Skip to content
Agentmart
Submit a tool

scienceswarm-getting-started

Help users install, configure, and run ScienceSwarm.

Skill by slowloris-98

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/slowloris-98-scienceswarm-getting-started

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Help users install, configure, and run ScienceSwarm. Use when someone asks how to set up ScienceSwarm, run the dev server, connect services, or troubleshoot first-run issues.

Use cases: backend

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/scienceswarm-getting-started

What's inside

Skill name
scienceswarm-getting-started
Description
Help users install, configure, and run ScienceSwarm. Use when someone asks how to set up ScienceSwarm, run the dev server, connect services, or troubleshoot first-run issues.
License
MIT
Instructions
55 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# ScienceSwarm — Getting Started

## What is ScienceSwarm?

ScienceSwarm is an open-source research workbench that combines:
- A **study dashboard** for managing research studies
- A **Second Brain** (wiki + RAG + memory) for capturing and retrieving knowledge
- A **Research Radar** for daily personalized briefings from arXiv, bioRxiv, etc.
- An **agent layer** (OpenHands / OpenClaw) for automated research tasks

## Installation

See [README.md](../../../../README.md) → Getting Started for user install. The installer seeds `.env` from `.env.example`, checks for Docker + Ollama, and prints the URL to finish configuration in `/setup`.

## Running

- `./start.sh` — starts all available services + frontend at `https://localhost:${FRONTEND_PORT:-3001}` by default
- `npm run dev` — frontend only

`start.sh` auto-detects and starts:
- **OpenHands** (Docker agent at `http://localhost:${OPENHANDS_PORT:-3000}`) — if Docker is available
- **OpenClaw gateway** — if the `openclaw` CLI is installed
- **Next.js frontend** defaults to HTTPS at `https://127.0.0.1:${FRONTEND_PORT:-3001}` when `FRONTEND_USE_HTTPS=true` (default).

## Key Environment Variables

| Variable | Purpose |
|---|---|
| `OPENAI_API_KEY` | Optional cloud fallback for hosted LLM features. |
| `FRONTEND_USE_HTTPS` | Set to `false` to serve ScienceSwarm over HTTP locally. |
| `OPENHANDS_URL` | OpenHands agent URL (default: `http://localhost:3000`) |
| `BRAIN_ROOT` | Second Brain data directory (default: `${SCIENCESWARM_DIR:-~/.scienceswarm}/brain`) |
| `TELEGRAM_BOT_TOKEN` | Enables Telegram capture + radar via bot |
| `LLM_MODEL` | Optional model override for agent tasks; the repo does not set it in `.env.example` |

## Health Check

Visit `https://localhost:${FRONTEND_PORT:-3001}/api/health` to see which services are connected:
- `openclaw`: connected/disconnected
- `openhands`: connected/disconnected
- `ollama`: connected/disconnected (local LLM)
- `openai`: configured/missing

## Common Issues

- **"No OPENAI_API_KEY"**: Open `https://localhost:${FRONTEND_PORT:-3001}/setup` or add the key to `.env`
- **OpenHands won't start**: Check Docker is running (`docker info`)
- **Port in use**: Override with `FRONTEND_PORT=<port>` (or `PORT`) in `.env`
- **OpenClaw unhealthy**: Run `openclaw doctor --fix` then `openclaw gateway --force`

## Quality Check

Run `npm run quality` to verify the build, lint, types, and tests all pass.

From slowloris-98/scienceswarm, MIT.

More from slowloris-98/scienceswarm

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Apr 27, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from slowloris-98

Cite this page

scienceswarm-getting-started skill. Agent Mart. https://agentmart.dev/skills/slowloris-98-scienceswarm-getting-started (last updated 2026-10-24)