Open Science Framework
GitHub
figshare
arXiv
Substack
Creative Commons
Medium
Google Scholar
Tempreon
ChainMemory
Memori
Agentmemory
OpenMemory MCP
cognee
TheSecondBrain.dev
VATES.jp
Tempreon is a personal memory layer for your AI tools, connected over MCP. Your knowledge, preferences, and decisions travel across Claude, ChatGPT, Cursor, and any MCP-capable client โ captured once, available everywhere. It learns how you actually work instead of just storing what you said.
Open Science Framework TempreonNo Tempreon videos yet. You could help us improve this page by suggesting one.
Tempreon's answer:
Tempreon started with a simple observation: AI models keep changing, but the thing that makes them useful to you โ your context, your preferences, your judgment โ gets rebuilt from scratch inside every tool, and lost every time you move.
We built the layer that fixes that: person-owned memory served over the open Model Context Protocol, so it works across assistants instead of belonging to one. Along the way we open-sourced the pieces that are useful to everyone regardless of whether they use Tempreon โ like memhaul, our MIT-licensed CLI for turning ChatGPT and Claude data exports into files you own.
The through-line is custody: the model is temporary, your memory shouldn't be.
Tempreon's answer:
Most alternatives in this space are memory infrastructure for developers building their own AI apps. If you're the person using several AI tools every day, that's not your problem โ your problem is re-explaining yourself to each of them and losing everything when you switch.
The choice is really about who the memory is for. Ours is for you.
Tempreon's answer:
Tempreon is built for the person, not the app. Most memory products are developer APIs for adding memory to a single product; Tempreon is a memory layer you own that travels with you across every AI tool you use โ Claude, ChatGPT, Cursor, anything MCP-capable.
Tempreon's answer:
Individuals who live in AI tools all day: operators, consultants, founders, sales professionals, and knowledge workers who use more than one assistant and are tired of being a stranger to each of them.
If you've ever pasted the same context into Claude and ChatGPT in the same week โ you're the audience.
Tempreon's answer:
The protocol choice is the product decision: build on the open standard, and your memory works everywhere the standard does.
Based on our record, Open Science Framework seems to be more popular. It has been mentiond 38 times since March 2021. We are tracking product recommendations and mentions on various public social media platforms and blogs. They can help you identify which product is more popular and what people think of it.
Last night I happened to listen to an episode[1] on EconTalk where the author of the post (Adam Mastroianni, a psychologist) was a guest. Definitely worth a listen. Adam also supports "open science framework" (https://osf.io/) and publishes his research and related artifacts there, which I really appreciate! [1] https://www.econtalk.org/a-users-guide-to-our-emotional-thermostat-with-adam-mastroianni/. - Source: Hacker News / over 2 years ago
Here are a few options to consider. First, Google Scholar. If you're logged into Google it will make a handful of recommendations on its front page. I've not really paid attention to how good the recommendations are. It says they're based on your Google Scholar record and alerts, so I guess you'll need both/one of those for it to work. https://scholar.google.com Second, Scopus from Elsevier (a company that plenty... - Source: Hacker News / almost 3 years ago
It's customary to use OSF (https://osf.io/) on papers this "groundbreaking," as it encourages scientists to validate and replicate the work. It's also weird that at this stage there are not validation checks in place, exactly like those the author performed. There was so much talk of needing this post-"replication crisis.". - Source: Hacker News / about 3 years ago
2.Open Science Framework - A non-profit (but not open source) "GitHub for scientific research" [4]. OSF is an incredible team and and product, that helps scientists openly publish their papers, datasets, code, and other research outputs. Their website is also geared towards a technical audience too - they help scientists store information, but they don't have a feature that helps users discover discuss new... Source: about 3 years ago
Our headline result is that a 10 percent increase in taxes is associated with a decrease in annual gross domestic product (GDP) growth of approximately รขหโ0.2 percent when bundled as part of a TaxNegative tax-spending-deficit combination. The same tax increase is associated with an increase in annual GDP growth of approximately 0.2 percent when part of a TaxPositive fiscal policy package. All of our data, output,... Source: about 3 years ago
GitHub - Originally founded as a project to simplify sharing code, GitHub has grown into an application used by over a million people to store over two million code repositories, making GitHub the largest code host in the world.
ChainMemory - Portable, verifiable memory for AI agents โ works across ChatGPT, Claude, Gemini and any MCP client
figshare - Securely store and manage your research outputs in the cloud, or make them openly available and citable.
Memori - Persistent memory from agent trace, not just conversation
arXiv - arXiv is a free distribution service and an open-access archive for scholarly articles.
Agentmemory - Persistent memory for Claude Code, Codex & coding agents