toolspool
Runcell - Jupyter AI Agent logo

Runcell - Jupyter AI Agent

verifiedFreemiumAgentruncell.dev

Jupyter-native AI agent that remembers a data project across sessions and reads chart/plot outputs, not just code.

What it does

Runcell is an AI agent that installs directly into an existing JupyterLab environment via pip and works across multi-week data or ML projects rather than single prompts. It retains memory of prior sessions, reads notebook outputs like charts and metrics to reason about real results, and can run long multi-step tasks autonomously inside the notebook. It's aimed at domain experts, not just software engineers.

How to use: 1. Install runcell with pip/conda/uv, for example, pip install runcell --upgrade 2. Restart your jupyter lab with `jupyter lab .` 3. On the right side of jupyter lab, you can find runcell extension, login and you can start to use the AI Agent.

Core features

Cross-session project memory recalling prior decisions and state
Autonomous execution of long, multi-step notebook tasks
Reads cell outputs (plots, tables, metrics), not just code
In-notebook cell-level assistance and error fixing
Installs directly into existing JupyterLab via pip, no new editor
Concept explanations with runnable example cells

Best for

→Data scientists running multi-week model iteration projects
→Domain experts (e.g. risk/fintech) who know the problem but not deep Python
→Researchers wanting an agent that remembers project context across days
→Analysts needing help understanding unfamiliar algorithms or libraries
Toolspool rankingby monthly traffic