Metadata-Version: 2.4
Name: sentinel-agentkit-provider
Version: 1.0.0
Summary: AgentKit action provider for SENTINEL — pre-execution transaction safety oracle for autonomous AI agents, paid via x402 on Base
Author-email: SENTINEL <iv@sentinel-agent.dev>
License: MIT
Project-URL: Homepage, https://sentinel-agent.dev
Project-URL: Documentation, https://sentinel-agent.dev/llms.txt
Project-URL: Methodology, https://sentinel-agent.dev/methodology
Project-URL: Stats, https://sentinel-agent.dev/stats
Keywords: agentkit,x402,coinbase,ai-agent,security,web3
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: coinbase-agentkit>=0.5.0
Requires-Dist: httpx>=0.27.0
Requires-Dist: pydantic>=2.0.0

# sentinel-agentkit-provider

AgentKit action provider for [SENTINEL](https://sentinel-agent.dev) — a pre-execution
transaction safety oracle for autonomous AI agents. Lets any AgentKit-powered agent
check whether a transaction is safe to sign, *before* signing it, and pays for the
check autonomously via [x402](https://x402.org) — no human in the loop, no API key,
no subscription.

**Independent, standalone package.** Not part of the official
[coinbase/agentkit](https://github.com/coinbase/agentkit) monorepo, and not intended
to be submitted there. Install and use directly.

## What it checks

- Contract security (honeypots, hidden owner/mint functions, proxy patterns, etc.)
- Transaction simulation (does the call actually succeed)
- For ambiguous cases: a second opinion from an LLM council (Claude + GPT-4o-mini)
- Prior history: has this exact contract been flagged before, by any other agent?
- Deployer wallet track record (transaction count as a freshness signal)

Returns a `SAFE` / `UNSAFE` / `UNKNOWN` verdict, a 0–100 risk score, and a
cryptographically signed (ed25519) receipt.

## Install

```bash
pip install sentinel-agentkit-provider
```

## Usage

```python
from coinbase_agentkit import AgentKit, AgentKitConfig
from sentinel_agentkit_provider import sentinel_action_provider

agent_kit = AgentKit(AgentKitConfig(
    wallet_provider=wallet_provider,  # any EVM wallet provider on Base
    action_providers=[
        sentinel_action_provider(),
        # ... your other action providers
    ],
))
```

Once registered, your agent gains a `check_transaction_safety` action it can call
before signing any transaction with an unfamiliar contract address on Base:

```
check_transaction_safety(to="0x...", value="0x0", data="0x...")
```

## Cost

$0.005 USDC per check, on Base mainnet, paid automatically via x402 from the
agent's own wallet. No trial, no free tier — the price itself is the friction,
by design.

## Links

- [Live methodology](https://sentinel-agent.dev/methodology) — exactly how a
  verdict is computed, published and machine-readable.
- [Aggregate stats](https://sentinel-agent.dev/stats) — track record across all
  callers, updated live.
- [Report an outcome](https://sentinel-agent.dev/v1/outcome) — free endpoint to
  report back what actually happened after acting on a verdict.

## License

MIT
