Create educational and/or useful demos using SingularityNET's own MeTTa programming language. This RFP aims at bringing more community adoption of MeTTa and engagement within our ecosystem, and to demonstrate and expand the utility of MeTTa. Researchers must maintain demos for a minimum of one year.
Main purpose
Develop educational and useful demonstrations using the MeTTa programming language.
Long description
Context and background SingularityNET Foundation, in collaboration with other partners such as the OpenCog Foundation and TrueAGI, is working toward a scalable implementation of the Hyperon AGI framework running on decentralized infrastructure, and toward implementation of the PRIMUS cognitive architecture within this framework.
Hyperon and PRIMUS are complex systems involving multiple components, which need to demonstrate appropriate functionalities both individually and in combination.
This RFP aims to address a portion of this overall need, via funding the initial iteration of one significant component of PRIMUS within Hyperon: Develop and maintain interesting demos in SingularityNET’s AGI-specific programming language aka MeTTa
The primary objective is to develop useful and interesting demonstrations using the MeTTa programming language.
Collaboration
This RFP will be followed by subsequent RFPs for applications that leverage Hyperon/PRIMUS to carry out various applications, and that aim to guide Hyperon/PRIMUS systems in cognitive development toward beneficial AGI.
Expected outcomes
Initial Deployment: Deployment of demonstration software in a Hyperon instance hosted by SingularityNET.
OSS code: Provision of the underlying code in an open-source repository with an appropriate OSS license.
Thorough Documentation: Comprehensive documentation detailing the structure and functionality of the demos to facilitate collaboration and further development.
Technical Report: A report summarizing experiments and results, enabling replication and further exploration.
Functional Requirements
Demonstrations should showcase MeTTa's capabilities in various practical applications, such as:
Data querying and manipulation
Real-time interaction and control of AI agents
AI that updates its own source code dynamically
Programs that produce runtime justifications for why they are operating a certain way
Programs line-by-line can be generated from logical deduction (so what is executing is accompanied by a justification)
Integration with existing AI systems and frameworks
Procedural content generation and automated reasoning
Ensure demonstrations are modular and can be expanded or adapted for different use cases.
Demonstrations that are useful and provide value to ongoing projects within SingularityNET are preferable, such as:
AI-driven research and analysis in genomics that can be used by Rejuve.bio
Autonomous agent control and interaction in virtual environments that can be applied within SophiaVerse
Libraries that extend the functionality of MeTTa
Examples of proposals that would be valuable to the SingularityNET ecosystem:
Integrations with existing MeTTa tools and systems
Creative and useful demonstrations that highlight MeTTa's potential
Biotech: Converting natural language user queries into MeTTa queries for bioinformatics analysis
Take biomedical user queries (such as from SingularityNET spinoff, Rejuve.bio) from NL into MeTTa/MeTTaLog queries that run against the “BioAtomspace”. Use EYE (Euler Yet another proof Engine) to answer a MeTTa query and show a proof of how that answer was derived.
Sophiaverse: Programming virtual agents to perform complex tasks based on user commands.
Produce a demo of neoterics (or some form of virtual ai agents) interacting with one another based on user prompts. Use MeTTa scripts to hack/change the plans and goals of a virtual world agent. Different uses complexity wise:
driving them around `!(walkTo Self Mirror)` .
or planning `!(Achieve Self (Wearing Self PartyDress))`
or NL goals `(AcheiveState "Wear a party dress")` would be great
or more social (AchieveState "Hold a dinner party to get to know other neoterics living nearby") or simpler (AchieveState "know everyone else's name") and have it when a neoteric is nearby a human or other neoteric it will at least ask their names... which would require…
to "know everyone else's name" we’d need to also have "Answer questions you are able to answer" (so they actually tell each other their names) but the RFP can include skills:
ability to remember things
ability to ask and answer questions that you have facts stored about in MeTTa
Non-functional Requirements
Must have
Code must be implemented in MeTTa
Must be able to demonstrate successfully and be replicated by other developers
Clean commented code and comprehensive documentation detailing the software’s structure, functionality, data models, and interaction interfaces (APIs/UI), enabling effective collaboration and development by other teams
Good to have
Implement advanced features such as probabilistic logic and procedural learning in MeTTa
Optimize performance for large-scale data and complex queries
Utilize the Distributed Atomspace (DAS) and/or other relevant components
Code offers modularity and/or extensibility of MeTTa language
Recorded tutorial that can be followed by other developers interested in learning MeTTa
Main evaluation criteria
Alignment with requirements and objectives
Does the proposal meet the requirements and advances the objectives of the RFP?
