Projects sharing features with Minima

llama.cpp is a high-performance C++ inference engine and runtime for executing large language models locally across various hardware architectures. It provides the core components for local model execution, including a dedicated model quantizer for compressing weights into the GGUF format and a system for generating text embeddings for semantic search. The project distinguishes itself through specialized memory and execution optimizations, such as block-wise weight quantization to reduce memory footprints and memory-mapped model loading. It supports structured text generation by using formal

Llama.cpp is an inference engine designed for the local execution of text-based and multimodal language models on consumer hardware. It provides a core environment for running models that process both text and image inputs, utilizing hardware-accelerated backends to optimize performance across diverse CPU and GPU architectures. The project distinguishes itself by offering a lightweight HTTP server that adheres to standard API specifications, enabling chat completion, embeddings, and reranking services. It includes a suite of tools for model quantization and conversion, which reduces memory us

LangChain is an orchestration framework designed for building, managing, and deploying applications powered by large language models. It provides a unified integration layer that normalizes disparate model provider APIs into a consistent set of primitives, enabling developers to build complex, multi-step AI workflows that manage state, memory, and tool execution. The project distinguishes itself through a durable execution runtime that maintains persistent state across long-running processes by checkpointing progress to external storage. It models agent workflows as directed graphs, allowing

Memori is an AI agent memory middleware platform designed to provide persistent, context-aware recall for language models. It functions as a non-intrusive layer that intercepts outbound model requests to automatically capture interaction history and execution traces, ensuring that agents maintain continuity across sessions without requiring modifications to existing application logic. The platform distinguishes itself through a dual-model storage architecture that maintains information as both structured relational primitives for precise fact retrieval and rolling narrative summaries for situ

Agent-S is a multimodal AI agent and LLM desktop automation framework designed to control operating systems through graphical user interface interactions. It functions as a computer use interface, utilizing vision-language grounding to translate natural language goals into precise screen coordinates and system actions. The project differentiates itself by combining structured accessibility tree inspection with vision-based element localization. It manages cross-application workflows by mapping conceptual descriptions to physical pixels and simulating low-level keyboard and mouse events to mov

Aye Chat: AI-powered terminal workspace

FinRL is a financial reinforcement learning framework and quantitative trading library. It provides a specialized system for developing, training, and simulating autonomous agents designed to automate financial trading and portfolio management. The project serves as an automated portfolio optimizer and financial market simulator. It enables the creation of decision-making policies to balance asset allocations, maximize potential returns, and minimize financial risk through reinforcement learning. The framework includes capabilities for financial market data engineering, algorithmic trading s

Developer AI Persona Search Agent

AudioGPT is an LLM-driven audio framework and processing suite that uses large language models to orchestrate neural audio pipelines. It functions as a multimodal audio generator and processing system, integrating a collection of pretrained models to handle speech synthesis, sound generation, and audio manipulation. The system is distinguished by its ability to generate audio from diverse inputs, including text and images, and its capacity to produce synchronized talking head videos. It also operates as a neural speech translator, converting spoken language between different tongues while pre

Reinforcement learning resources curated

Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Cursor CLI, OpenCode, Kilo, Pi, Kimi

Xiaozhi-esp32 is an open-source firmware platform designed for building voice-interactive embedded systems on resource-constrained microcontrollers. It functions as an IoT conversational device platform that manages live audio input, speech synthesis, and conversational state transitions to facilitate real-time natural language interaction. The system distinguishes itself by bridging language models with physical hardware through standardized protocols, allowing for the execution of commands on local peripherals or remote smart home services. It utilizes a specialized architecture to coordina

An MCP server that installs other MCP servers for you

A list of awesome tools, ideas, prompt engineering tools, colabs, models, and helpers for the prompt designer playing with aiArt and image synthesis. Covers Dalle2, MidJourney, StableDiffusion, and open source tools.

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

AI agents in Go — Temporal for durable, crash-resilient execution or run in-process with zero setup. OpenAI, Anthropic, Gemini, tools, MCP, A2A, RAG, conversations, AG-UI, streaming, sub-agents & human-in-the-loop.

Goose is an autonomous coding assistant and extensible AI agent framework designed to automate software development workflows. It functions as an orchestration engine that can install, execute, and test code, as well as manage local files and shell commands. The platform is model-agnostic, providing a flexible interface to connect with diverse cloud-based or self-hosted large language model providers. It distinguishes itself through a standardized context protocol for integrating external tools and extensions, and a recipe system that allows users to define and repeat complex, multi-step AI w

ZSH plugin that integrates OpenCode AI with your shell

OpenCode is a framework for orchestrating autonomous AI agents within development environments. It provides a multi-tiered architecture where primary assistants manage user interaction while specialized subagents handle specific tasks like planning, research, and code generation. The system includes a comprehensive command-line interface for managing these workflows, configuring agent behavior, and defining custom tools or commands through metadata-rich files. The platform features a modular plugin system and extensive integration support, including standardized protocols for connecting local

alpaca.cpp is a high-performance local inference engine implemented in C++ for executing instruction-tuned large language models. It serves as a quantized model runtime designed to load and run model tensors on local hardware with minimal dependencies, removing the requirement for a full Python environment. The project focuses on on-device text generation and the deployment of private AI chatbots. It utilizes model weight quantization to reduce memory requirements and increase inference speed on consumer-grade devices. The system covers hardware-optimized model execution through thread-pool

OCR in Javascript via Emscripten

AppFlowy is a local-first knowledge base and collaborative workspace platform designed for structured information management. It functions as a modular productivity suite where users organize content through a block-based document model, allowing for flexible nesting and granular manipulation of data. The system prioritizes data sovereignty by enabling self-hosted storage, ensuring that sensitive information remains under user control while maintaining offline accessibility. The platform distinguishes itself through a decoupled architecture that separates its high-performance, memory-safe cor

DocsGPT is a retrieval-augmented generation platform and private knowledge base used to build AI agents that perform grounded search and analysis. It functions as a multi-model AI orchestrator and enterprise agent builder, allowing for the integration of various local and cloud language models to customize reasoning and text generation. The project provides a visual environment for developing automated assistants using conditional logic and third-party API connectivity. It enables the creation of private AI agents capable of performing enterprise search and detailed document analysis using pr

Zsh plugin that integrates Claude Code CLI into your shell. Chat with Claude and execute AI-generated commands directly from your terminal prompt

acl-release-shield: https://img.shields.io/badge/version-53.1.0-green acl-release: https://github.com/ARM-software/ComputeLibrary/releases/v53.1.0

Code and data associated with the AmbiEnt dataset in "We're Afraid Language Models Aren't Modeling Ambiguity" (Liu et al., 2023)