ent101 · HN

The Safe, Production-Ready Backend for AI-Generated Apps

@mj_jimmi · X

memcode-in · GitHub

memcode Memcode: #1 Memory Layer for AI agents, Building Memory infra for every use case

@ShadcnExamples · X

@lawrencenika · X

OnlyMap is being built fast, docs already live. New trailer walks through it end to end. It already works with your coding agent — hit "Copy for your agent" on any example, build in Claude Code, Codex, or Cursor.

@BobbySBX · X

We just dropped Assay v0.2.6, the open source evaluation engine powering Most registries judge an AI tool by its README. We built Assay to actually run skills, MCP servers, and plugins inside isolated sandboxes with live models to observe what they do before you install them. What is new in v0.2.6: - NVIDIA API Catalog provider: Native support is here, allowing you to use NVIDIA driver and judge models to run behavioral benchmarks and multi-tier audits. - Zero runtime dependencies: Still a self-contained ~240 KB tarball that speaks directly to @nvidia , @AnthropicAI , @OpenAI , @OpenRouter , and local HTTP endpoints without SDK bloat. - Adversarial and static checks: Out of the box verification against prompt injection, tool scope creep, destructive shell commands, and supply chain drift. Every tool on is tested through Assay. That means 4,200+ skills, MCP servers, and plugins are commit-pinned, graded on actual runtime behavior, and rea

@itsarvinddev · X

@partharora9128 · X

@NodeESP · X

- Project for sale

pedrobalsadev · HN

I built Balsa UI because I was getting frustrated with coding agents not being able to consistently follow a design system. It usually worked fine at the beginning of a project, but as the project grew, things started to drift. The same happened when I had different projects using the same design system: I kept having to explain the same rules again, and the results were never quite consistent. Most design systems are still built around the idea that a developer reads the docs, understands the r

@Dmytri_Design · X

@onuro · X