Education1 month ago
openstem — code skills that finally stick
Learn code skills with flashcards, quizzes, and AI tutoring built on memory science.
@mkappworks · X
I am building lets connect
The full gallery
Tech stack
27 projects
Learn code skills with flashcards, quizzes, and AI tutoring built on memory science.
@mkappworks · X
I am building lets connect
Local-first cognitive runtime with live AST graphs, runs in your browser with no data sharing.
@fortsignal1 · X
Shared memory for AI coding agents to store team discoveries and reduce duplicate research.
snakaya · HN
Vibsync – One Shared Memory for Claude Code, Cursor and Codex (MCP)
Compare AI coding models on real tasks with live previews, cost tracking, and ELO rankings.
@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.
Write, execute, and learn code in Python, Java, JavaScript, C++, Go, and Rust.
@francis7_a · X
Building - learning tools for devs and student. happy to connect.
Build applications with AI-powered vibe coding.
@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:
AI coding assistant offering multi-model chat, code generation, refactoring, and agent orchestration.
shreyans_assistiv · Product Hunt
AskCodi Orchestrate agents at scale while reducing cost
Chat with multiple AI models for deep research and coding tasks.
@Shekar77hima · X
run deepresearch, coding agents for free.
AI-powered platform unifying coding assistance, trading tools, and team collaboration features.
@ThrillStack · X
Compare costs of coding-agent harness strategies with event-level cache and context accounting.
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
Desktop app for running multiple AI coding agents in parallel across git worktrees
vuphanse
Task queue for AI coding agents to request and complete work over MCP protocol.
JulianQuinn · HN
Show HN: TaskPeace – a task queue my AI coding agents pull work from over MCP