Directory
Published directory entries matching your search.
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.
Kitaru is an open-source, self-hosted tool providing replay-based evaluations for AI agents. It records or imports production runs as sessions and replays them against a changed model, prompt, or code, with tool calls answered from the recording. It is available for Python and TypeScript and comes from the team behind ZenML.
L2MAC is an open-source framework described as a Large Language Model Automatic Computer. It uses a prompt-program with instruction steps executed by agents that read and write to persistent memory, intended for generating extensive outputs such as large codebases. It is released under the MIT license.
lakeFS is a source-available data version control tool that turns object storage into a Git-like repository, allowing data lakes to be managed like code. It supports AWS S3, Azure Blob Storage and Google Cloud Storage, is API compatible with S3, and works with frameworks such as Spark, Hive, AWS Athena, DuckDB and Presto.
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.
LeanCTX is an open-source context gateway that sits between AI tools and the information they read. It selects task-relevant context, applies supported access and content controls, and records observable context operations and evidence. The engine can run locally through CLI, MCP, hooks and proxy paths, and an SDK embeds supported engine capabilities in applications.
Llama Coder is an open source Claude Artifacts alternative that generates small apps with one prompt, powered by Llama 3 on Together.ai. It uses Llama 3.1 405B from Meta for the LLM and an in-browser preview renderer.
Localforge is a free, open-source desktop GUI for Codex AI, Claude and other LLMs. It runs locally and lets autonomous agent loops edit files, run tests and work on large multi-file codebase tasks. It supports swapping providers and storing prompt templates, and is distributed under the MIT license.
MEKA is an open source implementation of methods for multi-label learning and evaluation, based on the WEKA Machine Learning Toolkit. It includes dozens of multi-label methods from the scientific literature and a wrapper to the MULAN framework. The project is distributed via SourceForge, with code hosted on GitHub.
PraisonAI is an open-source project hosted on GitHub under the MervinPraison/PraisonAI repository. It enables the deployment of autonomous, self-improving AI agents capable of researching, planning, coding, and executing tasks. The tool includes built-in memory and retrieval-augmented generation (RAG) capabilities, supports over 100 large language models, and can be deployed with 5 lines of code.
Repository containing the source code of the Python package loralib and examples of integrating it with PyTorch models, such as those in Hugging Face. LoRA learns pairs of rank-decomposition matrices while freezing the original weights, reducing the number of trainable parameters. PyTorch is the only supported framework for now.
ml.js is an open-source machine learning toolset implemented in JavaScript, hosted in the mljs/ml GitHub repository. It provides libraries for both supervised and unsupervised machine learning tasks, alongside usage resources and standalone example code for users.
MLReef is an open source ML-Ops platform for collaborating, reproducing and sharing machine learning work. The repository notes it is no longer supported or updated there, with work continuing on GitLab. Described sections include data management with versioned data hosting, containerized code repositories, experiment tracking and ML pipelines on Kubernetes, cloud or bare metal.
MLX is an array framework developed for use on Apple silicon hardware. The project includes example code, quickstart guides, installation instructions, and contribution guidelines. It is hosted as an open source repository on GitHub.
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.
MMDeploy is documented at version 1.3.1 and covers getting started, converting, running, evaluating and quantizing models, building from source or Docker image, and SDK usage. Its backend support pages describe ncnn, ONNX Runtime, OpenVINO, PPLNN, SNPE, TensorRT, TorchScript, RKNN, TVM and Core ML, and its codebase support covers several OpenMMLab projects.
An open standard for connecting AI models to external tools and data sources. MCP Registry opensource.
Discover open source deep learning code and pretrained models.
ModelDB is an open-source system for versioning machine learning models, including their code, data, config and environment, and for tracking ML metadata across the model lifecycle. It supports reproducible models, experiment management and lifecycle tracking. It runs on Docker and Kubernetes, offers Python and Scala clients, and is maintained by Verta.ai.
N2D2 is an open source computer-aided design (CAD) framework developed for deep neural network (DNN) simulation and the construction of full DNN-based applications. It is maintained as a public code repository by the research organization CEA-LIST.
NumPy is a Python library providing a multidimensional array object and routines for fast operations on arrays, including mathematical, logical, sorting, Fourier transforms, linear algebra and random simulation. It is open source under a BSD license and is described as the fundamental package for scientific computing in Python, with core code written in optimized C.
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.
Onyx is an open-source AI platform that connects to applications to index and surface knowledge, with self-hosted deployment options. It provides agentic RAG search, deep research reports, custom agents, web search, a secure sandbox for code execution, artifacts, and voice mode. It works with major LLMs.
