ReMe/docs/en/quick_start.md

Quick Start

Installation

ReMe requires Python 3.11+.

Install from pip:

pip install "reme-ai[core]"

Install from source:

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 ..

The static build step requires Node.js 22.13 or newer and makes Studio available when running ReMe from the source tree.

Installing the core extra is recommended. The current code imports the AgentScope wrapper, and self-evolving memory also depends on it.

To use agent workflows such as auto_memory, auto_resource, and auto_dream, configure an 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

You can initially omit the LLM configuration if you only need basic file operations and BM25 retrieval.

---

Start the Service

reme start

The default service address is 127.0.0.1:2333. If the port is already in use:

reme start service.port=8181

reme version
reme health_check
reme help

reme help lists server actions. Ordinary commands invoke server Jobs over HTTP.

The base reme-ai package does not include frontend assets. Install reme-ai[web] or reme-ai[core], then open http://127.0.0.1:2333/ for ReMe Studio. It uses the same service to browse, edit, and search the workspace and inspect the digest wikilink graph. Disable it with service.web_enabled=false, or provide a custom build with service.web_static_dir / REME_WEB_STATIC_DIR. The Job API still starts if no web build is found.

---

Workspace Layout

The default workspace is .reme/ under the current directory. It is created automatically at startup:

.reme/
├── metadata/   # persistent indexes, graph, catalogs, and related state
├── session/    # source conversation records
├── mem_session/ # generated Agent wrapper sessions/config
├── resource/   # external resources
├── daily/      # daily notes
└── digest/     # long-term memory

For directory layers, Markdown frontmatter, and wikilink semantics, see Memory as File.

You can also specify the workspace at startup:

reme start workspace_dir=/tmp/reme-demo service.port=8181

---

Write, Index, and Search

reme write \
  path=digest/wiki/quick-start-demo \
  name="Quick Start Demo" \
  description="Example memory for the quick start" \
  content="# Quick Start Demo

The default live watcher indexes Markdown under the daily and digest directories.

Related link: [[digest/wiki/search-demo.md]]"

path is relative to the workspace. A missing suffix is automatically completed with .md. For Markdown files, name and description are written to frontmatter.

The background watcher builds the index automatically. You can also rebuild it manually:

reme reindex

Search:

reme search query="quick start example memory" limit=5

Read:

reme read path=digest/wiki/quick-start-demo start_line=1 end_line=20

With the default configuration, retrieval is primarily BM25 plus wikilink graph expansion. Vector retrieval is supported by the code, but the embedding store is disabled by default. For the full retrieval flow, see Memory Search.

---

Files and Daily Notes

reme stat path=digest/wiki/quick-start-demo
reme edit path=digest/wiki/quick-start-demo old="indexes" new="continuously indexes"
reme frontmatter_read path=digest/wiki/quick-start-demo
reme frontmatter_update path=digest/wiki/quick-start-demo metadata='{"tags":["demo"]}'

The file-listing Job can be called directly from the CLI:

reme list path=digest recursive=true limit=50

The equivalent HTTP call is:

curl -s http://127.0.0.1:2333/list \
  -H 'Content-Type: application/json' \
  -d '{"path":"digest","recursive":true,"limit":50}'

Daily notes:

reme write path=daily/2026-06-20/demo-session.md name=demo-session description="Demo session" content="Recorded content"
reme daily_list
reme daily_reindex

write can create a daily note directly. Run daily_reindex when the day's index needs to be refreshed.

---

Automatic Memory

reme auto_memory \
  session_id=chat-demo \
  messages='[{"role":"user","content":"I prefer to preserve project experience as Markdown."},{"role":"assistant","content":"Recorded."}]' \
  memory_hint="Record the user's preference"

After placing external material under resource/YYYY-MM-DD/ or directly under resource/, the default background task watches md/txt/json/jsonl/csv/yaml/html. You can also trigger processing manually:

reme auto_resource changes='[{"path":"resource/2026-06-20/report.md","change":"added"}]'

Distill daily notes into long-term digest memory:

reme auto_dream date=2026-06-20
reme proactive date=2026-06-20

These flows require a working LLM. Without an LLM configuration, start with basic capabilities such as write, read, and search.

For more detail, see Auto Memory, Auto Resource, Auto Dream, and Proactive.

---

HTTP and Configuration

Every service-enabled Job is exposed as 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":"quick start","limit":5}'

The default configuration comes from reme/config/default.yaml. Override it at startup with dot notation:

reme start \
  workspace_dir=/tmp/reme-demo \
  service.host=127.0.0.1 \
  service.port=8181 \
  enable_logo=false

You can also specify a YAML or JSON configuration file:

reme start config=/path/to/custom.yaml