A privacy-first, self-hosted AI assistant platform featuring autonomous agents, 250+ tools, and integrations for IoT, browser automation, and messaging apps.

A CLI tool that integrates BMAD-METHOD planning and Ralph autonomous implementation to move AI-assisted projects from initial analysis to autonomous TDD coding.

An AI-powered code review tool that uses DeepSeek models to automate PR reviews via GitHub Actions or local CLI audits.

A Model Context Protocol (MCP) server that provides AI models with 69 precise browser automation tools for navigating, interacting with, and extracting data from the web.

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 state-native inference hypervisor for linear and hybrid-linear models that replaces paged KV caches with fixed-size state slots for efficient session management.

A native Rust toolkit for activation steering and LoRA fine-tuning of open-weight Llama models to control model behavior and traits.

A Vim plugin that brings Copilot-like AI code completion, chat, and tool-based editing to Vim using Ollama for local LLM execution and privacy.

An npm‑published Node library that adds LLM‑driven assistants to Kubernetes/DevOps workflows. It provides a CLI and a managed platform (MCP) for natural‑language cluster queries, deployment recommendations, automated remediation, policy‑driven prompt libraries, and semantic doc search, all packaged for easy installation on a Kubernetes cluster.

A visual deep multi-agent reasoning engine for Gemini and OpenAI-compatible models that decomposes complex queries into parallel expert tasks with a transparent reasoning workflow.

Aligator is a C++/Python library for fast, constrained trajectory optimization in robotics. It offers a modelling API, efficient solvers (ProxDDP, FeasibleDDP), Pinocchio integration, optional Crocoddyl compatibility, and parallel CPU optimisations. Install via conda or build from source (CMake/Pixi). Use it to generate motion plans or run model‑predictive control on complex robots.

Mulch is a CLI‑driven, git‑backed knowledge base that lets AI agents record structured learnings (conventions, failures, decisions, etc.) in per‑domain JSONL files and later retrieve context‑optimized excerpts for prompt injection. It supports custom record types, evidence‑based scoping, health‑checks, and pruning, enabling teams to accumulate and share expertise across agent sessions.

AgentKit is an open‑source SDK that provides a catalog of 70 ready‑made “kits” (full apps, pipelines, or templates) for building, testing and deploying AI agents. Kits are defined by a simple config file, can be edited in a visual flow studio, and are shipped as Next.js apps that run server‑less. The collection covers support triage, code review, RAG chat, hiring assistants, legal/medical bots, and many other business‑focused agents, making it a turnkey platform for creating reliable, enterprise‑grade AI agents.

A PyTorch implementation of 1-bit Transformers that replaces standard linear layers with binarized projections to drastically reduce LLM memory and compute requirements.

MMF is a modular PyTorch-based framework for vision and language multimodal research, providing reference implementations of state-of-the-art models and tools for distributed training.

A mobile GUI agent framework for Android that enables AI agents to perceive and operate app interfaces on real devices for automated, long-running workflows.

Kaldi‑Active‑Grammar is a Python wrapper for the Kaldi speech‑recognition engine that lets you compile many small grammars and activate only the needed ones per utterance. It ships binary wheels for all major OSes, includes a pre‑trained English model, and provides a backend for the Dragonfly and Caster voice‑control frameworks. Install via pip, download the model, define rules, and dynamically enable them for context‑aware command‑and‑control.

wav2letter++ is an end-to-end automatic speech recognition framework that provides recipes and pre-trained models to implement state-of-the-art speech-to-text architectures.

A local-first voice AI platform providing a desktop app, CLI, and server for speech-to-text, text-to-speech, and chat workflows without requiring cloud APIs.

The official Node.js SDK for ElevenLabs, enabling developers to integrate lifelike AI voice synthesis, real-time audio streaming, and voice-powered AI agents into their applications.

An MCP server that connects AI assistants to the Gemini/Antigravity CLI, enabling large-scale codebase analysis and sandboxed code execution.