Pre-existing R&D
Has the team previously done similar or related research or development work in other platforms / languages / contexts?
Team competence
Does the team have relevant skills
Cost
Does the proposal offer good value for money?
Timeline
Does the proposal include a set of clearly defined milestones?
Other resources
Hyperon and related AI-platforms are quickly evolving! This is a bit of a moving target, but the internal SingularityNET team will be available for help and expert advice, where needed. Also included:
Educational materials and resources for learning MeTTa
SingularityNET holds MeTTa study group calls every other week. Proposers are welcome to attend for support from our researchers and community.
Recurring Hyperon study group calls for community are currently being planned. These will cover MOSES, ECAN, PLN, and other key components of the OpenCog and PRIMUS Hyperon cognitive architectures.
Access to the SingularityNET World Mattermost server, with a dedicated channel for discussion and support among the RFP-winning teams and SingularityNET resources.
RFP Status
Completed & Awarded
The community and public are invited to view the full proposals and give feedback. During this time the RFP committee will doing their formal selection process to award winning proposals.
Bayesian Networks are a powerful tool for representing probabilistic models as directed acyclic graphs (DAGs). In this model, each node represents a variable (a true/false event or observation), and each edge represents a conditional dependency (e.g. an edge from A to B may indicate that the status of A has an influence over the probability that B is true). Bayesian networks allow us to determine, given a set of variables whose status is known, the probability that the other variables are true or false. We propose to implement a reusable process for representing Bayesian Networks as Atomspaces in MeTTa, and demonstrate how the MeTTa implementation can be used for inference on the network.
Many video games, such as Rogue, Diablo, and No Man’s Sky use procedurally-generated maps to help build large worlds that offer fresh experiences with every new play-through. We believe that the non-determinism offered by MeTTa can facilitate an interesting approach to this task, and serve as an interesting demo.
We aim to write a demo MeTTa program for generating and viewing randomly-generated maps. We believe that this will offer value in the fact that these algorithms are well-established and researched, and so they may offer a good way of comparing MeTTa to other languages. Additionally, viewing the output of a MeTTa program may help people understand the language better.
The MeTTa Coder Lab, an innovative educational program focused on lowering the entry bar for newcomers to MeTTa language. Structured into four progressive modules, the program guides participants through foundational knowledge, advanced concepts, and practical applications. Through a blend of synchronous and asynchronous methodologies, participants will explore modular design, dynamic reasoning, and AGI-focused applications. The program will provide multilingual resources in English, Portuguese, and Spanish, including open-source demos, tutorials, and gamified exams for certification. By fostering hands-on experimentation, we aim to empower developers and drive global adoption of MeTTa.
MeTTa was designed as a language for AGI, yet there is a noticeable lack of agent-based demos showcasing its full potential. This proposal seeks to address that gap through an innovative project that highlights MeTTa’s unique capabilities.
This project proposes a MeTTa-based simulation of a virtual dinner party involving neoteric agents with dynamic goal-setting, procedural learning, and introspective reasoning.
Each agent will have their own goals to hit during the dinner party. With their goals and knowledge stored in their Atomspace, each agent will be able to recursively subdivide their current goal, thus taking the best action at the moment to eventually reach their goal.
