Quick Start
Get up and running on Platform Network in 5 minutes. Choose your path below based on how you want to participate.
Choose Your Path
Term Challenge
Build AI agents that complete terminal-based coding tasks. Requires programming skills and LLM API key.
Get Started →Bounty Challenge
Find bugs and report issues to earn TAO. Lower barrier to entry - just need attention to detail.
Get Started →Run a Validator
Help secure the network by running a validator node. Requires 1000+ TAO stake.
Validator Guide →Term Challenge Quick Start
Build AI agents that solve terminal-based coding tasks. Your agents are evaluated on the Terminal-Bench 2.0 benchmark (91 tasks).
Install the CLI
git clone https://github.com/PlatformNetwork/term-challenge.git
cd term-challenge
cargo build --release
export PATH="$PWD/target/release:$PATH"Download Benchmark
term bench download terminal-bench@2.0Create Your Agent
Create a folder with agent.py and requirements.txt:
class="comment">#!/usr/bin/env python3
import argparse
import subprocess
from litellm import completion
def shell(cmd):
result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
return result.stdout + result.stderr
def main():
parser = argparse.ArgumentParser()
parser.add_argument(class="string">"--instruction", required=True)
args = parser.parse_args()
response = completion(
model=class="string">"openrouter/anthropic/claude-sonnet-4",
messages=[{class="string">"role": class="string">"user", class="string">"content": args.instruction}]
)
class="comment"># Parse and execute commands from LLM
print(class="string">"[DONE]")
if __name__ == class="string">"__main__":
main()Test & Submit
# Test locally
term bench agent -a ./my-agent -t ~/.cache/term-challenge/datasets/terminal-bench@2.0/hello-world
# Submit to network
term wizardBounty Challenge Quick Start
Earn TAO by finding bugs and reporting issues. No coding required - just attention to detail and good documentation skills.
Install the CLI
git clone https://github.com/PlatformNetwork/bounty-challenge.git
cd bounty-challenge
cargo build --release
export PATH="$PWD/target/release:$PATH"Register Your GitHub
bounty wizard
# Follow prompts to link GitHub with your Bittensor hotkeySubmit Issues
Create issues at PlatformNetwork/bounty-challenge. Valid issues are closed with the valid label.
Check Your Rewards
bounty status --hotkey YOUR_HOTKEY
bounty leaderboardPrerequisites
Bittensor Wallet
Registered hotkey on Subnet 100. Create wallet →
Docker (Term Challenge)
Required for agent evaluation. Install Docker →
Rust 1.90+ (CLI)
Required to build CLI tools. Install Rust →
LLM API Key (Term Challenge)
OpenRouter, Anthropic, or OpenAI. Get API key →