AI & ML interests

Agent-to-agent payments, x402, stablecoins, AI agents, spend policy

Recent Activity

sriram1983007  updated a collection 3 days ago
Stablemode · Agent Payments
sriram1983007  updated a collection 3 days ago
Stablemode · Agent Payments
sriram1983007  updated a collection 3 days ago
Stablemode · Agent Payments
View all activity

sriram1983007 
updated a Space 3 days ago
sriram1983007 
published a Space 3 days ago
sriram1983007 
posted an update 8 days ago
view post
Post
3,879
Should an AI agent sign this payment?

I’ve released SRA-RiskGate-4B v2. It’s a 4B model fine-tuned from Qwen3-4B-Instruct that answers approve, hold or reject for stablecoin payments made by agents (x402, EIP-3009, Circle), and it settles payment disputes.

On 2,000 held-out benchmark cases:
✅ 99.6% of payment decisions correct (base model: 59.8%)
✅ 0.35% unsafe approvals (base model: 34.6%)
✅ 90.2% of dispute outcomes correct, up from 77.8% in v1

The main change in v2: the dispute window is computed in code and passed into the prompt instead of asking a 4B model to subtract dates. Wrongful denials fell from 26% to 2.1%.

I also tested it on 227 real USDC payments from Base mainnet: it blocked none of the 151 real payments and approved none of the risky ones.

The model isn’t the security boundary. The open-source checks in pip install sra-riskgate run first and fail closed, with optional Chainalysis, TRM, Range and Webacy screening.

These are my own numbers. Every prediction is public, so you can re-score them.

🤖 Model: hf.co/sriram1983007/SRA-RiskGate-4B
🎮 Try to trick it: hf.co/spaces/sriram1983007/sra-riskgate-demo
📊 Benchmark: hf.co/datasets/sriram1983007/sra-stablecoin-risk-bench
🧾 Real payments: hf.co/datasets/sriram1983007/sra-real
  • 2 replies
·
sriram1983007 
posted an update 21 days ago
view post
Post
136
Two live agent payment runs with SRA-RiskGate today, plus a day of real x402 data.

Circle Gateway on Arc testnet: one agent task, three proposed payments. One approved, accepted by Gateway and settled to the payee. An unlimited approval was held and a look-alike payee was rejected, neither signed.

Base Sepolia: 0.01 USDC to the known payee approved, sent and verified from the receipt. 2.00 USDC to an unknown payee held before signing. Log: https://gist.github.com/sriram1983007-dev/35eab0e934a512346193bcdb5b12d9cf

Real traffic: 1,500 x402 settlements sampled across 24 hours on Base mainnet. Median signature had under 5 minutes left at settlement, but 23 were still usable for 8 to 41 days, one for 273.75 USDC.

Model: sriram1983007/SRA-RiskGate-4B
  • 9 replies
·
sriram1983007 
posted an update 24 days ago
view post
Post
92
🛡️ AI agents now pay with USDC through Circle and Coinbase AgentKit, and those payments are final. SRA-RiskGate checks the exact bytes before the agent signs. If this is useful for your agent, a ❤️ like on this sriram1983007/SRA-RiskGate-4B page helps others find it.

• Circle Wallets: guard_circle_wallets() wraps Circle's SDK. On Arc Testnet, a USDC payment went through, while an unlimited approve, an unknown payee and an unlimited permit never reached Circle.

• Circle Gateway: batched x402 payments checked with their own 3–8 day window. A look-alike GatewayWallet and a 30-day signature were held.

• Coinbase AgentKit: one action provider as the agent's only way to pay, with OFAC, limits and depeg checks before USDC moves on Base.

• Also: EIP-7702 delegations, address-poisoning look-alikes, long-lived x402 signatures, self-vouching payment text.

Backed by SRA-RiskGate-4B (unsafe approvals 34.6% → 0.47% on a 20k-case benchmark).

pip install "sra-riskgate[circle,agentkit]"

Model: sriram1983007/SRA-RiskGate-4B
Code: https://github.com/sriram1983007-dev/sra-riskgate
Video: https://www.youtube.com/shorts/3OAEJKTi32s
  • 2 replies
·
sriram1983007 
posted an update 28 days ago
view post
Post
506
AI agents can now pay for APIs on their own with x402 and USDC. The risky moment is the signature: a stablecoin payment is final, and one "approve" can let someone drain the wallet later.

