ZGI has shared its open-source Agent Runtime platform designed to run AI agents in production. The platform provides unified management of multiple models including GPT, Claude, DeepSeek, and Qwen, along with enterprise knowledge base integration. It features visual workflow composition with conditional logic, tool calls, and human approval, as well as reusable Skills for file generation and data queries. Every execution is traceable with node-level inputs, outputs, errors, and token usage. ZGI can be deployed via Docker on private infrastructure, and source code is available on GitHub and Gitee. A developer trial event offers 10,000 tokens for approximately 50 basic tasks.
SUB&SUB studio has released Markup Relay, an open-source browser-based tool that lets users annotate images and videos to help AI coding agents understand visual context. Files can be dragged in and annotated with a selection tool; unselected areas are automatically blurred. For videos, keyframes are extracted to describe dynamic changes. Processed files are uploaded to Cloudflare R2 and automatically deleted after a set time. The team is seeking feedback via ProductHunt.
Google DeepMind has shared a first look at Gemini Robotics 2, a new robotics-focused model, in a demonstration on a FR3 Duo robot. The video shows 20 minutes of uninterrupted, real-time tool use. No further details about the specific tasks, model architecture, or release plans are provided in the post.
ti is a terminal-based AI agent for quantitative analysis and trading, similar to Claude Code but tailored for quants and traders. It supports natural language backtesting—for example, "backtest AMD vs NVDA past two years"—automatically fetching data and running the analysis. The tool includes a built-in mean-variance portfolio optimization engine and provides proprietary data on US Congress members' and corporate insiders' stock trades (240+ Congress members, 10,800+ insiders). Real-time market quotes, news, and research reports are also integrated. Users can install via `bun i -g @tradeinsight-info/ti` and access a free trial after registration.
minchoi integrated ElevenLabs Speech Engine into their AI agent, enabling voice interaction. The agent can now listen, talk, stream replies, and handle interruptions in real time. The post demonstrates a personal use case of adding speech capabilities to an agent.
A new AI Agent startup, founded by a serial entrepreneur and incubated from previous tech explorations, has raised tens of millions of dollars from top-tier VCs including Sequoia. The company is hiring a Research Engineer to work on LLM reasoning, planning, tool calling, and multi-agent collaboration. The role includes building Agent Evals, analyzing model capabilities and failure cases, and translating research into real AI products. The position is remote and open to both full-time and internship. The founder has invested in over 20 AI projects and aims to connect with global AI innovators.