SkillAgentSearch skills...

researchforge

A lab protocol for coding agents. Freeze baselines, run hypotheses in isolated worktrees, reject failures and validate improvements from Claude Code, Cursor or a direct API key (Gemini/Anthropic/openAI).

Install / Use

claude mcp add forger-labs-hq -- npx -y github:forger-labs-hq/researchforge

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

84/100

Category

Automation

Supported Platforms

Claude Code
Claude Desktop
Cursor
Gemini CLI

Our assessment of researchforge

researchforge scores 84/100 on our quality scale, 2026th of 2,769 Automation skills we index.

Its MCP Server is 25 KB long, well organised into 30 sections with 8 code examples: a thorough specification that gives an agent plenty to work with.

It has 10 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
4/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated yesterday, so researchforge is actively maintained.
  • It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 97/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

researchforge compared with similar skills

All 4 of these similar skills score higher than researchforge; compare them before choosing.

SkillScoreStarsUpdatedFormat
researchforge (this skill)by forger-labs-hq84101d agoMCP Server
Agent-Reachby Panniantong100112.7k9d agoCLAUDE.md
rufloby ruvnet10082.0ktodayCLAUDE.md
headroomby headroomlabs-ai10079.9ktodayCLAUDE.md
CowAgentby zhayujie10048.0ktodayCLAUDE.md

Frequently asked questions

How do I install researchforge?
Run claude mcp add forger-labs-hq -- npx -y github:forger-labs-hq/researchforge. The install tabs above show the steps for each supported agent.
Which AI agents does researchforge work with?
It is written for Claude Code, Claude Desktop, Cursor and Gemini CLI, as a MCP Server file. Other agents that read the same format can often use it too.
Is researchforge safe to use?
It is Apache-2.0-licensed and scores 97/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is researchforge still maintained?
The repository was last updated yesterday, so researchforge is actively maintained.
<div align="center"> <img src="https://raw.githubusercontent.com/forger-labs-hq/researchforge/main/assets/logo.png" alt="ResearchForge" width="130"> <h1>ResearchForge</h1> <p><strong>Run experiments on your code overnight. Keep only what beats the baseline.</strong></p> <p>Give it a Kaggle competition or your repository before bed. On Kaggle it keeps your score current: every hour it finds the public notebooks scoring above you and turns them into rounds, then auto-run keeps experimenting on top of them. On your repository, an AI proposes experiments and ResearchForge measures each one against a frozen baseline, keeping only real wins. Nothing is submitted or shipped without your yes. Inspired by https://github.com/karpathy/autoresearch . </p> <p> <a href="https://pypi.org/project/researchforge/"><img src="https://img.shields.io/pypi/v/researchforge?color=7C3AED&label=PyPI" alt="PyPI"></a> <a href="https://pypi.org/project/researchforge/"><img src="https://img.shields.io/pypi/pyversions/researchforge?color=7C3AED" alt="Python 3.12+"></a> <a href="https://github.com/forger-labs-hq/researchforge/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-F59E0B" alt="Apache 2.0"></a> <a href="https://github.com/forger-labs-hq/researchforge/stargazers"><img src="https://img.shields.io/github/stars/forger-labs-hq/researchforge?style=flat&color=7C3AED" alt="GitHub stars"></a> </p> <h3><a href="#try-it-tonight">🚀 Try it tonight</a> &nbsp;·&nbsp; <a href="#demo">▶ Watch the 60-second demo</a> &nbsp;·&nbsp; <a href="https://github.com/forger-labs-hq/researchforge">⭐ Star on GitHub</a></h3> <p><a href="#every-way-to-run-it">Every way to run it</a> · <a href="#walkthroughs">Walkthroughs</a> · <a href="#what-you-get">Features</a> · <a href="#the-dashboard">Dashboard</a> · <a href="#real-results">Results</a> · <a href="#faq">FAQ</a> · <a href="https://www.researchforgehq.com/docs">Docs</a></p> </div>

