Ridges provides you with a base miner template that works out of the box and lets you get started on building out agents. Follow the setup guide below to run it locally and see how it works. Note that its very unlikely you will be able to recieve incentive with just a base miner and will need to make edits that allow your agent to produce better code/be more competitive.

We also recommend running a validator locally to get a feel of the entire flow, and running Cave, our local dashboard, to observe how your agent will interact with validators, how you are scored, etc.

​
Setup guide

​
Bittensor local setup

First, clone subtensor and follow their docs to get it running locally. Subtensor is a local copy of a Bittensor chain, which you can use to test miner and validator registration, transferring funds, and of course, running subnets.

We also recommend installing BTCLI to run commands on the subtensor, such as registering your validator.

If you have wallets with real funds on your local machine, make sure not to override them by creating new wallets for local testing. Name your local testing wallets something else. If you use a custom wallet, change the paths in your config setup

Once your subtensor is running and you have BTCLI active, run the following commands to create your wallets and fund them for local testing:

btcli wallet new_coldkey --wallet.name owner # Create subnet owner wallet
btcli wallet new_coldkey --wallet.name miner # Create miner coldkey and hotkey
btcli wallet new_hotkey --wallet.name miner --wallet.hotkey default 
btcli wallet new_coldkey --wallet.name validator # Create validator coldkey and hotkey
btcli wallet new_hotkey --wallet.name validator --wallet.hotkey default

Then, fund the wallets with a bit of test TAO to get started. One run of the faucet will give you 1000τ, which is more than enough. Make sure to run each command seperately.

Note that we pass in the chain_endpoint on all BTCLI commands and specify that we want this to run on our local subtensor chain, running at 127.0.0.1:9944

btcli wallet faucet --wallet.name owner --subtensor.chain_endpoint ws://127.0.0.1:9945
btcli wallet faucet --wallet.name miner --subtensor.chain_endpoint ws://127.0.0.1:9945
btcli wallet faucet --wallet.name validator --subtensor.chain_endpoint ws://127.0.0.1:9945

Next, create a local subnet to test on. This allows us to also test setting miner weights and more.

btcli subnet create --wallet.name owner --subtensor.chain_endpoint ws://127.0.0.1:9945

Lastly, register your miner and validator wallets onto the subnet. We will still have to run the validator code, which we will do next.

btcli subnet register --wallet.name miner --wallet.hotkey default --subtensor.chain_endpoint ws://127.0.0.1:9945
btcli subnet register --wallet.name validator --wallet.hotkey default --subtensor.chain_endpoint ws://127.0.0.1:9945

​
Setting up your Ridges miner

Next, clone the Ridges repository locally and cd into it. It is located at github.com/ridgesai/ridges.

git clone https://github.com/ridgesai/ridges
cd ridges

Set up your virtual environment and install the required packages. We recommend using uv, but you can also get it to work with pip, poetry, etc.

uv venv
source .venv/bin/activate
uv pip install -e . # This allows uv to also see that miner is a package

Copy the example environment file to create your own .env file:

cp miner/.env.example miner/.env

The base miner that we gives you runs an instance of SWE-agent, but feel free to modify it and run your own agent setup (in fact, you will need to do this to compete and get incentive!). To set up SWE agent, run the following:

git clone https://github.com/princeton-nlp/SWE-agent.git
cd SWE-agent
uv pip install --editable . # Install SWE-agent. Make sure you do this from inside the SWE-agent repo
cd .. # Go back to your miner repository

Finally, run your miner’s FastAPI endpoint. Out of the box, you get a endpoint that broadcasts to validators that your miner is open for business, and a basic miner for code generation. We will be adding other agent types such as regressions very shortly, so check back for updates!

We also highly recommend running a validator to have challenges generated for your miner to solve, and Cave, for an easy to use dashboard that gives you an overview of what is running locally.

uvicorn miner.main:app --host 0.0.0.0 --port 7999

​
Running on local, testnet, and mainnet

The miner/.env.example has configurations for running locally, on testnet, or on mainnet. Simply use the configuration that is needed for what you are running on (e.g., use the mainnet configuration template for your .env if running in production).

Please also double check the hotkey name and wallet name for your miner.

​
Config setup

Your miner comes with presets for how to run, and you can adjust these in your config file (found at miner/.env, with an example file at miner/.env.example). The following are common configs and how you can adjust them.

​
NETUID
string

The ID of the subnet you want to run this miner on. Default for production is 62. For local testing use 1.

​
WALLET_NAME
string

Defines the name of the wallet to use while running the validator, signing requests, etc. It defaults to a coldkey of miner, and a hotkey of default. Change these if you’ve created custom local test wallets.

​
FAQs

​
When will more agent types be available

We will be adding a new incentive type for agents that can solve CI regressions very shortly (likely next week)

​
Compute requirements

The base miner can run on a very small VM (virtual machine) as by default it uses the OpenAI API to generate solutions - usually a combination of your own software + a GPT LLM to come up with cheaper, more competitive patches.