DEV Community

Neeraj Sharma profile picture

Neeraj Sharma

Founder @ axionry.com: AI products, agents and MVPs shipped in days, $0 upfront. Book a call: axionry.com/book | X & IG @axionry_

Location India Joined Joined on  Personal website https://axionry.com/

Work

Founder @ Axionry | Head of Engineering @ AccioJob (YC '19)

Catching wrong-voice lines in AI-generated video with 60 lines of Python

Catching wrong-voice lines in AI-generated video with 60 lines of Python

Comments
4 min read
Architecture of a Multi-Tenant Private ChatGPT SaaS on LibreChat: Silo Tenants, Seat Billing and Token Caps

Architecture of a Multi-Tenant Private ChatGPT SaaS on LibreChat: Silo Tenants, Seat Billing and Token Caps

Comments
6 min read
How to Build Your Own Team ChatGPT With LibreChat, Claude and MCP (Pay per Token, Not per Seat)

How to Build Your Own Team ChatGPT With LibreChat, Claude and MCP (Pay per Token, Not per Seat)

Comments
5 min read
How to Build a Manus-Style AI Employee With Claude, OpenClaw, Lightpanda and Mem0

How to Build a Manus-Style AI Employee With Claude, OpenClaw, Lightpanda and Mem0

Comments
3 min read
Cursor Sold for $60B and Lovable Hit $13.3B: What It Means for How We Build AI Products

Cursor Sold for $60B and Lovable Hit $13.3B: What It Means for How We Build AI Products

Comments
4 min read
Build an AI Receptionist With Whisper, Claude, Chatterbox and LiveKit: Architecture, Latency Budget and Starter Code

Build an AI Receptionist With Whisper, Claude, Chatterbox and LiveKit: Architecture, Latency Budget and Starter Code

Comments
4 min read
n8n or Activepieces? Building a Multi-Tenant AI Automation Product Without Breaking the License

n8n or Activepieces? Building a Multi-Tenant AI Automation Product Without Breaking the License

Comments
5 min read
Your Voice Agent Needs a Flight Simulator Before It Gets a Phone Number

Your Voice Agent Needs a Flight Simulator Before It Gets a Phone Number

Comments
5 min read
Stop Spending a Full LLM Call on a Yes or No Question: OpenAI's Decisions API, Explained

Stop Spending a Full LLM Call on a Yes or No Question: OpenAI's Decisions API, Explained

1
Comments
4 min read
Your Voice Agent Isn't Slow. It's Silent. Non-Blocking Tools, Explained.

Your Voice Agent Isn't Slow. It's Silent. Non-Blocking Tools, Explained.

Comments
5 min read
Agent Skills Is Now a Linux Foundation Standard. My 113-Line Loader Cuts Prompt Tokens 56 to 81%

Agent Skills Is Now a Linux Foundation Standard. My 113-Line Loader Cuts Prompt Tokens 56 to 81%

Comments
10 min read
98% of Battle Drones Was Written by Claude: I Audited 334 Commits With 140 Lines of Python

98% of Battle Drones Was Written by Claude: I Audited 334 Commits With 140 Lines of Python

Comments
11 min read
Python requests and Node fetch still trusted eMudhra's compromised CAs on my machine. A 151-line check

Python requests and Node fetch still trusted eMudhra's compromised CAs on my machine. A 151-line check

Comments 1
8 min read
The OVHcloud CLI Swap Left a Fingerprint: A Script to Check Your Go Binaries

The OVHcloud CLI Swap Left a Fingerprint: A Script to Check Your Go Binaries

Comments
10 min read
Meta Said a Claude Tool Browsed at 4x Human Speed. Here's a 124-Line Python Fix for Impolite AI Agents

Meta Said a Claude Tool Browsed at 4x Human Speed. Here's a 124-Line Python Fix for Impolite AI Agents

Comments
10 min read
Stolen LLM keys ran up OpenCode users' bills overnight. A 115-line proxy that caps spend per app

Stolen LLM keys ran up OpenCode users' bills overnight. A 115-line proxy that caps spend per app

Comments
7 min read
GhostAction hit 30,000 repos this month. A 150-line script to check yours, and what to rotate

GhostAction hit 30,000 repos this month. A 150-line script to check yours, and what to rotate

Comments
9 min read
Your traffic spike might be one AI newsletter bot: find it, verify crawlers, rate-limit the rest

Your traffic spike might be one AI newsletter bot: find it, verify crawlers, rate-limit the rest

Comments
9 min read
Your AI coding CLI may still be running after you close it: I reproduced the Codex daemon and wrote an audit

Your AI coding CLI may still be running after you close it: I reproduced the Codex daemon and wrote an audit

1
Comments
5 min read
Passkeys are a trap? I decoded two real ones to see what a website learns

Passkeys are a trap? I decoded two real ones to see what a website learns

2
Comments 1
5 min read
Python 3.15 lazy imports took my cold start from 512 ms to 32 ms

Python 3.15 lazy imports took my cold start from 512 ms to 32 ms

1
Comments
4 min read
An offline voice agent for my terminal in 52 MB (Whistle + Needle)

An offline voice agent for my terminal in 52 MB (Whistle + Needle)

2
Comments 2
6 min read
Find the AWS waste in one afternoon: 7 read-only CLI checks

Find the AWS waste in one afternoon: 7 read-only CLI checks

2
Comments 1
5 min read
What an investor's engineer checks in your codebase before a round

What an investor's engineer checks in your codebase before a round

Comments
3 min read
Showing live voice agent transcripts in a Flutter app with LiveKit

Showing live voice agent transcripts in a Flutter app with LiveKit

Comments
3 min read
Estimate your AI feature's model bill before you build it

Estimate your AI feature's model bill before you build it

Comments
2 min read
Our voice agent costs 2.5¢ a minute. Here's the whole bill.

Our voice agent costs 2.5¢ a minute. Here's the whole bill.

Comments
2 min read
Why your NAT gateway bill keeps growing (and the 20 minute fix)

Why your NAT gateway bill keeps growing (and the 20 minute fix)

3
Comments 2
3 min read
loading...