Quickstart
Get a Blindference node running and earning in under 5 minutes.Prerequisites
- Python 3.10 or higher
- pip (Python package manager)
- A terminal with internet access
- No GPU required for mock inference
Step 1: Install
Step 2: Initialize
- Detects env vars — if
BLF_PRIVATE_KEYis set, auto-imports wallet (no prompt) - Detects GPU — checks for NVIDIA GPU and vLLM availability
- Detects API keys — if
GROQ_API_KEYorGOOGLE_API_KEYset, includes cloud models - Prompts only what’s missing — wallet creation, password, API keys
- Saves configuration — writes
~/.blindference/config.json
Example Output
Step 3: Attest Your Node
Before running, you must attest your node with the ICL:Interactive Attestation Flow
- Option 1 (Mock): Uses
weloveblindferencekey — fastest, no hardware needed - Option 2 (TEE): For production hardware attestation (SGX/TDX/TPM)
On-Chain Registration (Optional)
After ICL attestation, the CLI asks:Example Output
Step 4: Start the Daemon
| Loop | Frequency | Purpose |
|---|---|---|
| ICL Heartbeat | Every 60s | Proves liveness to ICL (free REST call) |
| On-Chain Heartbeat | Every 10 days | Proves liveness to NodeRegistry (gas tx) |
| Attestation Watchdog | Every 10min | Auto-re-attests if certificate expires within 6h |
| Assignment Poller | Every 5s | Polls ICL for pending inference jobs |
Example Output
Step 4: Verify
Check that your node is registered:Next Steps
Configuration
Customize node settings, models, and endpoints
Attestation
Learn about attestation tiers and hardware requirements