* fix(packaging): harden the Studio release workflow * chore(daily-paper): tune scheduled discovery defaults * fix(docs): link the ReMe blog to GitHub Pages * fix(docs): increase Chinese hero title spacing * refactor(docs): share hero title line spacing * fix(docs): keep desktop hero copy on two lines * fix(docs): widen the home hero description * style(docs): loosen hero title line height * fix(docs): hide Markdown frontmatter in rendered pages * docs(readme): simplify installation and remove standalone ReMe Studio instructions - Remove references to separate ReMe Studio package and static build steps - Clarify that `core` extra includes common integrations including Studio - Update installation instructions to use `pip install -e ".[core]"` - Remove detailed Studio usage and frontend development instructions - Note that Studio is included with `core` and optional via `web` extra - Simplify Quick Start guide by removing Studio usage step - Remove mentions of serving Studio with HTTP service when using extras - Update both English and Chinese README files accordingly * docs(readme): streamline and clarify memory design and operations - Remove redundant explanations about core extra installation - Simplify memory processing flow description for clarity - Clarify memory workspace directory default and customization - Condense automatic memory flow to emphasize rebuildable metadata - Refine search functionality explanation with RRF fusion details - Shorten and clarify agent integration description, removing redundancy - Update and simplify the operations command list, removing less common commands - Revise community and support section for conciseness and clarity - Maintain parallel updates in both English and Chinese README files * test(bump_version): add tests for version bumping and consistency checks - Add dynamic loading of bump_version and package_studio scripts for testing - Test that studio package and dependencies have matching versions - Implement fixtures to write temporary version files for testing - Add test ensuring bump_version updates all relevant files and dependencies - Add test to reject inconsistent version sources before writing - Refactor tests to use common REPOSITORY path variable - Include imports and setup for pytest in test file feat(bump_version): create script to update ReMe and Studio versions - Implement version reading from __init__.py and pyproject.toml files - Validate current versions are consistent across files before updating - Update version strings atomically to avoid partial writes - Ensure exact pinning of studio dependency in main package extras - Validate new version format against a safe pattern - Provide CLI interface to bump versions from command line - Raise errors if expected version declarations or pins are missing or duplicated * fix(release): validate split package publishing * fix(release): improve validation diagnostics * fix(release): sync docs and workflow inputs * fix(release): split PyPI publish jobs
5.4 KiB
快速开始
安装
ReMe 要求 Python 3.11+。
从 pip 安装:
pip install "reme-ai[core]"
从源码安装:
git clone https://github.com/agentscope-ai/ReMe.git
cd ReMe
pip install -e packages/reme_ai_studio -e ".[core]"
cd website
npm ci
npm run build:static
cd ..
静态构建步骤需要 Node.js 22.13 或更高版本,用于在从源码运行 ReMe 时提供 Studio。
