A Python CLI framework that stores threat‑hunting investigations as markdown using the LOCK pattern, makes them searchable, and optionally lets LLM agents generate research, run queries, and automate parts of the hunt.

A cost-effective inference library that enables running large Mixture-of-Experts models on memory-constrained GPUs by offloading expert weights to host memory and SSD.

A universal environment framework that runs AI agents against task environments and scores them through a standardized contract, treating benchmarks as frozen environments.

A platform for provisioning on-demand, isolated Linux microVMs that AI agents can use to execute code and browse the web securely.

A Rust-based long-term memory framework for AI agents that uses a three-tier hierarchical architecture and a virtual filesystem to provide persistent, context-aware interactions.

An open-source digital asset manager and gallery built for ComfyUI and AI production libraries to organize, search, and remix generations.

A synthetic environment generation pipeline that creates thousands of SQL-backed tool-use environments for large-scale agentic reinforcement learning.

A lightweight, open-source IAM stack that secures access for humans, AI agents, and machines with support for post-quantum security and decentralized identity.

A PyTorch-based framework for simulating quantum computations on classical hardware, enabling the training of parameterized quantum circuits and hybrid classical-quantum models.

A planning-and-execution layer for AI coding agents that turns high-level requests into structured plans and parallelized PRs through a rigorous design-and-review workflow.

A unified multimodal backend for AI data apps that combines a database, orchestration, and serving layers into a single Python file.

Rust bindings for the PyTorch C++ API (libtorch), enabling the use of PyTorch's tensor operations and deep learning tools in Rust.

An interactive terminal-based JSON query tool that provides real-time output and AI-powered assistance for writing jq queries.

A Go-based vulnerability scanner and exploitation tool for the Spring framework that integrates with AI agents via MCP to automate penetration testing.

A Python library for black-box optimization of mixed search spaces, providing a unified interface to 23 gradient-free algorithms for hyperparameter tuning and engineering design.

A bilingual and crosslingual embedding and reranking framework optimized for RAG, specializing in high-performance retrieval across Chinese and English.

A lightweight training framework for large-scale language models that focuses on modular configurations and fast iteration across SFT, RLVR, and evaluation.

An MCP server that allows AI assistants to programmatically control Adobe Photoshop on Windows to create documents, manage layers, and apply effects.

An open AI application framework for cybersecurity developers to build optimized pipelines for real-time IP traffic inspection and threat detection in data centers.

A hardened, minimal Linux operating system purpose-built for running AI agents securely with dedicated orchestration daemons and reproducible image builds.

A Python library for geospatial machine learning that provides tools to acquire vector data, divide areas into micro-regions, and embed them into vector spaces.

A PostgreSQL extension that implements the BM25 ranking algorithm and Block-WeakAnd indexing to provide native, high-performance full-text search and relevance scoring.

A Visual Studio Code extension that integrates Azure Machine Learning service to help users build, train, and deploy ML models to the cloud or edge.

A dynamic status line extension for pi CLI and DeepSeek Harness that provides real-time visibility into AI agent tool usage, progress, and internal reasoning.

An open-source AI agent runtime that turns an AI agent into a personal DNA expert by providing a local, private workspace for analyzing raw genomic data.

Julia bindings for Enzyme, a high-performance automatic differentiator that operates on LLVM to provide efficient gradients for optimized code.

A comprehensive evaluation library for NLP and LLM models to test for robustness, bias, fairness, and safety.

A Java thread dump and heap analysis tool that provides a GUI and an MCP server for diagnosing deadlocks, performance issues, and virtual thread pinning.

A lightweight, portable pure C99 ONNX inference engine designed for embedded devices with support for hardware acceleration.

A programming language designed for LLMs to write, featuring structural references instead of variable names and mandatory SMT-proven contracts to ensure correctness.

TorchX is a universal job launcher for PyTorch applications that allows users to launch jobs across Kubernetes, Slurm, Docker, and local environments.

An AI-as-a-Service platform to create and deploy RAG systems, agents, and inference endpoints via a REST API with a full management dashboard.

An automated evaluation framework for text-to-image and text-to-video models that uses multimodal LLMs to score visual-text alignment.

A public leaderboard that uses Vectara's Hallucination Evaluation Model (HHEM) to measure and compare how often different LLMs hallucinate when summarizing documents.

A Python library for building genetic algorithms to optimize machine learning algorithms and other mathematical functions.

A library for probabilistic reasoning and statistical analysis that integrates probabilistic methods with deep networks using TensorFlow or JAX.

LlamaDeploy is a tool for deploying and serving AI workflows, though it is now deprecated in favor of llama-agents.

A scikit-learn compatible library of Relief-based feature selection algorithms that identify important feature interactions in tabular data without exhaustive searching.

A probabilistic logic programming toolbox that combines logic programs with probabilistic facts to handle uncertainty and perform complex inference tasks.

autoresearch‑claude‑code is a Python framework that runs budget‑constrained auto‑research loops with Claude Code or Codex agents. You define a goal, a deterministic scorer, and files the agent may edit; the system creates a Git branch, measures each change, and automatically commits only statistically‑significant improvements while respecting run‑time and turn limits.

A tool for automating the and evaluation of multiple LLMs, prompts, and inference parameters via Ollama to find the optimal configuration for a specific task.

DR Tulu is an open‑source 8 B‑parameter model and toolkit for building research‑oriented agents that can browse, retrieve scholarly information, and generate long‑form answers. The repo provides an agent library with async tool‑calling, RL training (GRPO + evolving rubrics), SFT pipelines, evaluation scripts for multiple research benchmarks, and a CLI demo that runs on 1‑2 GPUs.

An open-source Gymnasium environment for simulating building energy coordination and demand response using multi-agent reinforcement learning.

A unified framework for Scientific Machine Learning (SciML) providing implementations of PINNs, DeepONets, and KANs for studying complex physical systems.

A collection of Python scripts to test OpenAI-compatible model endpoints to verify if the model being served matches its label.

A high-performance inference engine that uses SVDQuant to enable 4-bit quantization for diffusion models, significantly reducing VRAM usage and increasing inference speed.

A tuned OpenCL BLAS library that provides high-performance linear algebra routines for a wide variety of GPUs and accelerators.

A multi-tenant Postgres platform that decouples storage from compute to help B2B SaaS applications scale securely and efficiently with integrated vector database support.