Open-source alternatives to TabNine

This project is an on-device AI SDK providing a framework for running large language models, vision models, and speech models locally. It serves as an orchestration layer for local LLM execution, ensuring data privacy and offline availability by utilizing hardware acceleration on the device. The SDK is distinguished by its comprehensive voice and multimodal capabilities, including a coordinated voice pipeline for activity detection, speech-to-text, and text-to-speech synthesis. It also provides a dedicated implementation kit for local retrieval-augmented generation and tools for processing co

MNN is a high-performance inference engine and framework designed for on-device machine learning. It provides a comprehensive environment for executing, optimizing, and deploying neural network models directly on mobile and resource-constrained edge devices. The framework distinguishes itself through a robust model optimization toolkit that supports quantization, compression, and structural graph manipulation to minimize memory footprint and maximize execution speed. It features a modular architecture that abstracts hardware-specific backends, allowing models to run efficiently across diverse

ExecuTorch is a lightweight C++ runtime for deploying PyTorch models on mobile, embedded, and edge hardware. It provides an ahead-of-time compilation pipeline that exports, quantizes, and lowers model graphs into compact serialized programs, then executes them through a minimal runtime with hardware acceleration and on-device large language model inference capabilities. The project distinguishes itself through a hardware accelerator delegate system that partitions model subgraphs and offloads computation to specialized backends including NPUs, GPUs, and DSPs from Apple, Arm, Intel, MediaTek,

Tern is an editor-independent code analyzer and static analysis engine for JavaScript. It functions as a language server that provides semantic intelligence by parsing source code into abstract syntax trees to infer types and resolve symbols without requiring manual type annotations. The engine distinguishes itself through the use of JSON-based type definitions, which allow it to describe library signatures and external dependencies without needing the original source code. It also features a plugin system that enables the extension of server functionality to support custom loaders or framewo

This is a Visual Studio Code extension that provides framework-specific IntelliSense for Laravel projects. It acts as a project metadata provider, scanning PHP files and extracting application state to offer intelligent autocomplete for routes, views, configuration keys, and model attributes. The tool includes a specialized suggestion engine for Blade templates, providing autocomplete for directives, sections, and stacks. It supports containerized development by routing commands through virtual environments or custom paths to ensure metadata is accurately extracted from isolated project direc

RLS is a language server that provides language intelligence for the Rust programming language. It implements the Language Server Protocol to enable a standardized communication layer between the Rust compiler and various editor clients. The project focuses on providing real-time code completions, symbol navigation, and type information. It also supports automated structural changes, such as workspace-wide symbol renaming, to maintain semantic correctness during refactoring. The system incorporates static code analysis for linting and formatting, alongside a mechanism for incremental compila

PocketPal AI is an on-device LLM chat application for Android that runs small language models locally, enabling private AI conversations without requiring an internet connection. It functions as an offline inference engine that downloads and executes quantized language models directly on the device, with adjustable parameters like temperature and chat templates to control how the AI behaves. The application lets users create custom AI personalities by configuring unique system prompts and contextual settings for different conversational roles. It integrates with the Hugging Face Hub to downlo

gocode is a language server backend and autocompletion daemon for the Go language. It functions as a static code analyzer and symbol indexer that provides real-time identifier and symbol suggestions to text editors. The project utilizes a client-server daemon architecture to maintain a persistent background process, avoiding the overhead of reloading package metadata for every request. It employs a two-tier metadata caching system and parses compiled package binaries to enable fast symbol lookups and declaration retrieval. The system covers broad capability areas including context-sensitive

windsurf.vim is an AI-driven development tool for Vim and Neovim that integrates AI-powered code completion, a conversational coding assistant, and autonomous agent orchestration. It enables users to receive real-time code suggestions and perform complex refactoring via natural language instructions directly within the editor. The project provides a system for dispatching and monitoring multiple AI agents to execute engineering tasks across local and cloud environments. It includes context-aware project analysis by indexing the local codebase and supports shared workspace management to mainta

Ente is a privacy-focused platform for end-to-end encrypted storage and two-factor authentication management. It functions as a zero-knowledge identity provider, ensuring that all cryptographic operations, key derivation, and data encryption occur locally on the user's device. By maintaining this architecture, the service provider remains unable to access or decrypt any stored personal information or authentication credentials. The platform distinguishes itself through a combination of on-device intelligence and resilient data distribution. It utilizes a local machine learning engine to perfo

TabNine is an AI programming assistant and large language model completion tool that predicts and completes source code in real time. It functions as a language-aware code predictor, providing automated line completions and code snippets based on the context of the current file and project. The system utilizes custom language mapping and programming language tokenization to ensure suggestions remain syntax-accurate across various file extensions. By defining how source code is broken into symbols and identifiers, the tool maintains consistent suggestions across a project's different file type

