Guild AI is the source repository for an open source toolkit that automates and optimizes machine learning experiments. It runs unmodified training scripts, captures each run result as a unique experiment, and automates trials using grid search, random search and Bayesian optimization.
jcode is an open-source terminal coding agent written in Rust. It supports agent swarms, background tasks, and a small RAM footprint, and is installed with one command on macOS, Linux, or Windows. Login flows connect subscription and API model providers, and the agent itself is free while hosted inference plans are available.
Kilo is an open source AI coding agent for VS Code, JetBrains, CLI, desktop and cloud. It offers access to 500+ models at zero markup, bring-your-own keys, or local models for privacy. Kilo Gateway provides a unified API to access AI models through a single endpoint.
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.
Models.dev is an open-source database that lists AI model specifications, pricing and features. It covers models from multiple providers with details such as context length, modalities and open or closed availability.
Supermaven is an AI code completion tool that uses a 1 million token context window to provide code suggestions. It is compatible with VS Code, JetBrains IDEs and Neovim, and includes a chat interface for working with models including GPT-4o and Claude 3.5 Sonnet. A free tier is offered, and Pro adds a 1 million token context window.
Langfuse is an open source platform for tracing, evaluating and improving AI agents. It connects tracing, monitoring, datasets, experiments and evaluation in one continuous loop, capturing every LLM call, tool invocation and retrieval step. The platform includes prompt management, a playground, experiments and human annotation, and works with any language or framework supporting OpenTelemetry instrumentation.
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
jcode is an open-source terminal coding agent written in Rust. It supports agent swarms, background tasks, and a small RAM footprint, and is installed with one command on macOS, Linux, or Windows. Login flows connect subscription and API model providers, and the agent itself is free while hosted inference plans are available.
Kilo is an open source AI coding agent for VS Code, JetBrains, CLI, desktop and cloud. It offers access to 500+ models at zero markup, bring-your-own keys, or local models for privacy. Kilo Gateway provides a unified API to access AI models through a single endpoint.
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.
Models.dev is an open-source database that lists AI model specifications, pricing and features. It covers models from multiple providers with details such as context length, modalities and open or closed availability.
Supermaven is an AI code completion tool that uses a 1 million token context window to provide code suggestions. It is compatible with VS Code, JetBrains IDEs and Neovim, and includes a chat interface for working with models including GPT-4o and Claude 3.5 Sonnet. A free tier is offered, and Pro adds a 1 million token context window.
Langfuse is an open source platform for tracing, evaluating and improving AI agents. It connects tracing, monitoring, datasets, experiments and evaluation in one continuous loop, capturing every LLM call, tool invocation and retrieval step. The platform includes prompt management, a playground, experiments and human annotation, and works with any language or framework supporting OpenTelemetry instrumentation.