The AI Logic Puzzle Solver will provide an interactive platform where users input a logic puzzle in plain text, and MeTTa will solve it while explaining its reasoning process. This demo aims to highlight MeTTa's ability to process complex logic structures and deduce solutions efficiently and transparently. This project will deliver a lightweight yet powerful demo that highlights MeTTa’s logical reasoning capabilities. By solving classic puzzles interactively and transparently, the app will serve as an engaging entry point for exploring the potential of MeTTa within the SingularityNET ecosystem.
A groundbreaking application that integrates LLMs with MeTTa's symbolic reasoning via metta-motto, enabling dynamic, context-aware, and reasoning-driven language interactions for virtual agents in SophiaVerse.
We propose developing Empathetic AI Companions, AI-driven virtual agents capable of engaging with users based on real time emotional states detected via EEG. Using MeTTa scripting, these companions will dynamically adapt their behavior, responding empathetically to emotions such as happiness, sadness, focus and stress.
Leveraging our pre-existing EEG emotion classification model, developed under DF4 grant, this project will demonstrate MeTTa’s potential for real-time interaction and adaptive AI systems. While designed for versatile applications, these companions can seamlessly integrate into platforms like Sophiaverse, enhancing emotional engagement and interaction.
DeSearch AI is a decentralized research assistant leveraging SingularityNET's MeTTa programming language to automate and enhance key research activities, including literature review, paper summarization, and hypothesis generation. Designed to reduce the repetitive workload for researchers, DeSearch AI focuses on logical reasoning, decentralization, and adaptive learning, transforming raw research data into actionable insights. The project promises to accelerate scientific discovery by fostering a collaborative and decentralized approach to research.
Build general 3D Metaverse interfaces, fully customizable environments in which users can access and interact with information (and other users) anywhere in the world. With tools like Unity for the more front-end aspects, and tools like MeTTa for the more back-end aspects, we can build the first generation of interfaces into the long-anticipated Metaverse, which will open up vast new possibilities for learning, collaboration, organization, etc.
We propose to develop an AI-powered Integrated Development Environment (IDE) that leverages MeTTa's metaprogramming capabilities to enable self-modifying source code. This IDE will allow non-developer and developer users to interact with software programs that adapt themselves to fulfill user requirements dynamically. By integrating MeTTa into the IDE, we will create a platform where the source code adjusts itself based on user inputs, making programming more accessible, efficient, and alive. The project will involve forking and customizing an existing IDE (e.g., VS Code, Cursor AI, or Void) and incorporating MeTTa's features to achieve self-modification of programs.
The MeTTa Medical Guideline Chatbot (MMGC) project aims to develop an intelligent chatbot system that provides accurate medical guidelines to healthcare professionals and patients. Utilizing the MeTTa programming language, the chatbot will interpret natural language queries, convert them into MeTTa queries, and retrieve relevant medical information from a structured knowledge base. This project will showcase MeTTa's capabilities in natural language processing, data querying, automated reasoning, and demonstrate its potential in creating valuable medical AI applications within the SingularityNET ecosystem.
D ADA GA N, a neo-dadaist artist bot introduced at Tate Modern in 2019, was trained on over 100K drawings from DADA.art. Its first collection, minted in 2019, is recognized as a historic NFT and GAN artwork. As a satirical, anarcho-capitalist artist machine, D ADA GA N produces art, self-promotes, interacts with its community on Twitter, and autonomously sells NFTs via smart contracts. This proposal seeks to expand its capabilities on the MeTTa and Hyperon frameworks, enabling independent decision-making, adaptive learning, and real-time interactions, showcasing MeTTa’s potential for autonomous agents in blockchain art ecosystems.
A flexible, powerful semantic search engine built entirely in MeTTa, demonstrating the language's unique capabilities in knowledge representation, pattern matching, and nondeterministic reasoning.
This proposal aims to develop an AI-powered interactive coding education platform that leverages SingularityNET’s MeTTa programming language. The platform will provide real-time feedback, gamified learning structures, and a personalized learning experience to help learners improve their coding skills in an engaging and efficient way.