<a id="demo"></a>

https://github.com/user-attachments/assets/4ac96b88-c16d-4332-a660-534ccc3bdec1

Try it tonight

1. Install (one minute)

pip install researchforge
researchforge claude install --user     # using Cursor? researchforge cursor install --user
<img src="https://raw.githubusercontent.com/forger-labs-hq/researchforge/main/assets/screenshots/step1-install.png" alt="Terminal: researchforge claude install --user installs /overnight and the /researchforge-* skills into ~/.claude/skills" width="640">

2. Start, in Claude Code (in Cursor, type @ instead of /)

First, open Claude Code or Cursor in the folder you want to work in. For a repository, that's the repository itself. For a Kaggle competition, use a new or empty folder. ResearchForge keeps everything for the project in that folder (.researchforge/ for a repository, .overnight_<competition>/ for Kaggle), and every command below runs there.

| To improve… | Type | |---|---| | a Kaggle score | /overnight https://www.kaggle.com/competitions/titanic (or any competition you've joined). It keeps your score up to date with the best public notebooks, then improves on them. Setup offers auto-run too. | | your repository | /researchforge-start in a chat opened in your repo, then /researchforge-autorun: Claude runs the loop in the chat, round after round, with no API key | | either, with nothing open | Auto-run: researchforge kaggle auto-run <name> --on for a competition, researchforge auto-run settings --on --driver claude for a repository (how it works) |

📊 Watch it live at http://localhost:7842. /overnight opens the dashboard for you; for a repository, run researchforge dashboard.

<img src="https://raw.githubusercontent.com/forger-labs-hq/researchforge/main/assets/screenshots/step2-new-competition.webp" alt="Dashboard: + New competition, the same setup as /overnight as a form" width="820">

<sub>No editor? <b>+ New competition</b> in the dashboard runs the same setup as <code>/overnight</code>, as a form.</sub>

3. Go to sleep

It asks a few questions, then runs round after round. Nothing is submitted or shipped until you say yes. When it needs a decision, the question reaches you two ways:

  • On your phone: install the free ntfy app and subscribe to your topic. Set it with researchforge notify setup --topic <a-name-nobody-can-guess>, or in the dashboard under Run configs → Notifications, which also has a Send test alert button.
  • In the dashboard: the 🔔 at the top and the Questions for you list on Home show every open question, grouped by competition with how many submissions Kaggle still allows today. Answer right there: Approve & submit or Don't submit, add a comment the next round will follow, or dismiss it with ✕. An answer marked ⚙ also changes the setting it names (say, compute → Kaggle GPU) in Run configs when you pick it.
<img src="https://raw.githubusercontent.com/forger-labs-hq/researchforge/main/assets/screenshots/step3-questions.webp" alt="Dashboard: the 🔔 questions grouped by competition, with submissions left today and ⚙ answers that change Run configs" width="820">

No Claude Code or Cursor? Use an API key or a local model from the terminal.

What happens overnight

| When | What happens | |---|---| | Tonight | You give it a competition URL or open your repo, and answer a few questions: where to run, for how long, where to send alerts. | | Every hour (Kaggle) | It checks the competition's public notebooks, re-runs included, and ranks them by the score they claim. The ones ahead of your best are adopted or merged into rounds on your compute, so your score keeps pace with the best public work. | | Every round | The AI proposes one change → it runs on your chosen GPU, or in an isolated copy of your repo → it's scored against the baseline → kept, or rejected with the reason. | | When it needs you | Your phone gets "Submit R7 to Kaggle?" or "plan-003 waits for your approval". Answer from the dashboard. | | Morning | A briefing: what improved, what failed and why. One click to submit to Kaggle; one command to ship a branch. |

Every way to run it

Pick what you want to improve and where you'll drive it from. Each cell is the command that starts it. Run it from the folder the project lives in: your repository, or a folder for the competition.

| | Claude Code | Cursor | Terminal only | |---|---|---|---| | A Kaggle competition | /overnight <competition-url> | @overnight <competition-url> | researchforge kaggle overnight <competition-url><br>then researchforge kaggle run <slug> | | Your repository | /researchforge-start, then /researchforge-autorun | @researchforge-start, then @researchforge-autorun | ten commands, below | | A research idea | /researchforge-start | @researchforge-start | four commands, below | | One-time setup | researchforge claude install --user | researchforge cursor install --user | an API key: export ANTHROPIC_API_KEY=… (or GEMINI_API_KEY, OPENAI_API_KEY), or a local model: export RESEARCHFORGE_LLM=ollama/qwen3:14b | | Who proposes experiments | Claude, in your chat | Cursor's agent, in your chat | the API model, or your local model | | API key needed | No, your Claude plan | No, your Cursor plan | Yes, or none with Ollama | | Must stay open | the chat | the chat | the terminal |

The three columns are independent: install for Claude Code and Cursor and set a key, and use whichever fits the moment. To keep going with nothing open, turn on auto-run.

