@sinlair/reagent

ReAgent

Turn ongoing research into a reusable workflow, not a one-off conversation.

Local-first research workspace for paper discovery, evidence synthesis, research memory, and delivery.

English  |  简体中文

Roadmap  •  Contributing  •  Operations

Table of Contents

• Why ReAgent
• Highlights
• Workflow
• Quick Start
• Run Modes
• Repository Layout
• Development
• OpenClaw Plugin
• Documentation
• Inspiration
• License

Why ReAgent

ReAgent is not a chatbot with a few research buttons attached. It is closer to a local Research Workspace / Research OS.

It is designed for teams or individuals who need more than one-off answers:

• 🧭 Define structured Research Briefs with goals, baselines, constraints, and evaluation criteria.
• 🔎 Keep discovery running instead of restarting the same search every week.
• 🧠 Store papers, repos, evidence, feedback, and memory in one workspace.
• 🧾 Turn analysis into reports, briefings, decks, and reusable module notes.
• 🌐 Continue the loop through the web console, WeChat, and OpenClaw plugin surfaces.

Best for:

• researchers tracking one or more directions over time
• lab members who need paper reading, repo inspection, and meeting prep in one workflow
• teams exploring a research agent + workspace memory + delivery product shape
• developers who want a controllable, hackable, local research workspace

Highlights

Area	What You Get
🔎 Brief-driven discovery	Discovery stays tied to explicit goals, baselines, and evaluation criteria instead of loose prompts.
📄 Paper and repo analysis	Analyze papers, inspect repos, and extract reusable module notes inside one loop.
🧠 Durable research memory	Keep artifacts, reports, and feedback in file-backed memory and graph-friendly structures.
🧾 Delivery-ready outputs	Generate direction reports, baseline suggestions, daily briefs, and meeting deck material.
🔌 Multi-surface access	Use the web workspace, WeChat channel, and OpenClaw plugin without fragmenting the workflow.
⚙️ Local-first runtime	Run locally, keep background services visible, and inspect deployment/runtime behavior.

Workflow

Research Brief
  -> Discovery
  -> Paper / Repo Analysis
  -> Synthesis
  -> Report / Deck / Briefing
  -> Feedback
  -> Memory
  -> Next Research Round

Current workspace surfaces include:

• Home for workspace pulse, latest outputs, and fast entry points
• Command Center for health, recent activity, delivery posture, and runtime visibility
• Agent Desk for natural language and slash-command driven actions
• Evidence Workspace for briefs, tasks, scheduler control, reports, and artifacts
• Research Map for relationships across directions, papers, repos, modules, and presentations
• Knowledge Vault for file-backed memory search, write, and preview
• Channels for WeChat / OpenClaw status, pairing, lifecycle audit, and recovery

Quick Start

• Create a local env file from .env.example.
• Install dependencies.
• Push the Prisma schema to the default SQLite database.
• Start the dev server.

npm install
npm run db:push
npm run dev

Open http://127.0.0.1:3000/.

Minimal local setup:

LLM_PROVIDER=fallback
WECHAT_PROVIDER=mock

If PowerShell blocks npm, use npm.cmd instead.

Global CLI install:

npm install -g @sinlair/reagent
reagent init
reagent gateway

The published package name is @sinlair/reagent, while the installed command is reagent.

Always-on gateway lifecycle:

reagent gateway install
reagent gateway status
reagent gateway restart
reagent gateway stop

Run Modes

The root app can run as a foreground dev process or as an always-on background service.

Mode	Commands	Notes
🧪 Development	npm run dev	Live local development
♻️ PM2	npm run pm2:start / npm run pm2:restart / npm run pm2:logs	Keep the app running in the background
🪟 Windows Service	npm run service:install / npm run service:status / npm run service:start / npm run service:stop	Best for Windows machine-level runtime

See OPERATIONS.md for deployment and maintenance details.

Repository Layout

Path	Purpose
./	Root ReAgent app, web console, API server, and runtime
packages/reagent-core/	Reusable core research logic
packages/reagent-openclaw/	Installable OpenClaw plugin package
package/	In-repo OpenClaw WeChat reference package kept for compatibility and integration work
docs/	Product visuals, release notes, and supporting docs

Notes:

• The root app is publishable as @sinlair/reagent and installs a global reagent command.
• Publish-oriented packages live under packages/reagent-core and packages/reagent-openclaw.

Development

Validation:

npm run check:all
npm run test

If you only want to validate the publishable packages:

npm run build:packages
npm run check:packages

OpenClaw Plugin

Install the ReAgent OpenClaw plugin with:

openclaw plugins install @sinlair/reagent-openclaw --yes

Plugin source lives in packages/reagent-openclaw/.

Documentation

• 📘 Chinese README: README.zh-CN.md
• 🧭 Product blueprint: agent.md
• 🗺️ Roadmap: ROADMAP.md
• 🛠️ Operations: OPERATIONS.md
• 🤝 Contributing: CONTRIBUTING.md
• 🔐 Security: SECURITY.md

Inspiration

ReAgent is shaped by research-agent and research-workspace projects such as:

• GPT Researcher
• deer-flow
• PASA
• Paper2Agent
• enterprise-deep-research
• InternAgent
• OpenClaw

For a closer comparison, see docs/research-agent-landscape.md.

License

Released under the MIT License.