A cross-harness configuration organizer for AI coding tools that provides a unified dashboard to manage memories, skills, and MCP servers while optimizing token usage and detecting tool poisoning.

A governed, local-first agent runtime for Python that provides strict permission controls, persistent memory, and tool connectivity via MCP/ACP.

An open-source GTM engine and Clay alternative that orchestrates AI agents across your sales stack to automate lead sourcing, qualification, and personalized outreach.

An engineering governance and context framework for AI coding agents that provides shared instructions, architecture standards, and governed workflows across teams.

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

A Python-native toolkit for applied causal inference and econometrics that replaces the need to switch between Stata and R for empirical research workflows.

A Windows application for video localization that automates transcription, translation, and dubbing using AI models like Faster-Whisper and various TTS engines.

A pure C implementation of an AI assistant for the ESP32-S3 chip, providing a low-power, always-on agent with local memory and tool-calling capabilities via Telegram.

A multi-agent workspace that transforms existing AI CLI tools into a unified orchestration hub for parallel execution and automated workflows.

A toolkit for training and running inference on audio generation models, supporting various model types including diffusion and autoencoders.

A collection of Gymnasium-compatible environments for autonomous driving and tactical decision-making tasks.

A framework for synthesizing synthetic data and AI feedback to create high-quality datasets for training and fine-tuning AI models.

A PostgreSQL extension that enhances pgvector with a StreamingDiskANN index and Statistical Binary Quantization for high-performance, cost-efficient embedding search.

An open source Python framework for the holistic, reproducible, and transparent evaluation of foundation models, including LLMs and multimodal models.

An opinionated agent infrastructure that uses a multi-process architecture to handle concurrent conversations, long-term typed memory, and autonomous background tasks for teams and communities.

A series of billion-parameter text-to-3D human motion generation models that create skeleton-based animations from text prompts using Diffusion Transformers and Flow Matching.

Trackio is a free, lightweight experiment‑tracking library (compatible with wandb) that stores logs locally in SQLite, offers a fast non‑blocking API, a Gradio‑style dashboard, CLI/SQL query tools, alerts, and optional free hosting on Hugging Face Spaces or self‑hosting.

An official Model Context Protocol (MCP) server that enables LLMs to use Qdrant as a semantic memory layer for storing and retrieving information.

A local-first desktop AI assistant that uses agent orchestration and durable memory to perform complex work across local files, repositories, and external tools.

A Burp Suite extension that integrates AI agents and LLMs to automate vulnerability scanning and security analysis across 62 vulnerability classes.

A local-first knowledge management system that captures, indexes, and makes searchable all interactions with AI coding assistants across various IDEs and CLI tools.

MACE is an open‑source PyTorch library for equivariant graph‑neural‑network interatomic potentials. It provides fast training/evaluation, multi‑GPU and Apple‑Silicon support, optional CUDA acceleration, and a catalog of pre‑trained foundation models for materials and organic chemistry. Install via `pip install mace-torch`, train with the `mace_run_train` CLI (or YAML configs), and evaluate with `mace_eval_configs`. Documentation, Colab tutorials, and Weights & Biases integration are included. The project is stable on the v0.3 line while a major v1.0 rewrite is in progress.

OpenTSLM is an open‑source library that adds native time‑series handling to Llama 3.2 and Gemma LLMs, enabling natural‑language prompting and reasoning over medical signals (ECG, EEG, accelerometer, etc.). It provides pre‑trained checkpoints, a simple `OpenTSLM` Python API, demo scripts for inference on several benchmark tasks, and a curriculum‑learning training pipeline covering MCQ, captioning, and chain‑of‑thought reasoning stages. Install via `pip install opentslm`, load models from Hugging‑Face, and fine‑tune or evaluate using the supplied scripts. Licensed under MIT.

Attention Gym is a PyTorch‑based library that supplies reusable mask/score‑mod functions, sparse‑attention patterns, and linear‑attention kernels for the FlexAttention API, plus example scripts and utilities for building and benchmarking custom attention mechanisms.

A collection of high-performance GPU kernels for deep learning operations like RMSNorm and Softmax, implemented using CuTe-DSL for modern NVIDIA GPUs.

A highly extensible AI bot framework that enables LLMs to execute code in secure sandboxes and interact across multiple chat platforms via a unified adapter architecture.

An all-in-one model console WebUI that prioritizes Google Gemini's native capabilities while supporting OpenAI-compatible APIs, featuring a local-first architecture for privacy.

A system for decoding natural sentences from non-invasive brain recordings, enabling the reconstruction of text from brain activity during typing.

An evidence-driven framework for creating and maintaining AI agent skills that uses behavioral testing to ensure every skill demonstrably improves performance.

A mobile-first web interface for OpenCode AI agents that allows users to manage repositories, control AI coding sessions, and configure agent skills from any device.

NavDP is an end-to-end mapless navigation model using diffusion policies that enables robots to perform real-time path planning and obstacle avoidance with cross-embodiment generalization from simulation to reality.

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

An adaptive multi-agent framework that automates complex data science workflows by separating planning from execution and utilizing a self-correcting, iterative validation loop.

An MCP server that allows AI assistants to manage Coolify self-hosted PaaS infrastructure through 44 consolidated tools for deployment, debugging, and operation.

A library and MCP server that connects AI agents to Todoist, enabling LLMs to access and modify tasks and account data.

A live visual surface for terminal coding agents that renders diagrams, UI sketches, and diffs in a browser to replace text-only communication.

A library of optimized neural network kernels for Arm Cortex-M processors that maximizes performance and minimizes memory footprint for on-device AI.

A GPT-style humanoid motion Transformer pre-trained on 2 billion frames to enable zero-shot whole-body motion tracking for humanoid robots like the Unitree G1.

An AI-native library and MCP for end-to-end testing that allows users to perform actions and verify assertions in applications using natural language via Appium, Playwright, or Selenium.

Apache Texera is an open‑source visual platform that lets users build and run data‑analysis pipelines through a drag‑and‑drop GUI, with AI agents that translate natural‑language commands into workflow steps. It supports Python and Java operators, real‑time collaboration, interactive debugging, and scales from a laptop to large cloud clusters.

An Android chat application that provides a unified interface for interacting with cloud-based LLMs via OpenRouter and locally hosted models via Ollama, LM Studio, and others.

A suite of advanced multi-modal LLMs that provide large language models with generic hearing abilities and integrated audio-visual perception.

A portable ncnn-based implementation of the Z-Image generator that enables high-performance image generation, inpainting, and ControlNet support on any Vulkan-capable GPU.

An agent control plane for governance, safety, and trust that provides a deterministic layer to define, enforce, and audit the behavior of autonomous AI agents.

A collection of production-ready AI agent templates and reference architectures for connecting autonomous agents to business APIs and tools.

MDia is a Python library that formalises LLM intermediate reasoning as reusable “dialect cards” (LSFs) and provides a deterministic eight‑stage pipeline (collect → create → evolve → profile → select → run → validate‑rules → report) for generating, evolving, profiling, routing, and auditing these protocols across heterogeneous models. It supports black‑box LLM APIs, offers several routing plans, includes a 100‑rule bank, and guarantees reproducibility by freezing decisions before test evaluation. The repo includes a toy offline demo that runs without any API keys, extensive documentation, MIT licensing, and a citation to the ICML 2026 poster and arXiv paper.

An AI-powered learning system that converts courses, books, and lecture notes into interactive tutors that guide users through practice and source-backed verification to achieve actual skill mastery.

An AI-powered equity research framework that transforms AI agents into institutional-grade analysts by enforcing rigorous valuation, forensic accounting, and industry-specific research protocols.