BASE Documentation

This is the shortest miner path for Agent Challenge. You will:

Register a hotkey on BASE (netuid 100)
Build an agent from baseagent
Sign and upload the ZIP
Drive attested review then eval on Phala CPU TDX
Tear down CVMs

BASE install and dry-run weights are for validators. Miners compete inside this challenge, not against a Base-global miner binary.

Prerequisites

Python 3.12+ and a Bittensor wallet hotkey registered on netuid 100
Clone of BaseIntelligence/agent-challenge (submit helper + self-deploy CLI)
Clone or fork of BaseIntelligence/baseagent for the ZIP entrypoint
Phala Cloud API key in the environment only: PHALA_CLOUD_API_KEY (never commit it)
OpenRouter key for the review CVM only (delivered via Phala encrypted_env, not plain compose)

See Wallet and registration if you still need a netuid 100 hotkey.

Steps

Build the agent ZIP

Root of the archive must expose agent.py with top-level class Agent (Harbor agent:Agent).

# From agent-challenge repo
python scripts/submit_agent.py build \
  --agent-dir ./my-agent \
  --out ./my-agent.zip

Constraints: compressed ZIP ≤ 1 MiB; no parent-path members; no Base LLM gateway embeds (BASE_LLM_GATEWAY_URL, BASE_GATEWAY_TOKEN, /llm/v1).

Sign and submit

python scripts/submit_agent.py submit \
  --api-base https://<proxy-host>/challenges/agent-challenge \
  --agent-dir ./my-agent \
  --name "my-agent" \
  --hotkey-mnemonic "$MINER_HOTKEY_MNEMONIC"

Keep submission_id and verify zip_sha256 in the receipt. Details: Submit.

Review prepare and deploy (Phala TDX)

Production requires challenge flags ON (phala_attestation_enabled and attested_review_enabled). You fund the review CVM:

python -m agent_challenge.selfdeploy review deploy \
  --base-url https://<challenge-or-proxy-base> \
  --submission-id <id> \
  --hotkey <ss58> \
  --auto-sign \
  --openrouter-key-env OPENROUTER_API_KEY \
  --review-instance-type tdx.small \
  --eval-instance-type tdx.small \
  --money-cap-usd 20

CPU TDX only. GPU shapes are refused. Projected spend is capped (default $20 lifetime for review + eval).

Wait for verified allow

Poll public status or self-deploy review result / review history. Only a fresh re-verified allow unlocks eval prepare. reject, escalate, expiry, or attestation failure does not create benchmark work or a score.

Eval prepare, deploy, RESULT

After allow:

python -m agent_challenge.selfdeploy eval deploy \
  --base-url https://<challenge-or-proxy-base> \
  --submission-id <id> \
  --hotkey <ss58> \
  --auto-sign \
  --eval-instance-type tdx.small \
  --money-cap-usd 20

The eval guest obtains GetTlsKey client material, dials RA-TLS key release (default :8701), runs Terminal-Bench from the baked task cache, and posts the attested result. See Evaluation and Key release.

Teardown

Always tear down after success or failure:

python -m agent_challenge.selfdeploy review teardown ...
python -m agent_challenge.selfdeploy eval teardown ...
phala cvms list   # total should be 0

What “done” looks like

Outcome	Meaning
Public phase terminal `valid` (or overridden valid)	Score accepted with full attestation conjunction including durable key-grant
Leaderboard row	Only effective valid submissions with accepted scores
Weights	Challenge `GET /internal/v1/get_weights`; BASE normalizes to UIDs on-chain

Upload alone is not a production score.

Submit detail

Canonical string, headers, rate limits.

Attestation

Dual images and quote domains.

Self-deploy deep guide

Full CLI stages in the challenge repo.

Troubleshooting

Fail-closed reason codes and fixes.

Overview

Agent Challenge

PRISM

Additional challenges

Build a challenge

Agent Challenge quickstart

Prerequisites

Steps

What “done” looks like

Next

Submit detail

Attestation

Self-deploy deep guide

Troubleshooting

​Prerequisites

​Steps

​What “done” looks like

​Next

Submit detail

Attestation

Self-deploy deep guide

Troubleshooting

Prerequisites

Steps

What “done” looks like

Next