A Python library for reading and processing data for training and evaluating JAX models, providing a fast and deterministic data pipeline.

A Python package implementing the double/debiased machine learning framework for estimating structural parameters with reduced bias using scikit-learn.

A reinforcement learning rollout framework that provides rollout-as-a-service for training multi-turn LLM agents across diverse agent harnesses.

An LLM-based vulnerability discovery tool that finds and verifies security flaws in source code through a two-stage detection and attack process.

A fully-local session memory tool for Claude Code and OpenCode that automatically logs activity and creates compact summaries to eliminate the cold-start problem.

A PyTorch library for differentiable signal processing on the sphere, enabling spherical harmonic transforms and neural operators for physics-based AI.

A scalable simulator for spiking neural network models used to study the dynamics, size, and structure of neural systems.

A fast and extensible library for training, evaluating, interpreting, and serving decision forest models like Random Forest and Gradient Boosted Trees.

A Java-based LLM code assistant for IntelliJ IDEA that enables autonomous agentic programming, spec-driven development, and integrated security scanning using local or cloud LLMs.

A tool for managing and deploying AI models via Docker, streamlining the process of pulling and serving LLMs using backends like llama.cpp and vLLM.

A Python library for defining and optimizing symbolic mathematical expressions with multi-dimensional arrays, serving as the computational backend for PyMC.

An MCP server providing LLMs with real-time and historical financial data for Borsa Istanbul, US stocks, TEFAS funds, and crypto, enabling AI-driven financial analysis.

A security auditing tool for AI agent skills that analyzes markdown-based skills to identify potential security risks and provide evidence-backed reports before execution.

A multi-vector search engine (NextPlaid) and a corresponding semantic code search tool (ColGREP) that provide high-precision retrieval by storing multiple embeddings per document.

A high-performance C++ vector indexing library for similarity search, featuring specialized indexes for both sparse and dense vectors with Python and TypeScript bindings.

A Model Context Protocol (MCP) server that connects AI assistants to DuckDB and MotherDuck for SQL analytics and data engineering.

A multi-agent AI framework for Claude Code that implements a spec-driven development workflow to turn ideas into shipped code via structured planning and parallel specialist agents.

WildClawBench is an end-to-end agent benchmark that tests AI agents' ability to perform complex, real-world tasks in live environments using real tools like browsers and bash terminals.

A tool that analyzes repositories to find and apply the cheapest, most reliable AI coding configuration by testing candidates against real-world tasks.

A native Swift inference server for Apple Silicon that serves MLX models via an OpenAI-compatible API, featuring SSD expert streaming and KV cache compression.

KVPress is an NVIDIA‑maintained Python library that provides a suite of *presses*—algorithms for compressing the key‑value cache of transformer‑based LLMs. By pruning or approximating KV entries during the prompt‑prefill phase (and optionally during decoding), KVPress dramatically cuts the memory needed for long‑context inference, enabling cheaper, faster generation of very large prompts.

A CLI tool for scaffolding production-ready LLM training projects, providing templates for different model sizes and a complete pipeline from tokenization to deployment.

A collection of Model Context Protocol (MCP) servers that enable LLMs to query Neo4j databases, manage Aura cloud instances, and maintain persistent knowledge graph memory.

An open-source, real-time context infrastructure that synchronizes AI agent sessions, allowing users to share and version context across different AI tools.

An embeddable, zero-dependency vector database for Go that enables RAG and semantic search without requiring a separate database server.

A single-node launcher for DeepSeek V4 Flash on NVIDIA DGX Spark, enabling high-throughput serving with speculative decoding and context windows up to 384k tokens.

A lightweight Python proxy that allows multiple AI agents, including Hermes Agent, OpenClaw, and OpenCode, to run simultaneously on a single WeChat account.

A high-performance toolkit and 3-trillion-token open dataset for curating and cleaning large-scale corpora for language model pre-training.

A scalable toolkit for cleansing, transforming, and enriching unstructured data to prepare it for LLM pre-training, fine-tuning, and RAG applications.

Prime Intellect offers a Python‑based CLI and SDKs to provision cloud GPU pods, run hosted model training, manage verified environments, push evaluation results, and work with sandboxed code—all from the command line.

An open-source ranking service that provides real-time personalization and reranking for search and recommendation systems using machine learning and LLMs.

A macOS menu bar app that turns the Caps Lock key into a physical switch to keep MacBooks awake and running processes during closed-lid use.

An AI-powered penetration testing engineer for authorized security assessments that automates the discovery of business-logic flaws and cloud misconfigurations across global and Chinese cloud providers.

An open-source API security platform that provides continuous API inventory and tests for business logic vulnerabilities using real traffic data.

A browser-based Gomoku AI implemented using the Minimax algorithm and Alpha-Beta pruning, featuring adjustable difficulty and a comprehensive performance evaluation suite.

A lightweight compatibility layer that enables developers to write dataframe-agnostic code, supporting libraries like pandas, Polars, and cuDF without requiring them as dependencies.

A durable execution runtime for Laravel that allows long-running PHP workflows to persist state and resume after failures or restarts.

A universal data framework and serialization format for processing and analyzing uni- and multi-modal spatial omics datasets.

A backend toolkit for building full-stack AWS applications that allows developers to run their entire backend locally before deploying the same code to AWS.

An open-source MySQL branch that integrates DuckDB for high-performance analytics and native HNSW vector search for AI applications.

A Python library providing a wide range of solvers for Optimal Transport problems used in machine learning, signal processing, and image processing.

A library that brings WebGPU capabilities to React Native applications using the Dawn implementation for high-performance GPU computing and graphics.

A graph data science library for Neo4j that provides graph algorithms, transformations, and machine learning pipelines operated via Cypher procedures.

An AI-powered, free alternative to Postman for API testing, mocking, and collaboration, supporting local-first usage and self-hosting.

A developer-focused toolkit for Julia that provides standardized interfaces and reusable functionality for creating new GPU array types across different hardware backends.

An optimized Basic Linear Algebra Subprograms (BLAS) library that provides high-performance linear algebra routines across a wide variety of CPU architectures.

A simple, compact Python-based chess engine that serves as a platform for experimenting with search algorithms and neural network evaluations.

A monitoring and control package for NVIDIA Jetson series boards that provides real-time hardware stats and system management via a terminal UI or Python library.