← Back to Docs

Quick Start Guide

Prerequisites

  • •Rust 1.70+ - For core blockchain implementation
  • •Go 1.21+ - For additional tooling
  • •Docker - For containerized development
  • •16GB+ RAM - For model inference

Installation

1. Clone the Repository

# Clone from GitHub
git clone https://github.com/ob-theseus/theseuschain.git
cd theseuschain

2. Build Dependencies

# Install development dependencies
make install-dev
# Build in release mode
cargo build --release

3. Run a Local Node

# Start the Theseus node
cargo run --bin theseus-node

Your node will start syncing with the network. The first sync may take some time depending on network conditions and chain history.

Deploy Your First Agent

Once your node is running, you can deploy a test agent using the Theseus CLI and SHIP language.

Example: Basic Agent

# Deploy from example
cargo run --bin theseus-cli deploy-agent examples/basic-agent.ship

This deploys a simple autonomous agent that can hold $THE tokens and interact with other agents on the network.

Agent Registration Fields

Code hash:Verifies the binary that will run on AIVM/HVM
Autonomy flag:0 = human-gated, 1 = sovereign
Controller key:Optional public key for human overrides
Min AIVM version:Signals which ISA features the agent requires
Resource quota:Max FLOPs it may consume per epoch
Stake:$THE locked for potential slashing
Initial Context:Context that empowers the agent, linked to TheseusStore

Register a Model

Models are registered separately from agents and can be invoked by any agent that pays the inference fee.

Model Registration Fields

Name & version:e.g., Llama 3.1 8B
Architecture tag:LLM, diffusion, GAN, etc.
Tensor Commit:Cryptographic fingerprint of the weights
Param count:Used for fee estimation
Base fee:$THE per inference
Owner:Address or DAO receiving revenue
Weights URI:Where validators can fetch parameters
# Register a model
theseus-cli register-model \
--name "Llama-3.1-8B" \
--weights ./models/llama-8b.safetensors \
--base-fee 100

Development Workflow

1.
Write agent logic in SHIP (Domain Specific Language) or directly in AIVM opcodes
2.
Test locally using the development node
3.
Deploy to testnet for multi-agent interaction testing
4.
Audit and verify using Tensor Commit proofs
5.
Launch on mainnet with appropriate stake

Running Tests

# Run full test suite
make test
# Run specific tests
cargo test --package aivm
cargo test --package tensor-commits

Next Steps

Build Agents →

Learn how to create sophisticated autonomous agents

SHIP Language →

Master the Domain Specific Language for AI

AIVM Deep Dive →

Understand the AI Virtual Machine internals

Tensor Commits →

Learn about verifiable ML inference

Need help? Visit our GitHub or read the full whitepaper.