Product Hunt Daily ·
Product Hunt Daily: 5 new
5件の出典約2分
KVWang Browser phone and follow-up notes for US customer calls — Manually call US customers from your browser and keep contacts, call history and next-step notes together. Try a simulated demo with no real calls. Real calling requires individual approval and number assignment. Operated by Tapilot LLC. $15/month includes 200 ordinary US billed minutes; extra minutes cost $0.02. High-cost and special destinations are blocked. Not an autonomous AI calling agent. 1
/dev/null a social network for devs — /dev/null started as a live stream from the JetBrains office. On Oct 15, 2026, Nuno Maduro, Brent Roose, Matthieu Napoli, and Pauline Vos built a social network for web developers from scratch in 48 hours, in the open. Sign in with GitHub, share code snippets, like, reply, etc, etc! Hundreds of you sent PRs. Laravel’s Taylor Otwell stopped by mid-stream (“Laravel forever”), and Vercel’s Guillermo Rauch called it “really well done.” Thank you for watching, sharing, and roasting us. 2
Composio Instant The easiest way for AI agents to pay for their own tools — Give your agent superpowers. No subscriptions, no signups. With Composio Instant, your agent can search the web, find business contacts, create voiceovers, turn audio into text, and so much more. Try it free: composio.dev/instant 3
Hoistbay Open-source desktop app for Amazon S3 and CloudFront — Hoistbay is a free desktop app for macOS and Windows that takes the repetitive work out of S3 and CloudFront. Set header rules once (Cache-Control, Content-Type, Content-Encoding by file pattern) and they apply on every upload. Download whole folders, clear CloudFront cache in one click, and switch AWS accounts instantly. Keys stay in your OS keychain, no backend, no telemetry. MIT licensed. 4
Harness² Harness the agent. Then harness its self-improvement. — Harness² from Google Research is a plug-and-play recursive agent harnessing framework that lets LLM agents automatically evolve their execution harnesses (prompts, tools, memory) for open-world tasks—without ground-truth verifiers. Dual recursion: task-level Propose-Probe-Compose refinement + harnessing-level accumulation of reusable experience. Up to +11.5 points on professional benchmarks like WorkBuddy-Bench. 5
Product Hunt Daily
Yesterday's top 5 Product Hunt launches, ranked by upvotes and explained — every morning.