core extra 建议安装:当前代码会导入 AgentScope wrapper,自进化记忆也依赖它。
如果要使用 auto_memory、auto_resource、auto_dream 这类 Agent 流程,再配置 LLM:
cat > .env <<'EOF'
LLM_BACKEND=openai
LLM_MODEL_NAME=qwen3.7-plus
LLM_API_KEY=your_api_key
LLM_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
EOF
只跑基础文件读写和 BM25 检索,可以先不配。
启动
reme start
默认服务地址是 127.0.0.1:2333。如果端口被占用:
reme start service.port=8181
reme version
reme health_check
reme help
reme help 会列出服务端 action。普通命令会通过 HTTP 调用服务端 Job。
基础 reme-ai 包不包含前端资源。安装 reme-ai[web] 或 reme-ai[core] 后,浏览器打开
http://127.0.0.1:2333/ 即可进入 ReMe Studio,在同一服务中浏览、编辑和搜索
workspace,并查看 digest Wikilink 图。可用 service.web_enabled=false 关闭,或通过 service.web_static_dir /
REME_WEB_STATIC_DIR
指定自定义静态目录;找不到构建产物时,Job API 仍会正常启动。
Workspace 目录
默认 workspace 是当前目录下的 .reme/,启动时会自动创建:
.reme/
├── metadata/ # 索引、图谱、catalog 等持久状态
├── session/ # 对话来源记录
├── mem_session/ # Agent wrapper 生成的 session/配置
├── resource/ # 外部资料
├── daily/ # daily note
└── digest/ # 长期记忆
目录分层、Markdown frontmatter 和 wikilink 语义见 Memory as File。
也可以启动时指定:
reme start workspace_dir=/tmp/reme-demo service.port=8181
写入、索引、检索
reme write \
path=digest/wiki/quick-start-demo \
name="Quick Start Demo" \
description="快速开始示例记忆" \
content="# Quick Start Demo
默认实时 watcher 会索引 daily 和 digest 目录中的 Markdown。
相关链接:[[digest/wiki/search-demo.md]]"
path 是 workspace 内路径;没有后缀时会自动补 .md;Markdown 文件会写入 name 和 description front matter。
后台 watcher 会自动建索引;也可以手动重建:
reme reindex
搜索:
reme search query="快速开始 示例 记忆" limit=5
读取:
reme read path=digest/wiki/quick-start-demo start_line=1 end_line=20
默认配置下,检索主要是 BM25 + wikilink 图谱扩展;向量检索能力在代码中支持,但默认未启用 embedding store。完整检索流程见 Memory Search。
文件与 Daily Note
reme stat path=digest/wiki/quick-start-demo
reme edit path=digest/wiki/quick-start-demo old="会索引" new="会持续索引"
reme frontmatter_read path=digest/wiki/quick-start-demo
reme frontmatter_update path=digest/wiki/quick-start-demo metadata='{"tags":["demo"]}'
文件列表 Job 可以直接通过 CLI 调用:
reme list path=digest recursive=true limit=50
等价的 HTTP 调用是:
curl -s http://127.0.0.1:2333/list \
-H 'Content-Type: application/json' \
-d '{"path":"digest","recursive":true,"limit":50}'
Daily note:
reme write path=daily/2026-06-20/demo-session.md name=demo-session description="Demo session" content="记录内容"
reme daily_list
reme daily_reindex
write 可直接创建 daily note;需要刷新当天索引时运行 daily_reindex。
自动记忆
reme auto_memory \
session_id=chat-demo \
messages='[{"role":"user","content":"我偏好把项目经验沉淀成 Markdown。"},{"role":"assistant","content":"已记录。"}]' \
memory_hint="记录用户偏好"
外部资料放入 resource/YYYY-MM-DD/ 或直接放在 resource/ 下后,默认后台会监听 md/txt/json/jsonl/csv/yaml/html。
也可以手动触发:
reme auto_resource changes='[{"path":"resource/2026-06-20/report.md","change":"added"}]'
把 daily 整理到长期 digest:
reme auto_dream date=2026-06-20
reme proactive date=2026-06-20
这些流程需要可用 LLM;未配置 LLM 时请先使用 write/read/search 这类基础能力。
更多细节见 Auto Memory、Auto Resource、Auto Dream 和 Proactive。
HTTP 与配置
每个可服务 Job 都暴露为 POST /<job>:
curl -s http://127.0.0.1:2333/version \
-H 'Content-Type: application/json' \
-d '{}'
curl -s http://127.0.0.1:2333/search \
-H 'Content-Type: application/json' \
-d '{"query":"快速开始","limit":5}'
默认配置来自 reme/config/default.yaml。启动时可以用 dot notation 覆盖:
reme start \
workspace_dir=/tmp/reme-demo \
service.host=127.0.0.1 \
service.port=8181 \
enable_logo=false
也可以指定 YAML/JSON 配置文件:
reme start config=/path/to/custom.yaml