
rnow-cli
by ReinforceNow
The RL training platform. Use ReinforceNow to train reliable AI agents from raw data to production.
SKILL.md
name: rnow-cli description: Use the ReinforceNow CLI for RLHF training. Use when running rnow commands, initializing projects, submitting training runs, testing rollouts, or downloading models. Triggers on "rnow", "rnow init", "rnow run", "rnow test", "rnow download", "rnow login", "training run". allowed-tools: Bash, Read, Grep, Glob
ReinforceNow CLI Reference
The rnow CLI manages RLHF training projects on the ReinforceNow platform.
Installation
pip install rnow
Command Overview
| Command | Description |
|---|---|
rnow login | Authenticate with the platform |
rnow logout | Remove credentials |
rnow status | Check auth and running jobs |
rnow orgs | Manage organizations |
rnow init | Create new project from template |
rnow run | Submit training run |
rnow stop | Cancel active run |
rnow test | Test rollouts locally |
rnow download | Download trained model |
rnow login
Authenticate using OAuth device flow.
rnow login [OPTIONS]
| Option | Description |
|---|---|
--force | Force new login even if already authenticated |
--api-url URL | Custom API base URL |
Example:
rnow login
# Opens browser for authentication
# Stores credentials in ~/.reinforcenow/credentials.json
rnow logout
Remove stored credentials.
rnow logout
rnow status
Check authentication status and running jobs.
rnow status
Output:
Logged in as: user@example.com
Organization: My Team (org_abc123)
Active runs: 2
- run_xyz789 (running) - Math Training
- run_def456 (queued) - Code Agent
rnow orgs
List or select organizations.
# List all organizations
rnow orgs
# Select an organization
rnow orgs ORG_ID
Example:
rnow orgs
# Output:
# * org_abc123 - My Team (owner)
# org_def456 - Other Team (member)
rnow orgs org_def456
# Switched to: Other Team
rnow init
Initialize a new project from a template.
rnow init [OPTIONS]
| Option | Description |
|---|---|
--template NAME | Template to use (see below) |
--name NAME | Project name (prompts if not provided) |
Available Templates
| Template | Type | Description |
|---|---|---|
start | RL | Default single-turn RL (alias for rl-single) |
rl-single | RL | Single-turn with math reasoning |
rl-tools | RL | Multi-turn with tool calling |
sft | SFT | Supervised finetuning |
tutorial-reward | RL | Learn reward functions |
tutorial-tool | RL | Learn tool functions |
mcp-tavily | RL | External MCP server (web search) |
deepseek-aha | RL | DeepSeek aha-moment training |
finqa | RL | Financial QA |
convfinqa | RL | Conversational financial QA |
quantqa | RL | Quantitative finance |
new | RL | Minimal template |
blank | - | Empty (config only) |
Examples:
# Create SFT project
rnow init --template sft --name "my-sft-project"
# Create RL project with tools
rnow init --template rl-tools
# Create from tutorial
rnow init --template tutorial-reward
Generated Files
| Template | Files |
|---|---|
sft | config.yml, train.jsonl |
rl-single | config.yml, train.jsonl, rewards.py, requirements.txt |
rl-tools | config.yml, train.jsonl, rewards.py, tools.py, requirements.txt |
blank | config.yml |
rnow run
Submit project for training.
rnow run [OPTIONS]
| Option | Description |
|---|---|
--dir PATH | Project directory (default: current) |
--name NAME | Custom run name |
Required files:
config.yml- Configurationtrain.jsonl- Training datarewards.py- Reward functions (RL only)
Optional files:
tools.py- Tool definitionsrequirements.txt- Python dependencies
Example:
cd my-project
rnow run
# Output:
# Validating project...
# Uploading files...
# Starting run: run_abc123xyz
# View at: https://www.reinforcenow.ai/runs/run_abc123xyz
rnow stop
Cancel an active training run.
rnow stop RUN_ID
Example:
rnow stop run_abc123xyz
# Are you sure you want to stop run_abc123xyz? [y/N]: y
# Run stopped.
# Duration: 2h 15m
# Cost: $12.50
rnow test
Test RL rollouts locally before submitting.
rnow test [OPTIONS]
| Option | Default | Description |
|---|---|---|
-d, --dir PATH | . | Project directory |
-n, --num-rollouts N | 1 | Number of rollouts |
--entry INDICES | random | Test specific entries (e.g., "0,2,5") |
--model MODEL | config | Override model for testing |
Examples
Basic test:
rnow test
# Runs 1 rollout, shows reward breakdown
Multiple rollouts:
rnow test -n 5
Test specific entries:
rnow test --entry 0,3,7
# Tests entries at indices 0, 3, and 7 from train.jsonl
Override model:
rnow test --model gpt-5-nano -n 3
# Uses gpt-5-nano instead of config.model.path
Test Output
Rollout 1/3
Entry: 0
Prompt: What is 2+2?
Turn 1:
Assistant: The answer is 4.
Rewards:
accuracy: 1.0
format_check: 1.0
Total: 1.0
---
Rollout 2/3
...
rnow download
Download a trained model checkpoint.
rnow download RUN_ID [OPTIONS]
| Option | Default | Description |
|---|---|---|
-o, --output DIR | ./model | Output directory |
Example:
rnow download run_abc123xyz -o ./my-model
# Downloading checkpoint...
# Progress: 100%
# Saved to: ./my-model/
Score
Total Score
Based on repository quality metrics
SKILL.mdファイルが含まれている
ライセンスが設定されている
100文字以上の説明がある
GitHub Stars 100以上
3ヶ月以内に更新がある
10回以上フォークされている
オープンIssueが50未満
プログラミング言語が設定されている
1つ以上のタグが設定されている
Reviews
Reviews coming soon