I wrote a short tutorial on three deterministic checks to run before an agent signs anything:

1. Decode the exact transaction and hold token approvals, including the unlimited approve() that drains agent wallets
2. Apply your own policy: amount limits, new payees, and payment text that vouches for itself
3. For x402, check the EIP-3009 signature itself, including how long it stays valid

All examples run as-is with an open-source Python library (sra-riskgate), and the same checks are available as an MCP server for Claude and Cursor.

The broader lesson from fine-tuning a model for this: let the model judge, and let code enforce.

https://dev.to/sriram1983007/stop-your-ai-agent-from-signing-an-unlimited-usdc-approval-10c0
Model: sriram1983007/SRA-RiskGate-4B
Video: https://www.youtube.com/shorts/3OAEJKTi32s
Demo: sriram1983007/sra-riskgate-demo

#AIagents #Stablecoins #x402 #AISafety #OpenSource
sriram1983007 
posted an update about 1 month ago
view post
Post
172
A 4B model that decides whether an AI agent’s payment should go through, with every prediction published so you can check the score yourself

AI agents are starting to pay for things on their own: x402 API calls, stablecoin transfers, token approvals. One bad approval can’t be reversed. So I fine-tuned a small model to sit in front of the payment tool and answer one question: approve, hold or reject?

Try it:

Free Colab notebook (T4 GPU), linked from the model card
GGUF + Ollama: sriram1983007/SRA-RiskGate-4B-GGUF
pip install sra-riskgate: a guard for x402 + Coinbase AgentKit
pip install sra-riskgate-mcp: an MCP server
pip install langchain-sra-riskgate: LangChain middleware

🔗 Model: sriram1983007/SRA-RiskGate-4B
🔗 Benchmark: data
🔗 Benchmark: sriram1983007/sra-stablecoin-risk-bench
🔗 Published predictions (re-score them yourself): sriram1983007/sra-bench-results
🔗 SDK (x402 + AgentKit): https://github.com/sriram1983007-dev/sra-riskgate
🔗 MCP server: https://github.com/sriram1983007-dev/sra-riskgate-mcp
🔗 LangChain middleware: https://github.com/sriram1983007-dev/langchain-sra-riskgate
🔗 Live demo: sriram1983007/sra-riskgate-demo
🔗 Try it free in Colab: use the “Open in Colab” badge link

SRA-RiskGate-4B reads the payment, the policy and the verification results, and returns a JSON verdict with flags and reasons.

On 1,175 held-out payment cases:

99.49% of decisions correct
Unsafe approvals: 4 of 847 (0.47%). The base model approved about 35%.
Legitimate payments wrongly blocked: 0 of 328
Also: 825 dispute cases at 77.8%, with impossible on-chain remedies proposed only 0.38% of the time

Also be aware: the benchmark is synthetic. How the model handles real-world attacks it has never seen is still an open question, and that’s what the next version of the benchmark will test.

Check the numbers yourself: every prediction from two full runs is public, and the benchmark has an eval.yaml for Community Evals.
sriram1983007 
posted an update about 2 months ago
sriram1983007 
posted an update about 2 months ago
view post
Post
3,779
🛡️ SRA-RiskGate-4B is Live on ZeroGPU - Stablecoin - Risk Decision Engine & Dispute Lifecycle Agent

A domain-specialized 4B neural firewall fine-tuned for stablecoin rails (EIP-3009, x402, AgentKit) to gate payments (approve / hold / reject) and resolve disputes deterministically.

Live Demo: sriram1983007/sra-riskgate-demo

Agent Protocol: Ready for coding agents via curl -s sriram1983007/sra-riskgate-demo

Artifacts:

Model: sriram1983007/SRA-RiskGate-4B

GGUF: sriram1983007/SRA-RiskGate-4B-Q4_K_M-GGUF

Benchmark: sriram1983007/sra-stablecoin-risk-bench

SDK: pip install sra-riskgate

Feedback and edge-case submissions welcome!
  • 9 replies
·