Directory
Published directory entries matching your search.
The kaggle-bestbuy big repository, hosted on GitHub under the user zygmuntz, contains code for the Best Buy competition hosted on the Kaggle data science platform. It is an open-source project that accepts contributions from GitHub users.
Keepsake is a version control system for machine learning projects. It allows tracking changes to models, data, and experiments. It is developed by Replicate and hosted on GitHub as an open-source repository. The project is not actively maintained.
Kiln AI is a platform and open-source library for building, evaluating, and optimizing AI systems. It offers tools for working with retrieval-augmented generation, AI agents, synthetic data, model fine-tuning, and prompt optimization, with a free downloadable application available for macOS, Windows, and Linux.
Open source MLOps project that eases model handoffs between data scientist and DevOps.
Kubeflow is described as the cloud native AI platform, composed of modular open source projects forming a Kubernetes-native stack for data and AI workloads. Its subprojects include Kubeflow Pipelines for building and deploying portable machine learning workflows, Kubeflow Trainer for distributed AI training and LLM fine-tuning, Kubeflow Katib for automated machine learning, Kubeflow Notebooks for interactive development environments, and Kubeflow Hub for indexing models and metadata. It is a Cloud Native Computing Foundation project.
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.
Linear Digressions is a podcast series covering machine learning and AI topics, with episodes such as "LLM as a Judge," a cross-post on AI and podcasting from the Harvard Data Science Review, and a benchmark installment on ExploitGym. One episode examines mechanistic interpretability, described as an approach that opens the model itself to trace why it behaves as it does.
LlamaIndex is an open-source document processing platform built for artificial intelligence applications. It is maintained in a GitHub repository by run-llama, offering tools to handle documents as part of AI workflows.
A tool that provides a Model Context Protocol server for any web application with an OpenAPI specification. It can connect Claude Desktop and other apps to external tools and data services, similar to ChatGPT plugins.
Lutra AI is a productivity agent platform that connects to work applications and services to build custom automations. It supports integration standards including MCP, REST, and OpenAPI, with use cases such as contact enrichment, data extraction, and email campaign assistance.
Meaning of is the personal blog of Kenny Bastani, covering open source software, graph databases, cloud native architectures, information theory, artificial intelligence, and machine learning. As of September 18, 2025, the blog is no longer maintained, with readers directed to the author's GitHub or LinkedIn profiles.
MetaReview is a free, open-source online meta-analysis tool that combines PubMed literature search, AI screening and data extraction, effect-size calculation for OR/RR/HR/MD/SMD, forest and funnel plots, subgroup and sensitivity analysis, PRISMA flow diagrams and report export. It runs in the browser without R, Stata or RevMan. A comparison page states the tool is free.
Milvus is open source vector database for production AI, written in Go and C++, scalable and blazing fast for billions of embedding vectors.
MLRun is an open source MLOps platform for building and managing continuous machine learning applications across their lifecycle. It integrates with development and CI/CD environments to automate the delivery of production data, ML pipelines, and online applications.
mlxtend is a library that provides extension and helper modules for Python's data analysis and machine learning libraries. The project includes installation guides, example code, license information, and contact details. It is hosted as an open source repository on GitHub.
An open standard for connecting AI models to external tools and data sources. MCP Registry opensource.
NASGym is a proof-of-concept OpenAI Gym environment for Neural Architecture Search. It implements reinforcement learning steps for NAS and encodes networks using the Neural Structure Code from BlockQNN. A network is modeled as a list of NSCs, an action adds a layer, and the reward is accuracy after early-stop training. CIFAR-10 is the default dataset. The code and documentation may contain minor bugs.
Ombre is an open-source AI infrastructure layer. It runs eight specialized agents on every request to handle security, caching, memory, hallucination detection, and tamper-proof audit trails. It is installed with one line of code, and user data never leaves the user's server.
onWatch is an open-source tool developed by onllm-dev that tracks AI API quotas for services including Synthetic, Z.ai, Anthropic Claude Code, Codex, GitHub Copilot and Antigravity in real time. It functions as a lightweight background daemon that uses less than 50MB of RAM, stores data in SQLite, and provides a Material Design 3 dashboard. The tool does not collect telemetry.
Model Context Protocol - An open standard for connecting AI models to external tools and data sources. MCP Registry.
Vanna is an open source tool that enables users to interact with SQL databases via natural language. It uses large language models and agentic retrieval to generate accurate text-to-SQL queries.
pgvecto.rs is an open-source tool that provides scalable, low-latency, hybrid-enabled vector search for PostgreSQL. It is designed to enhance vector search capabilities without modifying the core database system, per its official GitHub repository.
PyOD is an open-source Python library hosted on GitHub for anomaly detection across tabular, time series, graph, text, image and audio data. It includes over 60 anomaly detectors, an ADEngine orchestration tool, and supports agentic workflows for use with AI agents.
Pyramid Flow is a training-efficient autoregressive video generation model based on Flow Matching, presented as Pyramidal Flow Matching for Efficient Video Generative Modeling. It was trained only on open-source datasets within 20.7k A100 GPU hours. The project page shows text-to-video generation at 1280x768 in 10-second and 5-second, 24fps clips, plus text-conditioned image-to-video.
