Hermes Agent
— Open-source self-hosted AI agent with persistent memoryOpen-source self-hosted AI agent with persistent memory
Home
Featured products picked by the team, and the best AI products as voted by the community. VibeHacker is where builders find, review, and launch AI products.
Featured products
Hand-picked by the VibeHacker team. Upvote what you'd use.
Grok
— AI assistant for chat, image creation, coding, and web answersAI assistant for chat, image creation, coding, and web answers
Claude Code
— An AI coding agent for terminal, IDE, web, and SlackAn AI coding agent for terminal, IDE, web, and Slack
ChatGPT
— AI assistant for answers, writing, images, work, and codeAI assistant for answers, writing, images, work, and code
Top products
Most upvoted this month. The ones worth your time.
Pipecat
— Open-source Python framework for building real-time voice and multimodal conversational agentsOpen-source Python framework for building real-time voice and multimodal conversational agents
Lindy
— No-code platform for building AI agents that handle email, meetings, scheduling, and business workflowsNo-code platform for building AI agents that handle email, meetings, scheduling, and business workflows
Hedra
— Generate expressive talking-character videos from an image, a script, or your own voiceGenerate expressive talking-character videos from an image, a script, or your own voice
Captions
— AI video creation and editing app for talking videos: captions, eye contact, dubbing, and AI avatarsAI video creation and editing app for talking videos: captions, eye contact, dubbing, and AI avatars
OpenEvidence
— AI medical search engine that answers clinical questions with citations to peer-reviewed literatureAI medical search engine that answers clinical questions with citations to peer-reviewed literature
Sierra
— Conversational AI platform for branded customer experience agents that can take actionConversational AI platform for branded customer experience agents that can take action
Modal
— Serverless cloud for running AI inference, training, batch jobs, and sandboxes with just PythonServerless cloud for running AI inference, training, batch jobs, and sandboxes with just Python
Promptfoo
— Open-source CLI for testing prompts and LLM apps, plus red teaming for security vulnerabilitiesOpen-source CLI for testing prompts and LLM apps, plus red teaming for security vulnerabilities
Dia
— An AI browser from The Browser Company that lets you chat with your tabs, write, and get help right where you browseAn AI browser from The Browser Company that lets you chat with your tabs, write, and get help right where you browse
Vapi
— Developer platform for building, testing, and deploying voice AI agents over phone and webDeveloper platform for building, testing, and deploying voice AI agents over phone and web
Trending discussions
What builders are talking about this week.
left claude code running overnight and woke up to $47 on anthropic
left a "just fix the flaky e2e" prompt open around midnight. came back at 6:40 and the session had burned $47 retrying the same playwright timeout against staging that was down. usage dashboard looks…
Cursor updated mid-agent and ate my docker-compose diff
Left Claude Code refactoring a compose file on Mac while I grabbed coffee. Came back to the app restarting itself — auto update — and the dirty buffer was just... gone. Recovered most of it from /Lib…
agent committed node_modules after I said stage the fix
told cursor to stage only the auth patch. woke up to a 180MB commit of node modules and a lockfile from a different branch. reverted, added a pre commit size check. anyone else hard blocking the agen…
qwen2.5-coder:14b OOMd my Mac Studio mid-refactor
left ollama running an agent loop overnight on a 200 line auth refactor. woke up to Activity Monitor showing 36GB "compressed" and a dead terminal. num ctx was still on the default 128k. dumb. anyone…
agent silenced 40 type errors with `as any` and opened a green PR
Asked Cursor agent to unblock the types after a Prisma 6 bump. PR came back green. Diff was mostly as any on the query results. One file had // @ts nocheck shoved under the imports. Commit message sa…
12-prompt eval was green, prod still invented Stripe refund ids
ran a 12 prompt golden set against claude sonnet and gemini 2.0 flash friday night. both scored 11/12. shipped the flash path for support replies because it was $0.004/turn. monday morning: three tic…