Cosolvent is an open-source platform designed to democratize access to AI-powered matching technology. Built specifically for “thin markets”—where participants are scattered and struggle to find each other … Cosolvent provides a foundation for anyone wanting to explore LLM+RAG automation and build specialized trading environments that offer the following features:
Intelligent Profile Creation: Users can build profiles by uploading existing documents—specifications, certifications, product descriptions, or any relevant materials. Cosolvent’s AI automatically extracts and structures this information into searchable, matchable profiles with a consistent look and feel without requiring users to fill out complex forms or learn new systems.
Curated Industry Context: Each market implementation includes a carefully assembled library of industry-specific information—standards, regulations, terminology, and best practices—that provides essential context for accurate matching and relevant responses.
Curated Industry Context: Each market implementation includes a carefully assembled library of industry-specific information—standards, regulations, terminology, and best practices—that provides essential context for accurate matching and relevant responses.
Open Source Commitment: Released under the MIT license, Cosolvent is freely available on Github for modification, deployment, and commercial use. Our goal is to empower developers, entrepreneurs, and organizations worldwide to create more efficient markets, particularly in underserved sectors and developing economies where improved market access can drive meaningful economic impact.
Building Toward a Thin Market Ecosystem
When the Cosolvent toolkit is filled out for a given thin market, the system sponsor will have to supply a lot more information than Deeperpoint is putting into the open source Cosolvent. That will require design, marketing and support to the set of people and organizations that are expected to participate in the market. The sponsor will also have to assemble and curate the documents, links and assets that will form the, hopefully trustworthy, industry context.
In most instances, the participants won’t be aware of Cosolvent’s design or operations. They will just be ordinary people that are persuaded to use the resulting system. Recruiting and supporting the market participants will be a separate (and probably much more daunting) task for the thin market system sponsers.
Conceptually, Cosolvent must be customized for each specific thin market and a market sponsor will have to hire and manage a team of people to recruit and support the many participants and end users. The challenge for the Cosolvent design process is that we couldn’t see how to build and test a fully working implementation without first organizing a corresponding ecosystem. Only then can we test realistic AI prompts and explore the possibilities for an exciting and enticing user experience.
That’s where Deeperpoint’s companion GPSim simulator project comes in. It uses AI (the ClientSynth project) to generate a synthetic, but realistic ecosystem of users and participants for a chosen thin market scenario. That creates the playground where Deeperpoint developers, and soon registered users, can play with realistic scenarios. For more information on that companion process, check out the Grainplaza section of this website.
At the same time, visitors are welcome to poke around the Cosolvent repository on Github. You can clone a current version and follow the documented guidelines to set up and play with your own version. Since it is released under the MIT license, you are welcome to fork the design and go off on your own merry development way. We hope that you will keep in touch and perhaps give back to the project, but that is totally up to you.
When the Cosolvent toolkit is filled out for a given thin market, the system sponsor will have to supply a lot more information than Deeperpoint is putting into the open source Cosolvent. That will require design, marketing and support to the set of people and organizations that are expected to participate in the market. The sponsor will also have to assemble and curate the documents, links and assets that will form the, hopefully trustworthy, industry context.
In most instances, the participants won’t be aware of Cosolvent’s design or operations. They will just be ordinary people that are persuaded to use the resulting system. Recruiting and supporting the market participants will be a separate (and probably much more daunting) task for the thin market system sponsers.
Conceptually, Cosolvent must be customized for each specific thin market and a market sponsor will have to hire and manage a team of people to recruit and support the many participants and end users. The challenge for the Cosolvent design process is that we couldn’t see how to build and test a fully working implementation without first organizing a corresponding ecosystem. Only then can we test realistic AI prompts and explore the possibilities for an exciting and enticing user experience.
That’s where Deeperpoint’s companion Grainplaza simulator project comes in. It uses AI (the ClientSynth project) to generate a synthetic, but realistic ecosystem of users and participants for a chosen thin market scenario. That creates the playground where Deeperpoint developers, and soon registered users, can play with realistic scenarios. For more information on that companion process, check out the Grainplaza section of this website.
At the same time, visitors are welcome to poke around the Cosolvent repository on Github. You can clone a current version and follow the documented guidelines to set up and play with your own version. Since it is released under the MIT license, you are welcome to fork the design and go off on your own merry development way. We hope that you will keep in touch and perhaps give back to the project, but that is totally up to you.
Visit our Github Repository to follow the Cosolvent Project as it develops.