Mycelis
Serverless AI workspace with smart routing & MCP agents
What it does
Mycelis abstracts hardware completely. Instantly spin up open-source models on optimized GPUs, or bring your own keys (BYOK). It acts as a unified OpenAI-compatible API gateway for coding clients like OpenCode, desktop apps, or scripts. Includes conditional smart routing, a vector-powered semantic cache to slash costs, integrated RAG, and native MCP agents (GitHub, Slack, Discord, etc.). Get full control over your AI environment with zero server maintenance.
Does the same job
all alternatives →
Apideck MCP ServerMay 2026 · apideck.com · ▲178Give AI agents access to real-time data across 200+ apps
- SBServerlessAI – Build, scale, and monetize AI apps without back end2024 · serverlessai.dev · ▲86
Hello HN, I’ve always loved building frontend-only apps—those you can prototype over a weekend, host for free on GitHub Pages, and scale to millions of users. Unfortunately, AI-enabled apps complicate things, as exposing your OpenAI key to the world is obviously a no-go. This also means mobile developers often have to run their own servers. That’s why I built ServerlessAI, an API gateway that lets you securely call multiple AI providers directly from client side using OpenAI-compatible APIs. You can authenticate users through any identity provider, like Google or Apple, and set per-user…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com