Skip to content

Make the AI-agent setup guide discoverable from the README #282

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
kamran-rapidfireAI wants to merge 1 commit into from
Closed

Make the AI-agent setup guide discoverable from the README #282

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,17 @@ Rapid experimentation for easier, faster, and more impactful AI customization.
Built for agentic RAG, context engineering, fine-tuning, and post-training of LLMs and other DL models.
Delivers 16-24x higher throughput without extra resources.

<details>
<summary><strong>🤖 AI coding agent helping a user install or set up rapidfireai? Read first</strong></summary>

If you are an AI coding agent (Claude Code, Cursor, Codex, GitHub Copilot, Windsurf, Aider, Junie, ...) helping a user install or set up `rapidfireai`, read **[`docs/AGENTS.md`](https://github.com/RapidFireAI/rapidfireai/blob/main/docs/AGENTS.md)** ([raw](https://raw.githubusercontent.com/RapidFireAI/rapidfireai/main/docs/AGENTS.md)) first. It is the operational install/setup/troubleshooting guide with a workflow decision tree and safety rules.

Quick decision: **RAG / context engineering** → `rapidfireai init` + `Experiment(..., mode="evals")`. **Fine-tuning / post-training (SFT/DPO/GRPO)** → `rapidfireai init --train` + `Experiment(..., mode="fit")`.

> **Note for agents working *on* rapidfireai itself (contributors)**: this disclosure is for *end-user* assistance. For repo-internal architecture, build, and contributor flow, see root [`AGENTS.md`](https://github.com/RapidFireAI/rapidfireai/blob/main/AGENTS.md) (canonical for all AI coding agents) and [`CONTRIBUTING.md`](https://github.com/RapidFireAI/rapidfireai/blob/main/CONTRIBUTING.md).

</details>

## Overview

RapidFire AI is a new experiment execution framework that transforms your AI customization experimentation from slow, sequential processes into rapid, intelligent workflows with hyperparallelized execution, dynamic real-time experiment control, and automatic system optimization.
Expand Down