-
cmux is a Ghostty-based macOS terminal built for running fleets of AI coding agents
cmux is a free, open-source macOS terminal designed explicitly for developers running multiple AI coding agents at once. Built in Swift and AppKit on libghostty, it reads your existing Ghostty config so themes, fonts, and colors carry over. ## What makes it agent-native The vertical-tab sidebar shows per-workspace metadata most terminals don’t track: git branch,… Continue reading
-
Forsy turns your AI agent workflow data into a sellable asset — building the agent data economy
Forsy captures workflow data from the agents you already use — OpenClaw, Claude, Codex, Hermes — and turns it into structured, sellable data, with licensing and privacy built in. The pitch: real agent workflows are valuable training data, and you should be able to monetize yours. ## How it works Forsy tracks workflow data in… Continue reading
-
Cohere Command A+ is its first fully Apache 2.0 model — 218B MoE with native citations, runs on 2 H100s
Cohere released Command A+ — a 218B-parameter sparse MoE model (25B active) under full Apache 2.0, the company’s first fully open-weight model. It’s tuned for complex reasoning, multimodal document processing, and agentic workflows, and it runs on a single NVIDIA B200 or just two H100s. ## Native citations The standout feature: when Command A+ retrieves… Continue reading
-
GenEvolve makes image-generation agents self-improve by distilling their own successful attempts
GenEvolve, from MeiGen-AI, is a self-evolving framework for image generation agents. The core reframe: each generation attempt isn’t a one-shot prompt, it’s a tool-orchestrated trajectory — the agent gathers evidence, selects reference images, invokes generation skills, and composes them into a prompt-reference program. ## Tool-orchestrated visual experience distillation Instead of calling a diffusion model once,… Continue reading
-
ACC compiles AI agent trajectories into long-context training data — turning agent runs into a learning signal
ACC (Agent Context Compilation) tackles a clean idea: when agents solve problems, they produce massive trajectories — tool calls, environment observations, dozens of turns. That data is usually thrown away after the task. ACC converts it into long-context training material instead. ## How it works When an agent works a search, software-engineering, or database-querying task,… Continue reading
-
FinceptTerminal is an open-source Bloomberg alternative with built-in AI agents and Python quant research
FinceptTerminal is an open-source financial terminal — a free alternative to Bloomberg that bundles market data, quant research, trading workflows, and AI agents into one desktop platform. Trending on GitHub at 537 stars per day. ## What’s in it Version 4 is built with C++20 and Qt6 as a native desktop app, embedding the full… Continue reading
-
Presenton is an open-source AI presentation generator with an API — bring your own models, export editable PPTX
Presenton is an open-source AI presentation generator positioned against Gamma, Beautiful.ai, and Decktopus. Apache 2.0 licensed, it gives you full control over the workflow: choose your models, keep your data private, run it locally. ## What sets it apart Most AI slide tools are closed SaaS that lock your decks in their format. Presenton exports… Continue reading
-
Anthropic’s Project Glasswing has found 10,000+ critical vulnerabilities, partners report 10x bug-discovery gains
Anthropic shared a sweeping update on Project Glasswing — its AI-assisted security testing initiative powered by Claude Mythos. The headline number: more than 10,000 high- or critical-severity vulnerabilities uncovered across widely used software, with several partner organizations reporting bug-discovery rate gains of more than 10x after integrating AI into their testing workflows. ## The coalition… Continue reading
-
Kanbots runs a Claude Code or Codex agent on every Kanban card — up to 4 in parallel, fully local
Kanbots is an open-source desktop Kanban board where each card is an AI coding agent. Drop a task on a card, and a Claude Code or Codex agent works it. The autopilot mode runs up to 4 agents in parallel, splitting work and evolving the backlog until tasks complete or budget caps hit. MIT licensed,… Continue reading
-
NVIDIA debuts Nemotron 3 open models — Nano delivers 4x the throughput of Nemotron 2 for multi-agent systems
NVIDIA debuted the Nemotron 3 family of open models — Nano, Super, and Ultra — positioned as the most efficient open models for building agentic AI applications. The headline: Nemotron 3 Nano delivers 4x higher throughput than Nemotron 2 Nano, and the most tokens per second for multi-agent systems at scale. ## The architecture Nano’s… Continue reading
Top AI Product
Every day, hundreds of new AI tools launch across Product Hunt, Hacker News, and GitHub. We dig through the noise so you don't have to — surfacing only the ones worth your attention with honest, no-fluff reviews. Explore our latest picks, deep dives, and curated collections to find your next favorite AI tool.
Top AI Product 