Launching today
Hipo Hipo
Portable project memory for all your agents
1 follower
Portable project memory for all your agents
1 follower
Your workspaces follow you, not your agents. Every time you open a new window or switch AI agents, your AI gets amnesia. Hipo Hipo is a portable, governed "Brain" for your projects. Instead of dumping noisy chat logs into a vector DB, it stores your raw materials (evidence) alongside structured project memory (decisions, constraints, and methods). Connect one Brain to any agent, resolve context conflicts before overwriting, and take your workspace anywhere.
Launch Team
Framer AI AgentsDesign and publish professional sites with AI
Promoted
Hey Product Hunt! 👋
I’m so excited to share Hipo Hipo with you today!
Like many of you, my daily workflow involves juggling multiple AI agents, chat windows, and devices. And every single day, I hit the same wall: AI amnesia.
The moment you open a new window, switch from one agent to another, or come back to a long-term project after a few days, your AI forgets everything. You’re forced to re-upload files, re-explain constraints, and watch it repeat the exact same mistakes you already solved yesterday.
🤔 Why "adding memory" isn't just dumping chat logs into a vector DB
When we started building Hipo Hipo, we realized a fundamental flaw in how most tools approach AI memory: what you actually want to save is NOT your chat history.
If you just chop up historical conversations and throw them into a vector database, you’re mostly saving noise—dead-end brainstorms, half-baked prompts, and outdated assumptions.
Real project continuity requires structure. So we built Hipo Hipo around a dedicated, portable Brain for each project or research topic:
1. Raw Materials + Project Memory (Not Chat Noise): Each Brain stores your original sources (papers, financial docs, experiment logs, notes) for verifiable evidence, alongside structured project memory—specifically your effective decisions, constraints, and methods.
2. Memory Governance & Conflict Exposure: Projects evolve. What happens when a new conclusion (Decision B) contradicts an earlier one (Decision A)? Hipo Hipo doesn't blindly overwrite A with B. Instead, it exposes the conflict first—letting you decide whether it's an official change, a scoped exception, or just a temporary experiment.
3. One Brain, Any Agent: Raw materials provide evidence, project memory preserves decisions, external agents do the work, and new conclusions flow back into your Brain after governance. Whether you’re analyzing management guidance across earnings calls, running a multi-month research topic, or shipping code across different agents, your context stays intact.
💡 Our Philosophy: "Your workspaces follow you, not your agents."
The AI agent landscape changes every week. New models and better agent tools will keep emerging—and you should be free to switch between them at zero cost. Agent tools can change, but your accumulated memory and context must belong to you. With Hipo Hipo, you can connect the same Brain to different agents, or pack up and take your raw materials and context with you anytime.
🔗 Try it out here: https://hipohipo.ai/
We’d love to hear your honest feedback and questions! To kick things off: How many different AI agents or chat windows do you switch between in a typical day, and how are you currently keeping your project context alive across them? 👇