Skip to Content
DocumentationIntroduction

Aether Forge

Spec-first agent builder framework. Idea to governed, testable, production-capable agent in one CLI.

# Install from GitHub (not yet on PyPI)
pip install 'aether-forge[all] @ git+https://github.com/HeyElsa/aether-forge.git'
 
# Or clone and install locally
git clone https://github.com/HeyElsa/aether-forge.git
cd aether-forge
pip install -e '.[all]'

What is Aether Forge?

Building autonomous agents today means scattered configs, no policy enforcement, untested deployments, and zero auditability. Moving to production is a leap of faith.

Aether Forge gives every agent a governed lifecycle: typed specs, policy-checked execution, scenario-driven evaluation, and evidence-backed promotion from sandbox to production.

Every tick, an LLM re-reads your plain-English strategy, picks from declared capabilities, and emits typed steps the runtime executes against four layers of memory.

Key Features

FeatureWhat it does
LLM-DrivenAuto-detect Ollama, Claude, GPT, Gemini, or OpenRouter. Any model, hot-swappable.
Real WalletsOWS across 9 chain families with encrypted AES-256-GCM backups
A2A ProtocolAgent-to-agent task delegation via Google’s A2A (JSON-RPC over HTTP)
x402 PaymentsAgents send AND receive USDC on Base mainnet via EIP-3009
MCP ToolsConsume any Model Context Protocol server — filesystem, GitHub, messaging
On-Chain IDERC-8004 Agent NFT on Base mainnet. 61,000+ agents in the registry
4-Layer MemoryReplays, working set, SQLite diary, MemPalace knowledge graph
SecurityAES-256-GCM backups, prompt injection scanning, kill switch, 8-point audit
AutoresearchKarpathy keep-or-discard loop for runtime strategy self-improvement

Quick Example

# Generate an agent with a strategy file
forge generate-fast \
  --name "ETH Swing Trader" \
  --strategy-file strategy.md \
  --wallet --autonomous \
  --output ./my-agent
 
# Validate all artifacts
forge validate ./my-agent
 
# Paper trade with real prices
forge run ./my-agent --mode paper --auto-approve --autoresearch
 
# Go live on Base mainnet
forge run ./my-agent --mode live --chain base

Architecture

Every agent action flows through the same governed pipeline:

Planner ──▶ Policy Gate ──▶ Execute ──▶ Step Ledger
   ^                                        │
   └──────── loop (max 20 steps) ───────────┘
  • Planner proposes next steps (LLM-driven by default)
  • Policy Gate evaluates rules: environment, notional limits, wallet chains, approvals
  • Execute runs the capability via the appropriate router
  • Ledger records every step for audit, replay, and resumption

Side-effecting capabilities default to deny until policy explicitly allows.

Last updated on
Getting Started