Quick Start

Get up and running with Feynman in under five minutes — launch the REPL, run deep research, and explore slash commands.

This guide assumes you have already installed Feynman and completed feynman setup. If not, start there first.

1. Launch the REPL

   Start an interactive session by running Feynman with no arguments:

   feynman
   

   You are dropped into a conversational REPL where you can ask research questions, run workflows, and interact with agents in natural language. Type your question and press Enter.

   Sessions are persisted automatically. The next time you run feynman, you resume where you left off. Use --new-session to start a clean session:

   feynman --new-session
   
2. Try a one-shot prompt

   For a quick answer without entering the REPL, pass a prompt directly on the command line:

   feynman --prompt "Summarize the key findings of Attention Is All You Need"
   

   Feynman processes the prompt, prints the response, and exits. This is useful for scripting or piping output into other tools.

3. Run deep research

   Deep research is the flagship workflow. It dispatches multiple agents to search, read, cross-reference, and synthesize information from academic papers and the web.

   From the REPL:

   feynman
   > /deepresearch What are the current approaches to mechanistic interpretability in LLMs?
   

   Or run it directly from the command line without entering the REPL:

   feynman deepresearch "transformer architectures for protein folding"
   

   The agents produce a structured research report with citations, key findings, and open questions. The full report is saved to your outputs/ directory.

4. Explore slash commands

   Type /help inside the REPL to see all available slash commands grouped by category. Each command maps to a workflow or utility:

   > /help
   

   Key workflows you can invoke:

   Command	What it does
   /deepresearch <topic>	Multi-agent investigation with parallel researchers
   /lit <topic>	Literature review from paper search and primary sources
   /review <artifact>	Simulated peer review with severity and revision plan
   /audit <item>	Paper vs. codebase mismatch audit
   /replicate <paper>	Replicate experiments on local or cloud GPUs
   /compare <topic>	Source comparison matrix
   /draft <topic>	Paper-style draft from research findings
   /watch <topic>	Recurring research watch
   /outputs	Browse all research artifacts

5. Find your outputs

   Feynman writes research artifacts to your working directory using a slug-based naming scheme. After a research run, check these directories:

   Directory	Contents
   outputs/	Research reports, briefs, and comparison matrices
   papers/	Paper-style drafts
   notes/	Session logs and intermediate research notes

   Use /outputs in the REPL to browse all artifacts interactively.

What’s next

CLI commands reference

Complete reference for all Feynman CLI commands, flags, and subcommands.

Slash commands reference

Full list of REPL slash commands and their arguments.

Setup

Change your model provider, configure API keys, or connect to alphaXiv.

Introduction

Learn about the four research subagents and the full workflow catalog.