@mkappworks · X

I am building lets connect

@fortsignal1 · X

snakaya · HN

Vibsync – One Shared Memory for Claude Code, Cursor and Codex (MCP)

@intheworldofai · X

On the World of AI Bench (vibe-coding composite): Claude Fable 5 → 85.2 GPT-5.6-sol → 82.4 kimi-k3 → 81.5 Moonshot’s K3 just walked in and claimed bronze on one of the toughest coding-focused leaderboards out there.

@francis7_a · X

Building - learning tools for devs and student. happy to connect.

@Craftapp_AI · X

Six Capabilities a Real Vibe Coding Platform Must Have, Or You're Wasting Time and Money Building a demo is easy. Building a real product is where platforms fall apart. Watch the full video on YouTube: Build with CraftApp today:

shreyans_assistiv · Product Hunt

AskCodi Orchestrate agents at scale while reducing cost

@Shekar77hima · X

run deepresearch, coding agents for free.

@ThrillStack · X

taosx · HN

I created a simulation for coding harnesses based on my own pi sessions. When taking into account all factors, DS-v4-Pro is cheaper than gpt-5.6-luna due to caching. Look at the bill segments difference for cache read cost and uncached cost between deepseek and the other models. At this point is cheaper to use ds-v4-pro than the luna models from openai. ignore the numbers except the classic and keep in mind that classic is based on pi with the only change limiting tool output to 10kb https://har

vuphanse

JulianQuinn · HN

Show HN: TaskPeace – a task queue my AI coding agents pull work from over MCP