The project will create an intuitive and educational demo showcasing MeTTa’s capabilities while offering learners a structured pathway to master programming.
By combining AI, gamification, and open-source tools, this project will promote MeTTa adoption within the SingularityNET community and contribute to the global coding education ecosystem.
Automated Peer Review of Recent Preprints in MeTTa
Expert Rating
2.3
We propose developing an AI-powered system for automated peer review of bioRxiv preprints using MeTTa. The exponential growth of preprints in computational biology and computer science has created an urgent need for rapid evaluation mechanisms, as these fields evolve too quickly for traditional peer review cycles. Our system will leverage MeTTa's unique capabilities to provide rapid, transparent, and justified assessments of preprint quality and impact.
The goal of this project is to create useful demonstrations of how to bring recent scientific knowledge graphs of various formats and sizes to OpenCog Hyperon. This is achieved by extending an existing literature review and ETL package from the author in DFR3 by covering newer literature, adding several new KGs to the package and implementing further MeTTa encodings in the loading step to enable more efficient queries (e.g. via MORK and/or PLN). A downstream objective is to thereby support 1) ongoing development and testing of MeTTa scalability solutions such as MORK and 2) other knowledge graph projects in the SingularityNET ecosystem such as Rejuve's work on biomedical knowledge graphs.
This project focuses on creating a MeTTa demo for sequence learning. A sequence learning model will be implemented in MeTTa, designed to learn in real-time and continuously predict future events. The model is capable of continual learning without experiencing catastrophic forgetting. Additionally, its internal states will be visualized, enabling users to interpret and explain the model's behavior. This demo aims to showcase the development of a relatively complex MeTTa project and demonstrate how MeTTa can be utilized in advanced AI research.
This proposal aims to develop an innovative interactive experience powered by MeTTa/Hyperon, highlighting their advanced reasoning and memory management capabilities. Users will engage with a dynamic system where their actions drive the progression, while a live panel provides insight into the underlying logic in real time. The project balances entertainment with education, offering a clear demonstration of MeTTa/Hyperon's potential. Future enhancements may include integration with Zarqa’s capabilities to further expand the system’s interactivity and depth.
Programming is evolving: from writing solutions to systems that evolve to find their own solutions. The idea behind Chimera is that software of any kind, including agents, can use MeTTa to learn from experiences and evolve through distributed knowledge sharing. AtomSpaces can accelerate learning across multiple instances and agents, allowing each agent or even "dumb" software to benefit from others' evolutionary insights. This proposal's demos will look at self-healing servers, database queries that evolve for performance, and move toward machine "self-consciousness" through reflection and world modelling. The end result will be an SDK/module for use in real projects
Hi Jan, thank you very much for your question!! The answer is yes –– we would love to welcome any single entity to submit multiple proposals for this RFP.
Nice to meet you! If you have any question about our services,
feel free to contact us.
Send a message
Sending…
We're on it!
You'll receive an email reply within 1-2 days.
We use cookies to ensure that we give you the best experience on our website. If you continue to use this site we will assume that you are happy with it.Ok
logannn
Aug 27, 2024 | 1:43 AMEdit Comment
Processing...
Please wait a moment!
looking forward to this one!
khellar
Sep 4, 2024 | 6:16 AMEdit Comment
Processing...
Please wait a moment!
Cheers, I thought you might be!
Jan Horlings
Project Owner Aug 15, 2024 | 9:19 AMEdit Comment
Processing...
Please wait a moment!
Hi Khellar, is it possible for a single organization or team, to submit multiple proposals?
khellar
Sep 4, 2024 | 6:17 AMEdit Comment
Processing...
Please wait a moment!
Please stand by Jan, I'm checking with some colleagues and will get back to you asap :)
khellar
Sep 4, 2024 | 6:32 AMEdit Comment
Processing...
Please wait a moment!
Hi Jan, thank you very much for your question!! The answer is yes –– we would love to welcome any single entity to submit multiple proposals for this RFP.