Partha Mehta's profile on Product Hunt

About

• Software, AI & Data Engineer with 5+ years of experience building cloud-scale data platforms, distributed systems, and AI-powered applications. • Currently building AI agents, RAG systems, MCP servers, and security tooling for autonomous AI workflows. Previously worked across cybersecurity, cloud infrastructure, data engineering, and machine learning, delivering production systems using Python, Go, PySpark, AWS, Databricks, Kubernetes, and Terraform. • Interested in AI agents, AI security, observability, developer tools, LLM infrastructure, and open-source products. Always exploring ways to make AI systems more secure, reliable, and useful in real-world environments.

Links

Badges

Tastemaker

Gone streaking 10

Gone streaking

Gone streaking 5

Maker History

OpenClaw LLM ProxyScan every LLM API call for PII and injection attacks
Jun 2026
SentinelAI agent security platform, install once, protect everything
Apr 2026
Breach Intel — Agent SecurityThe audit layer for AI agents — zero code changes
Apr 2026
SuperfastClaw with security inbuiltA AI gateway. One binary.10 channels.infinite reach.
Apr 2026
Email IntelligenceAI reads your Gmail and turns every email into clear tasks
Mar 2026

Forums

p/openclaw-llm-proxy

•

2mo ago

Launching Tuesday - what security layer do you use for LLM API calls?

We're launching OpenClaw LLM Proxy on Tuesday at 12:01 AM PDT - a drop-in OpenAI API replacement with built-in PII scanning and injection detection.

Curious to hear from the community before we go live: when you send prompts to OpenAI/Anthropic/Google, is there anything scanning for sensitive data before it reaches the provider?

•

1mo ago

OpenClaw LLM Proxy - Scan every LLM API call for PII and injection attacks

OpenClaw sits between your app and any LLM provider. Every prompt is scanned for PII (SSN, credit cards, API keys) and injection attacks before reaching the model. Every response is scanned for data leaks. Routes across 6 backends (OpenAI, Anthropic, Google, Ollama, vLLM) by model prefix. Block, redact, or log - your choice. Multi-tenancy with per-team budgets. Spend tracking. Response caching. Prometheus metrics. Helm chart. 113 tests. One Docker command.

•

2mo ago

Show PH: OpenClaw - LLM proxy with built-in PII scanning

Hey PH! We're building OpenClaw LLM Proxy and would love early feedback.

It's a drop-in OpenAI API replacement that scans every prompt and response for PII (SSN, credit cards, API keys) and injection attacks before they reach the provider. Block, redact, or log.