-
Semble cuts AI agent code-search tokens by 98% with natural language queries instead of grep
MinishLab released Semble — a code search library purpose-built for AI agents. It returns the exact code snippets an agent needs instead of having grep dump full files into the context window. The result: roughly 98% fewer tokens used per code-search step. Show HN hit 212 points this morning. ## The numbers End-to-end indexing of… Continue reading
-
Vivago Video Agent bundles Sora 2, Veo 3.1, and Kling under one conversational interface for $8/month
Vivago.ai’s Video Agent lets you describe a video in plain language and routes the request across OpenAI’s Sora 2, Google’s Veo 3.1, Kling v2.6 Pro, Nano Banana Pro, and Seedream v4 — picking the right model and writing the prompt for you. No prompt engineering, no comparing pricing across providers. ## What’s actually in the… Continue reading
-
CLI-Anything turns any software into agent-native CLI through a 7-phase Claude Code plugin
HKUDS shipped CLI-Anything — a Claude Code plugin that automatically generates production-ready CLI interfaces for any software with a codebase, turning GUI apps and SaaS platforms into agent-native tools. It’s sitting at 306 daily stars on GitHub trending today. ## The 7-phase pipeline Analyze → Design → Implement → Plan Tests → Write Tests →… Continue reading
-
Shannon Lite scores 96% on XBOW benchmark — open-source autonomous AI pentester powered by Claude
Shannon Lite is an autonomous AI pentester from Keygraph that reads your web application source code, finds attack vectors, and then actually exploits them to prove the vulnerability is real. It scored 96.15% on the XBOW benchmark in hint-free, source-aware mode — completing 100 of 104 exploit challenges. ## The two-stage pipeline Stage 1: agentic… Continue reading
-
agent-skills hits 900+ daily stars: a vetted skill registry for Claude Code, Cursor, and 17 other AI coding agents
tech-leads-club’s agent-skills shot to the top of GitHub trending this weekend with 923+ daily stars. It’s a curated, security-hardened skill registry for Claude Code, Cursor, Copilot, Antigravity, Windsurf, Cline, and 13 more AI coding agents. ## The security pitch In an ecosystem where 13.4% of open-marketplace skills contain critical vulnerabilities, agent-skills positions itself as the… Continue reading
-
δ-mem boosts frozen LLMs by 31% on MemoryAgentBench with an 8×8 online memory state
δ-mem is a lightweight memory mechanism from DECLARE Lab that augments a frozen full-attention LLM with a compact online state of associative memory. The paper hit Hacker News with 216+ points this weekend. Open-source code is up at declare-lab/delta-Mem. ## The mechanism Past information gets compressed into a fixed-size state matrix updated by delta-rule learning.… Continue reading
-
Writer ships event-triggered AI agents that watch Gmail, Slack, and Gong without a human prompt
Writer launched event-based triggers for its Writer Agent platform — enterprise AI agents that autonomously detect business signals across Gmail, Gong, Google Calendar, Google Drive, Microsoft SharePoint, and Slack, then execute multi-step workflows without a human hitting “go.” ## How it works A trigger watches a connected app for a specific event — an RFP… Continue reading
-
OpenAI gives every Maltese citizen a free year of ChatGPT Plus in first country-scale partnership
OpenAI signed its first country-scale deal: every Maltese citizen and registered resident now qualifies for free ChatGPT Plus access for a full year, gated behind a government-managed AI literacy program. ## How it works Eligibility runs through Malta’s online identity system. After completing a free online course called AI for All — developed by the… Continue reading
-
Zerostack: Unix-inspired Rust coding agent ships at 8MB RAM, 0% idle CPU
Zerostack is an open-source Unix-inspired coding agent written in pure Rust. It hit #1 on Hacker News this weekend with 223+ points. The pitch is unusual: a coding agent that doesn’t bloat your machine. ## The memory story Empty session: ~8MB RAM. Actively working: ~12MB. Compare to JavaScript-based coding agents like Claude Code, which typically… Continue reading
-
Supertonic v3: 99M-parameter on-device TTS covers 31 languages with expression tags
Supertone Inc shipped Supertonic v3 — 99M parameters, 31 languages, running entirely on-device via ONNX Runtime with zero cloud calls. GitHub trending lit up this week with 745+ daily stars as the broader dev community discovered the release. ## The size argument At 99M parameters Supertonic v3 is roughly 7-20x smaller than competing open TTS… 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 