WeaveMind – AI Workflows with human-in-the-loop
Hi! I spent 3 years evaluating LLMs for OpenAI, Anthropic, METR, and other labs. Kept running into the same problem: AI workflows break in production because there's no clean way to add human oversight, handle failures gracefully, or deploy without choosing between "all cloud" and "all self-hosted." WeaveMind is a visual workflow builder in Rust. The core idea is that humans and AI are interchangeable nodes in the same graph. When a workflow needs judgment, it pauses, notifies the team via browser extension, first responder picks it up. There's also an AI assistant that generates workflows…
In plain words
WeaveMind is a visual workflow builder that treats humans and AI as interchangeable nodes in automated processes. Built in Rust, it lets teams add human oversight to AI workflows by pausing execution and notifying reviewers through a browser extension when judgment is needed. The platform handles failures gracefully and offers flexible deployment options between cloud and self-hosted setups. It includes an AI assistant for generating workflows from natural language descriptions and durable execution to prevent data loss. Currently in beta and free for users bringing their own API keys.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi! I spent 3 years evaluating LLMs for OpenAI, Anthropic, METR, and other labs. Kept running into the same problem: AI workflows break in production because there's no clean way to add human oversight, handle failures gracefully, or deploy without choosing between "all cloud" and "all self-hosted." WeaveMind is a visual workflow builder in Rust. The core idea is that humans and AI are interchangeable nodes in the same graph. When a workflow needs judgment, it pauses, notifies the team via browser extension, first responder picks it up. There's also an AI assistant that generates workflows from natural language, and durable execution so nothing gets lost on failure. Early beta, free (bring your own API keys). Planning to open source once stable (Q2 2026). Feedback welcome. Discord: https://discord.gg/FGwNu6mDkU
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 · 26d ago · cactuscompute.com