Lost at any point? researchforge status prints the exact next command for the project you're in.

Setup in two minutes

  1. pip install researchforge (Python 3.12+ and git). researchforge doctor checks your machine.
  2. Set up one or more ways to drive it, from the last row of the table above. researchforge all install --user sets up Claude Code and Cursor together.
  3. For Kaggle: join the competition on kaggle.com and add your Kaggle API token to ~/.kaggle/, or paste it into the dashboard's Keys & accounts page.
  4. Optional: phone alerts with ntfy: researchforge notify setup --topic <a-name-nobody-can-guess>.
  5. Optional: the live dashboard: researchforge dashboard (http://localhost:7842).

Walkthroughs

Keep up with the Kaggle leaderboard, then improve on it

You need: a Kaggle account that has joined the competition, and its API token.

In Claude Code or Cursor

  1. Type /overnight https://www.kaggle.com/competitions/<name> (@overnight in Cursor).
  2. It reads the competition (metric, data size, deadline, top public notebooks) and your machine, then asks a few questions: where to run (local GPU, Kaggle GPU, Colab, your SSH server or a cloud GPU, each with what it found and a recommendation), how long, phone alerts, and whether to keep going on its own.
  3. It keeps your score current. Every hour it checks the competition's public notebooks and ranks them by the score they claim. The ones ahead of your best become rounds first, adopted as they are or merged with your best, so you keep pace with the leaders' public work.
  4. Then it improves on that. It runs its own rounds on top: propose an experiment → run it on the compute you chose → score it against your best → keep or reject. Your directions on Steer, arXiv papers and the loop's own results feed the ideas. Every improved round that Kaggle could take raises a Submit? question.
  5. Keep the chat open, or say yes to auto-run in step 2 so rounds continue with the chat closed.

In a terminal (with an API key or a local model)

researchforge kaggle overnight https://www.kaggle.com/competitions/<name> --gpu kaggle --time-hours 8
researchforge kaggle run <name>          # the loop
researchforge kaggle finish <name>       # the morning report

In the morning

A briefing on your phone, and the dashboard shows every round. To send a round to Kaggle, click Approve & submit on its question. It checks Kaggle's daily limit first and never sends the same round twice.

No editor at all? Open the dashboard, click + New competition, paste the URL and answer the same questions as a form.

Improve a repository

You need: a git repository with its work committed, and a command that measures what you care about: a benchmark, an eval script or a test that prints a number (accuracy, F1, latency, …).

In Claude Code or Cursor, opened in your repository

  1. Type /researchforge-start (@researchforge-start in Cursor), choose Improve a repository, and give one sentence naming the metric: "Raise F1 without slowing inference."
  2. It scans the repo, searches arXiv for related work and proposes testable hypotheses.
  3. It drafts the contract, researchforge.yaml: the metric, hard limits (like latency), which files experiments may change and which are protected. You read it and approve it by typing.
  4. It measures the baseline once and freezes it. Every experiment is compared to this number.
  5. Type /researchforge-autorun. Each round it plans experiments, you approve the first batch, and they run in separate git worktrees (your checkout is never touched), get measured, and feed the next round's hypotheses.

In a terminal (with an API key or a local model), from your repository

researchforge project create --mode improve_repository --objective "Raise F1 without slowing inference"
researchforge repo scan .
researchforge research search            # related papers from arXiv
researchforge research synthesize        # research directions and testable hypotheses
researchforge report build
researchforge contract generate       

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars10
CategoryAutomation
Updated1d ago
Forks0

Languages

Python

Trust signals

97/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 info