Velatir

What it does

Velatir adds a human decision layer to your AI workflows. Our lightweight SDK lets you route AI-generated decisions to a human for approval, right where your team already works (Slack, Teams, email, etc.). Use it in agents, automations, or custom LLM setups.

• 
  HumanLayer2024 · ▲225

  Human-in-the-loop infra for AI agents

• 
  AI Agents by Threado2024 · ▲611

  Instant, automated support for customers and internal teams

• 
  Humans in the LoopJan 2026 · clawsyndicate.ai · ▲465

  A free community to talk all-things-agentic-coding-AI

• 
  MakersClawJun 2026 · makersclaw.com · ▲424

  Hire AI employees that live in your Slack, Teams, Telegram

• 
  Venn.aiMar 2026 · venn.ai · ▲337

  Delegate real work to AI agents with safety guardrails

• 
  xpander.ai | Slack-native agents2025 · ▲203

  Turn AI agents into Slack native teammates

• 
  I trained a 125M model to autocomplete piano on-device▲598

  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 · 18d ago · simedw.com

• 
  Astute▲585

  Automate your B2B brand going viral, with new media creators

  AI · 19d ago · company-app.joinastute.com

• 
  Grok Bot▲547

  AI teammates that you can give real work to

  AI · 26d ago · x.ai

• 
  Needle2: 14MB agentic LLM for phones, wearables, smart home and robots▲537

  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 · 28d ago · cactuscompute.com

• 
  Monid▲477

  One wallet, every paid tool your agent needs

  AI · 7d ago · monid.ai

• 
  Clara AI SDR▲460

  Turn website visitors into qualified pipeline

  AI · 20d ago · clarasdr.ai

• 
  Tapflow 2.0▲1,127

  Turn your docs into sellable guides, playbooks, workflows

  Work · 2025 · tapflow.ai

• C9
  Clippy – 90s UI for local LLMs▲1,122

  Life & fun · 2025 · felixrieseberg.github.io

• 
  Appwrite Sites▲990

  Appwrite 2.0 brings a new engine, a rebuilt Console, five database types, an S3 API, an OAuth 2.1 server, and organization-level Domains and Firewall.

  Dev tools · 2025 · appwrite.io

• 
  AI Meeting Notes by Notion▲964

  Perfect meeting memory in Notion

  AI · 2025 · notion.com

• 
  Den▲948

  Multiplayer AI agent builder

  AI · 2025 · getden.io

• 
  Raycast for iOS▲865

  Powerful productivity on the go

  AI · 2025 · raycast.com