All activity
Nipun AI is a stock analysis tool that gives you a 25 section research report. Works for both Indian and US stocks.
The thing that makes it different from Screener.in or Moneycontrol - it runs three AI models, generates valuation estimates using 3 different methods, fact-checks its own output, and gives you insider trading data and institutional ownership in one place.
It's completely free. Uses free-tier APIs. Your API keys are encrypted locally with AES-256 and never leave your browser.

Nipun AIOpen-source Bloomberg alternative - runs locally, zero cost
Rleft a comment
Hey, I built a open source alternative to Bloomberg terminal and it runs with just one command. I've been building this for a few months and finally feel good enough about it to share. Nipun AI is a stock analysis tool that generates a 25-section report with 55+ data dimensions. Think of it like getting a Bloomberg-level research report, but it runs locally on your machine and uses free-tier...

Nipun AIOpen-source Bloomberg alternative - runs locally, zero cost
Open-source AI security firewall.
81 engines for PII detection, prompt injection defense, MCP security, and egress classification.
Local-first.
Zero cloud dependency.
Zero telemetry.
Zero trust violations.

Sentinel ProtocolOpen Source Local AI Firewall
Rleft a comment
I built a deterministic prompt optimizer that cuts AI token usage by ~30% without changing the meaning. It’s free to try in the browser. It might help drop that bill. Link: risk-mirror.vercel.app

Risk MirrorAI Security, Without the Hallucinations
Rleft a comment
Introducing Risk Mirror The safe and secure way to use AI in 2026 - No infra, No extra tools, just safer output. Copy, sanitize, paste - done. Built for AI users

Risk MirrorAI Security, Without the Hallucinations
Rleft a comment
Stop burning $20/mo on Claude credits. I unlocked the Prompt Optimizer for free. If you're hitting the message cap on Claude/Cursor, you're sending too much fluff. "Please", "Thank you," and verbose context contexts are eating 30% of your token budget. I built Risk Mirror to mathematically compress prompts (removing filler, preserving logic). It’s usually a Pro feature, but is completely free...

Risk MirrorAI Security, Without the Hallucinations
It sits between your users and your LLM (OpenAI/Anthropic) and strips out sensitive data before it leaves your server.
The Tech (Zero AI Inference): Instead of asking an LLM "is this safe?", I use:
152 PII Types: My custom engine covers everything from US Social Security Numbers to Indian Aadhaar cards and HIPAA identifiers.
Shannon Entropy: To detect high-entropy strings (API keys, passwords) that regex misses.
Deterministic Rules: 100% consistency. No "maybe."

Risk MirrorAI Security, Without the Hallucinations
Rleft a comment
I previously built the PII Firewall Edge API to handle high-fidelity PII detection without using ML models. Then I decided to package my API into a full-featured UI/Toolkit called Risk Mirror. AI Safety should be deterministic. If you rely on an LLM to police another LLM, you are stacking probability error rates (99% * 99% = 98%). What it does: It sits between your users and your LLM...

Risk MirrorAI Security, Without the Hallucinations
Rleft a comment
🔐 What we do differently: • 150+ PII types detected (SSN, AADHAAR, passport numbers, API keys, etc.) • Sub 10ms latency (edge-processed, not cloud queued) • Zero logs, zero storage. Your data never touches a database. • No AI/ML. Pure regex + validation (we don't send your data to another LLM) 💰 Developer-friendly pricing: • $5/mo PRO (10K calls) • $10/mo ULTRA (50K calls) • $25/mo MEGA (250K...

PII Firewall EdgeStop PII from leaking to LLMs—one API call
Building with AI? Your users' data is at risk.
Every API call to OpenAI, Claude, or Gemini could be leaking SSNs, emails, phone numbers, and 150+ types of PII. Compliance teams are waking up to this. Are you ready?
PII Firewall Edge is a zero AI, zero-storage privacy API that runs on Cloudflare's edge network. One API call sanitizes text before it hits any LLM.

PII Firewall EdgeStop PII from leaking to LLMs—one API call
