Lander

Hi everyone, I just launched Phaeton — a privacy app for sending encrypted messages that vanish after viewing. • End-to-end encryption • No accounts, no tracking • Burn-after-read, password, view limits Try it: phaeton-five.vercel.app #security #webdeveloper #buildinpublic

I built HookCheck Scans your dependency files and flags risky packages + known CVEs No server. No uploads. Everything runs in your browser hookcheckv2.vercel.app #buildinpublic #opensource #webdev #cybersecurity

@code_codeforge this is mine: hookcheckv2.vercel.app It's a package scanner which scans each package in your manifests and tells you all the CVEs and issues in each of package.

Drop your project URL Let’s drive some traffic

Here are the 3 Core Pillars of Every AI Agent's Context Here's why MCP, RAG and Skills are now unavoidable... Before we dive in, here's why all 3 exist in the first place: Every AI Agent struggles with 3 core problems: - Connecting to external tools requires writing custom API code every time - Answering accurately from knowledge it was never trained on - Repeating the same instructions in prompts; wasting tokens on every single call MCP, RAG, and Skills were each built to solve exactly one of these problems. 📌 1\ MCP (Model Context Protocol) MCP eliminates the need to write custom API integration code every time your agent needs to connect to an external tool. How it works: - User sends a query → MCP Client selects the right server - LLM processes the request and routes it to the MCP Server - Server (Slack, Qdrant, Brave Search) responds with the relevant data - Final output is returned back to the user Key insight: Without MCP, every new tool connection means new custom code. With MCP, your agent plugs into any server through one standardized protocol. Use when: You want your agent to access external tools and services without rebuilding integrations from scratch each time. 📌 2\ RAG (Retrieval Augmented Generation) RAG gives your agent memory-enabled retrieval, so it reasons over knowledge it was never trained on, instead of hallucinating answers. How it works: - Data sources are chunked → converted into embeddings - Stored as dense vectors inside a Vector DB - User query triggers a search → most relevant chunks are retrieved - Retrieved info + query + system prompt → fed into the LLM → Output Key insight: Without RAG, agents confidently make things up. With RAG, they retrieve first, then reason. Use when: You want your agent to reason over large, dynamic knowledge bases with accuracy and context. 📌 3\ Agent Skills Skills stop your agent from wasting tokens by repeating the same instructions in every single prompt. How it works: - User query → LLM sends a Skill Request to the Skill Manager - Skill Manager retrieves the right skill using stored prompts and actions - Tools like Git, Docker, Python Interpreter, and Shell are triggered - Skill data flows back to the LLM → Final Output is delivered Key insight: Without Skills, you bloat every prompt with repeated instructions. With Skills, your agent loads only what it needs, exactly when it needs it. Use when: You want reusable, token-efficient actions your agent can execute without being re-instructed every time. Save 💾 ➞ React 👍 ➞ Share ♻️ Cc : Rakesh Gohel

@delveroin A fully local audio player with EQ band and DSP chains. Do check it out: localtunev1.vercel.app

who’s building something cool AND useful? Drop your URL lets send some traffic

@heyblake Looking for a fully local audio player with EQ band and DSP Chain. Do check it out. localtunev1.vercel.app

Drop your project URL Let’s drive some traffic

Every idea feels taken. Every API already exists. Every SaaS has 12 competitors. So what do we even build now?

I built a local first audio player entirely with browser APIs and @claudeai Live: localtunev1.vercel.app GitHub: github.com/Bhavye2003Deve… Runs fully in the browser. Drop audio files or folders and it plays offline. No server. No uploads. #WebDev #JavaScript #OpenSource

I built a small browser game - Pulsewave Try it out: pulsewave-ivory.vercel.app #indiedev #WebDev #js

@akshaymarch7 sir, Day 4 Solved remove outermost paratheses, evaluate reverse polish notation, next greater element ( first understood O(n) approach then solved it), daily temperature and next greater element 2nd #dsa #js

@akshaymarch7 sir, Day 3 Solved implementation of queue using stack, valid parentheses and understood and solved min stack question. #dsa #js

@akshaymarch7 sir, Day 2 Understood and solved the implementation of stack using single and 2 queues. #DSA #js

@akshaymarch7 sir, Day 1 Completed strings. Next is stacks and queues. I was already as day 38 but not able to solve 1 question a day for which I have reset my streak to 1 in order to remember this. #dsa #js

@akshaymarch7 sir, Day 36 Started strings. Solved length of last word, find words containing character and jewels and stones. #dsa #js

@akshaymarch7 sir, Day 34 and 35 Solved again remove linked list elements and solved add two numbers on first approach only same as akshay sir's and solved remove nth node from end 1 pass approach but needed to understand that via video. Starting with string tomorrow. #DSA #js

@akshaymarch7 sir, Day 30, 31, 32 and 33 Solved swa n nodes interative approach and merge two sorted lists. Came up with different solutions that akshay sir but took 4 days for thinking of solutions. Need to improve thinking... #DSA #js

Day 29 Came up with approach for remove duplicates in sorted linked list and odd even linked list, on my own. But the approaches I came up are a little complex then akshay sir, need to work on simple thinking. #DSA #js

@akshaymarch7 sir, Day 26, 27 and 28 Solved palindrome linked list (not able to think approach on first time), intersection of two linked list (able to think set based approach on my own) and remove nth node from end(able to think approach 1 on my own). #DSA #js