Bindu is an open‑source framework that turns any LLM‑based agent into a secure, identity‑verified, payment‑enabled internet service. It provides built‑in mTLS, DID signatures, OAuth2 via Hydra, USDC (x402) payment enforcement, skill advertising, push notifications, and polyglot SDKs (Python, TypeScript, Kotlin). With a single `bindufy()` call you get a JSON‑RPC endpoint, optional public tunneling, and deployment helpers, making it easy to build swarms, paid APIs, or regulated B2B agent integrations.

A free online image annotation tool for generating computer vision ML training data with support for automated bounding box generation and dataset format conversion.

An AI-powered RSS reader that aggregates multiple feeds and uses LLMs to automatically generate article summaries for a lightweight, static reading experience.

Crabwalk is a real‑time web UI that visualises OpenClaw AI agents’ activity across WhatsApp, Telegram, Discord and Slack. It streams events from the OpenClaw gateway via WebSocket, shows a live node‑graph of sessions, lets you inspect tool calls, and supports Docker, CLI, or source‑install deployment.

An OpenAI-compatible serverless worker for RunPod that enables fast LLM deployment using the vLLM inference engine.

A local-first RAG system that enables users to upload local documents and chat with them using Ollama or OpenAI-compatible models.

A system for generating high-quality 3D objects from a single 2D image by combining 2D and 3D diffusion priors in a coarse-to-fine pipeline.

A lightweight and efficient TypeScript text chunking library designed for RAG applications, offering multiple strategies including semantic, recursive, and code-aware splitting.

A unified AI model gateway and agent coordinator that simplifies provider management, request routing, and remote control of AI agents.

A PyTorch-based library for multimodal and transfer learning that provides a standardized, pipeline-based API to create sustainable and reusable AI workflows.

A procedural memory system for AI coding agents that transforms scattered session logs into a persistent, cross-agent knowledge base of rules and anti-patterns.

AgileRL is a Python library for deep reinforcement learning that adds *RLOps*: evolutionary hyper‑parameter optimisation, distributed training, and a cloud platform (Arena) for running experiments at scale. It ships many algorithms (PPO, DQN, TD3, MADDPG, bandits, LLM fine‑tuning, etc.) and lets you train a single agent or a population that evolves its hyper‑parameters automatically, promising up to 10× faster HPO than traditional methods.

A drop-in prompt compression library that reduces LLM input-token costs by 10-40% using loss-tolerance routing to protect critical code and tool calls while compressing prose.

A fast, local GGUF inference engine written in Zig that provides a command-line interface, browser chat, and OpenAI-compatible API for consumer GPUs.

Orthrus is a dual-architecture framework that enables high-speed parallel token generation for LLMs while maintaining the exact generation fidelity of the original base model.

A token compression engine for LLMs that uses a 14-stage fusion pipeline to reduce prompt size by 15-82% without requiring LLM inference.

An AI Agent application development framework that provides a concise, Pythonic SDK to build agents with planning, tool-use, and broad LLM compatibility.

ReCode is an LLM agent framework that uses recursive code generation to unify high-level planning and low-level action, enabling dynamic granularity control for complex tasks.

An ultra-lightweight, anchor-free real-time object detection algorithm optimized for high-speed inference on ARM CPUs and embedded devices.

Mish is a self-regularized non-monotonic activation function that creates smoother loss landscapes to improve accuracy and optimization in deep neural networks.

A Streamlit component for handling and-transmitting real-time video and audio streams, enabling live media processing and AI integration in web apps.

A GenAI configuration framework that uses Jsonnet to manage prompts and chains as declarative configuration, enabling versioning and automatic hardware parallelism via WebAssembly.

A unified codebase and framework for advanced world models, integrating various open-source research for video generation, 3D scene generation, and visual-action reasoning.

A config-based CLI tool for launching and managing LLM fine-tuning experiments, allowing users to run ablation studies across different models, prompts, and optimization techniques.

A no-code GUI and framework for fine-tuning large language models, enabling users to experiment with hyperparameters and advanced training techniques without coding.

A Python package that adapts the Segment Anything Model (SAM) for geospatial data, enabling easy segmentation of satellite imagery using text, points, or boxes.

A no-code tool for training and deploying machine learning models, supporting a wide range of tasks from LLM fine-tuning to image classification.