 检索读取 | `reme node_search` | 根据候选抽象的名称与描述召回相似 digest 节点，主要用于 `auto_dream` 去重或关联。 | 必填：`query`；可选：`limit` | +| 检索读取 | `reme traverse` | 从指定路径出发遍历 wikilink 图谱。 | 必填：`path`；可选：`depth`、`direction` | +| 检索读取 | `reme read` | 读取 workspace 下的 Markdown 文件。 | 必填：`path`；可选：`start_line`、`end_line` | +| 检索读取 | `reme read_image` | 读取 workspace 下的图片文件并返回 base64。 | 必填：`path` | +| 索引维护 | `reme reindex` | 清空文件存储索引，并基于现有文件重建索引。 | 配置项：`watch_dirs`、`watch_suffixes` | +| Daily | `reme daily_list` | 列出某一天的 notes。 | `date` | +| Daily | `reme daily_reindex` | 重建 day-index 页面 `daily/.md`。 | `date` | +| 元数据 | `reme frontmatter_read` | 读取文件 frontmatter。 | 必填：`path` | +| 元数据 | `reme frontmatter_update` | 合并 key-values 到文件 frontmatter。 | 必填：`path`、`metadata` | +| 元数据 | `reme frontmatter_delete` | 删除文件 frontmatter 中的指定 keys。 | 必填：`path`、`keys` | +| 文件操作 | `reme stat` | 获取 workspace 路径状态，包括大小、mtime、是否存在、是否目录或文件。 | 必填：`path` | +| 文件操作 | `reme list` | 列出 workspace 路径下的文件。 | `path`、`recursive`、`limit` | +| 文件操作 | `reme write` | 创建或覆盖 Markdown 文件，并写入 name/description frontmatter。 | 必填：`path`、`name`、`description`、`content`；可选：`metadata` | +| 文件操作 | `reme edit` | 对 Markdown 文件执行全文 find-and-replace。 | 必填：`path`、`old`、`new` | +| 文件操作 | `reme move` | 移动或重命名 workspace 文件，并默认重写入站 wikilink。 | 必填：`src_path`、`dst_path`；可选：`overwrite`、`retarget` | +| 文件操作 | `reme delete` | 删除 workspace 文件或文件夹，并返回仍存在的入站 wikilink。 | 必填：`path` |
@@ -256,6 +297,22 @@ ReMe 通过统一的 CLI / Service Job 接口操作 workspace。Agent 通常只 url = {https://reme.agentscope.io}, year = {2026} } + +@inproceedings{cao-etal-2026-remember, + title = "Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution", + author = "Cao, Zouying and + Deng, Jiaji and + Yu, Li and + Zhou, Weikang and + Liu, Zhaoyang and + Ding, Bolin and + Zhao, Hai", + booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026", + year = "2026", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2026.findings-acl.829/", + pages = "16803--16822" +} ``` ## ⚖️ 许可证 diff --git a/docs/figure/auto-dream-and-proactive.svg b/docs/figure/auto-dream-and-proactive.svg index 4f134826..0206f496 100644 --- a/docs/figure/auto-dream-and-proactive.svg +++ b/docs/figure/auto-dream-and-proactive.svg @@ -3,27 +3,27 @@ A left-to-right flow from changed daily notes to digest integration, interest topic writing, catalog checkpointing, and proactive reads. - - + + - - + + @@ -121,8 +121,8 @@ Proactive material daily/<date>/interests.yaml - Boundary - Read only; caller decides. + Boundary + Read only; caller decides proactive reads interests.yaml after auto_dream writes it diff --git a/docs/figure/auto-index-and-memory-search.svg b/docs/figure/auto-index-and-memory-search.svg index d03ed607..ae44f889 100644 --- a/docs/figure/auto-index-and-memory-search.svg +++ b/docs/figure/auto-index-and-memory-search.svg @@ -3,27 +3,27 @@ A concise left-to-right flow from automatic workspace indexing to memory search and progressive link expansion. - - + + - - + + diff --git a/docs/figure/auto-memory-resource.svg b/docs/figure/auto-memory-resource.svg index 86c2295a..4fa22dc6 100644 --- a/docs/figure/auto-memory-resource.svg +++ b/docs/figure/auto-memory-resource.svg @@ -3,27 +3,27 @@ A concise flow where auto memory and auto resource both create daily cards, which are indexed in the daily memory layer and then used by dream and search. - - + + - - + + diff --git a/docs/figure/design-philosophy.svg b/docs/figure/design-philosophy.svg index e2c09cad..23692903 100644 --- a/docs/figure/design-philosophy.svg +++ b/docs/figure/design-philosophy.svg @@ -3,29 +3,29 @@ A simple diagram showing ReMe's design philosophy: file-native memory, progressive abstraction, and explicit relationship graph for agents. - - + + - - + + diff --git a/docs/figure/memory-as-file.svg b/docs/figure/memory-as-file.svg index 181ec89d..1223dab1 100644 --- a/docs/figure/memory-as-file.svg +++ b/docs/figure/memory-as-file.svg @@ -3,28 +3,28 @@ A diagram showing ReMe workspace files as both a human readable memory interface and an agent operable memory graph, flowing from raw input to daily notes, digest nodes, and metadata indexes. - - + + - - + + diff --git a/docs/figure/qwenpaw-auto-dream.gif b/docs/figure/qwenpaw-auto-dream.gif new file mode 100644 index 00000000..79cd9b7a Binary files /dev/null and b/docs/figure/qwenpaw-auto-dream.gif differ diff --git a/docs/figure/qwenpaw-auto-memory.gif b/docs/figure/qwenpaw-auto-memory.gif new file mode 100644 index 00000000..0ca2f4e9 Binary files /dev/null and b/docs/figure/qwenpaw-auto-memory.gif differ