Docs · Start here
Install ResearchForge and pick how it runs
Install#
Every path starts with the same pip install. Then add the skills for your editor — or use no editor at all.
Claude Code
- 1
pip install researchforge - 2
researchforge claude install --useror install the Claude Code plugin (below)
- 3
/overnight <competition-url>from the plugin: /researchforge:overnight
Cursor
- 1
pip install researchforge - 2
researchforge cursor install --user - 3
@overnight <competition-url>in the agent chat
No editor
- 1
pip install researchforge - 2
export RESEARCHFORGE_LLM=ollama/qwen3:14ba local model, or ANTHROPIC_API_KEY / GEMINI_API_KEY / OPENAI_API_KEY
- 3
researchforge kaggle overnight <competition-url> - 4
researchforge kaggle run <slug>
Claude Code plugin. Instead of researchforge claude install, you can install the same skills from the plugin marketplace. Plugin skills are namespaced (/researchforge:overnight). Use one or the other, not both, or every skill appears twice.
› /plugin marketplace add forger-labs-hq/researchforge› /plugin install researchforge@researchforge
researchforge --version and researchforge doctor. The doctor names anything missing (git, Python, Docker) and how to fix it.Pick how it runs#
Something has to propose each experiment. That is either the AI in your editor, or a model ResearchForge calls itself. ResearchForge always does the running, measuring and record-keeping.
| Drive it from | Who proposes | Key | Editor stays open | Start with |
|---|---|---|---|---|
| Claude Code | Claude, in your Claude Code session | None — your Claude plan | Yes — or turn on auto-run | /overnight <url> |
| Cursor | Cursor’s agent | None — your Cursor plan | Yes — or turn on auto-run | @overnight <url> |
| BYOK (your API key) | Claude, Gemini or OpenAI, called directly from the terminal | ANTHROPIC_API_KEY, GEMINI_API_KEY or OPENAI_API_KEY | No — runs headless | researchforge kaggle run <slug> |
| Local model | Your Ollama model, called by ResearchForge | None — RESEARCHFORGE_LLM=ollama/<model> | No — runs headless | researchforge kaggle run <slug> |
Or start without an editor. Open the dashboard with researchforge dashboard, add the competition under + New competition, set your keys under Keys & accounts and pick a driver for auto-run. You can open Claude Code or Cursor later and continue with /overnight <slug> — or never.

$ export ANTHROPIC_API_KEY=sk-ant-... # or GEMINI_API_KEY / OPENAI_API_KEY$ export RESEARCHFORGE_LLM=ollama/qwen3:14b # local model, no key (after: ollama pull qwen3:14b)$ export OLLAMA_HOST=http://gpu-box:11434 # only if Ollama runs on another machine
Choose a track#
Kaggle Overnight
Give it a competition URL; read the morning report.
OpenResearch loop
Explore an idea or improve a repository, unattended.
OpenTeams & enterprise
Governance, isolation, air-gapped use and pilots.
OpenWhichever track you pick, four short pages answer the usual next questions:

Requirements#
- Python 3.12+ and git. macOS, Linux or Windows.
- For Kaggle Overnight: a Kaggle account and API token (
~/.kaggle/kaggle.jsonorKAGGLE_USERNAME/KAGGLE_KEY), or paste it on the dashboard's Keys & accounts page. - Optional: Docker, to run repository experiments in containers.
- Optional:
pip install "researchforge[serve]"for the live read-only monitor (researchforge serve,researchforge hub).
Upgrade#
$ pip install --upgrade researchforge$ researchforge --version
Skills and rules installed with claude install / cursor install refresh themselves after an upgrade. Ones you edited are left alone. Plugin users update from /plugin. What changed in each release is in the changelog.