The full gallery
Tech stack
21 projects
Design and test AI-ready APIs using a visual flow builder with team collaboration.
@milonspace · X
A specification nobody can find is functionally the same as no specification.
Connect 1000+ SaaS providers to AI agents via SDK, CLI, MCP, HTTP, or OpenAPI.
oomol-lab · GitHub
open-connector Open-source auth gateway connecting 1000+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI.
OpenTunnel gives your local apps persistent public domains—perfect for webhooks, live demos, and mobile testing. No ports to open, no router to fight, no traffic left unseen.
@troywrlds · X
Desktop-first open-source productivity system with Pomodoro tracking, habit building, and AI reflection.
@Shourya60756648 · X
Let's connect, checkout
Asynchronous coordination platform for autonomous coding agents with audit trails.
tyagivivek · HN
Parley – your coding agent can talk to a teammate's agent
Enable AI agents to post and schedule tweets to X via API, MCP, or CLI.
@opentweetio · X
Open-source ecosystem for discovering, evaluating, and publishing AI tools with a sandboxed testing framework.
@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
A daily automated sweep of AI, robotics and smart-hardware repositories on GitHub, scored for reproducibility and shipped with clone commands, setup steps and download links.
@shawkalent · X
我开发了两个平台，一个是开源平台：
Backend platform providing auth, storage, database, and LLM APIs (Claude, OpenAI, Gemini) via a single JavaScript library.
ent101 · HN
The Safe, Production-Ready Backend for AI-Generated Apps
https://t.co/3doapHeqkT & https://t.co/qCHWvWuIaq High-Level Architecture (built with Gemini & Grok): Agentic orchestration (LangGraph + CrewAI) Lead qualification + Sales agents A
@LasoffDavid · X
& High-Level Architecture (built with Gemini & Grok): Agentic orchestration (LangGraph + CrewAI) Lead qualification + Sales agents AI Video pipeline (HeyGen/Vyond/Runway etc.) Ad placement optimizer n8n workflows + Voice agents (WhatsApp-heavy for India) HubSpot/Zoho CRM backbone
Deterministic MCP tools for AI agents: EU AI Act and GDPR/CCPA checks, trust scoring, verification. Free tier, no key required — same input, same answer.
Atomadic · HN
Atomadic – Zero-LLM Sub-200us MCP Action Interlock
Autonomous AI research engine that generates full academic papers with real citations from a prompt.
@fedeponte1 · X
my first saas. i think i built something people actually want and completely failed at the business side. would genuinely love help. openpaper ( writes full, cited research papers from a prompt. research, outline, writing, real citations, export. the honest numbers: - ~2,300 signups - ~1,500 generated a full paper. people actually use it. - ~5 have ever paid. ~$45/mo. activation is great, revenue is basically zero. i've been staring at this for weeks. the paywall is on export (pay ~$12 to download the pdf). but the full cited paper is right there on screen, free, you can read it and copy-paste it. so i'm charging for the gift wrap after handing over the gift. almost nobody even reaches checkout. 76% generate exactly one paper and leave. one-and-done, so subscriptions make no sense. the audience is mostly students and researchers on personal gmail, all over the world, almost none on university or company emails. traffic is x and github. so i genuinely can't tell
