MiniAGI is a simple autonomous agent compatible with GPT-3.5-Turbo and GPT-4. It combines a prompt with a minimal set of tools, chain-of-thoughts and short-term memory with summarization, and is capable of inner monologue and self-criticism. A critic can be enabled for additional API requests.
Nixified packages AI executable code as self-contained Nix packages, including dependencies, and builds each project from source. Users can install and run the code with a single nix command on Linux distributions and on Windows through WSL. The project lists textgen and InvokeAI as packaged projects and offers GPU support for NVIDIA and AMD.
Creator Website provides machine-learning models, research, training resources, or evaluation tools.
NExT-Chat is a large multimodal model trained using the pixel2emb method, in which the model outputs location embeddings decoded by different decoders. This allows bounding boxes and masks in multimodal conversations and supports tasks such as visual grounding, region caption and grounded reasoning.
Juno is an AI researcher that designs studies, interviews real people, and works through the evidence to report findings. It offers REST, MCP and A2A API access with self-service API keys scoped to one organisation. Pricing is $45 USD per completed interview, with study design free and no seats or subscription; recruitment and incentives are not included.
ahaz is an R package providing computationally efficient procedures for regularized estimation with the semiparametric additive hazards regression model. It depends on R version 2.10 or later, along with survival, Matrix and methods, and requires compilation. The package is authored and maintained by Anders Gorst-Rasmussen under GPL-2 and appears in the MachineLearning and Survival views.
StepByStepML provides free online machine learning calculators that solve algorithms step-by-step for computer science exams. Users input a dataset and the site shows the full manual calculation for algorithms including K-Means, Minimax, KNN, A* Search, and evaluation metrics. Theory guides accompany the interactive solvers, and the site states it is built for CS students.
Community notes
Be the first to share how this project worked for you.
Sign in with a verified account to leave a review or join the discussion.
Sign in to reviewKeep exploring
Nixified packages AI executable code as self-contained Nix packages, including dependencies, and builds each project from source. Users can install and run the code with a single nix command on Linux distributions and on Windows through WSL. The project lists textgen and InvokeAI as packaged projects and offers GPU support for NVIDIA and AMD.
Creator Website provides machine-learning models, research, training resources, or evaluation tools.
NExT-Chat is a large multimodal model trained using the pixel2emb method, in which the model outputs location embeddings decoded by different decoders. This allows bounding boxes and masks in multimodal conversations and supports tasks such as visual grounding, region caption and grounded reasoning.
Juno is an AI researcher that designs studies, interviews real people, and works through the evidence to report findings. It offers REST, MCP and A2A API access with self-service API keys scoped to one organisation. Pricing is $45 USD per completed interview, with study design free and no seats or subscription; recruitment and incentives are not included.
ahaz is an R package providing computationally efficient procedures for regularized estimation with the semiparametric additive hazards regression model. It depends on R version 2.10 or later, along with survival, Matrix and methods, and requires compilation. The package is authored and maintained by Anders Gorst-Rasmussen under GPL-2 and appears in the MachineLearning and Survival views.
StepByStepML provides free online machine learning calculators that solve algorithms step-by-step for computer science exams. Users input a dataset and the site shows the full manual calculation for algorithms including K-Means, Minimax, KNN, A* Search, and evaluation metrics. Theory guides accompany the interactive solvers, and the site states it is built for CS students.