This project is a comprehensive productivity guide and configuration reference for the VS Code editor. It provides a curated collection of shortcuts, configuration tips, and tutorials designed to improve efficiency and optimize the daily coding workflow. The resource covers advanced AI-assisted development, including the integration of autonomous agents, custom prompt files, and AI-powered coding assistants for task automation and code generation. It also provides specialized guidance on integrated terminal management, such as configuring shell profiles and automating command execution. Addi

This project is a cross-platform machine learning inference engine designed to execute pre-trained models across diverse operating systems and hardware environments. It functions as a standardized execution framework that manages the entire lifecycle of model inference, from loading and graph optimization to hardware-accelerated execution and generative sequence management. The runtime distinguishes itself through a highly modular architecture that decouples model logic from hardware-specific kernels. By utilizing an execution provider abstraction, it enables developers to offload computation

Tempest is an orchestration platform designed for the execution and management of autonomous coding agents. It provides a framework for running multiple agents in parallel, coordinating their workflows, and maintaining persistent session states through a centralized management interface. The platform distinguishes itself through its focus on secure, isolated execution and intelligent context management. Each agent operates within a dedicated sandbox, utilizing ephemeral file systems and database copies to perform tasks without impacting production environments. To optimize performance and red

Universal Ctags is a multi-language symbol indexer and regex-based parsing engine used to extract and catalog functions, classes, and variables from source code. It functions as a source code indexer that scans files across diverse programming languages to create searchable catalogs of definitions and declarations. The project is distinguished by its extensible parser framework, which allows users to define new language rules using regular expressions and configuration files. It supports complex parsing scenarios through state-based parsing, stack-oriented scope tracking, and guest-parser del

This repository contains the comprehensive documentation for a code editor focused on AI-assisted software development and remote development workflows. It covers the implementation of AI agents and language models used for autonomous code generation, large-scale refactoring, and task iteration. The project is distinguished by its deep integration of autonomous AI agents capable of web navigation, application logic validation, and orchestrating multi-step development processes. It provides specialized frameworks for tailoring AI behavior through custom instructions, model context protocols, a

coq_nvim is an asynchronous code completion engine for Neovim. It aggregates suggestions from multiple sources, including language servers, tag files, and local buffers, to provide non-blocking code completion. The engine distinguishes itself through a typo-resistant fuzzy completion filter and a two-stage weighted ranking system that prioritizes candidates based on recency and proximity. It utilizes an embedded SQLite database for local caching and background symbol indexing to accelerate lookups without freezing the editor interface. The project also includes a system for defining and expa

copilot.lua is a Lua-based Neovim plugin that integrates GitHub Copilot to provide an AI code completion engine. It delivers real-time ghost text and inline suggestions within the editor, utilizing a Neovim LSP client to manage communication and buffer-specific activations. The project handles GitHub account integration through token-based authentication and corporate instance support. It allows for the management of AI models and the configuration of language server protocols to authorize and customize service access. The system covers AI coding assistance through predictive edit suggestion

Positron is a data science integrated development environment and AI-powered code editor designed for polyglot development, specifically supporting Python and R. It functions as a remote compute workspace that separates the user interface from the execution kernel via SSH or container integration. The environment features a deep integration of large language models that provide context-aware suggestions and automated data analysis by accessing real-time interpreter state, in-memory objects, and plot outputs. It distinguishes itself through a polyglot runtime bridge that enables cross-language

MiniCPM-V is a multimodal large language model and vision-language system designed for complex visual and linguistic understanding. It functions as an on-device AI model, providing the capacity to process text, images, and video as a compact neural network. The project is specifically developed as an edge AI framework, utilizing quantization and weight sharding to run on memory-constrained mobile chipsets. This allows for the deployment of multimodal intelligence directly on mobile operating systems for local inference. Its capabilities cover multimodal content analysis of high-resolution im

Turbopilot is a local large language model inference server designed to provide private code completions. It functions as a self-hosted engine that executes models on local hardware, ensuring development workflows remain offline and source code does not leave the machine. The system includes a quantization tool and model manager used to compress weights and merge sharded data into a unified binary format. This optimization reduces memory footprints and accelerates loading for execution on consumer-grade hardware. Performance is managed through a GPU accelerated inference engine that offloads

CopilotForXcode is an AI source editor extension for the Xcode development environment. It provides a suite of tools including a conversational chat interface, a code completion tool, and a natural language refactorer to assist with Apple platform development. The project differentiates itself by integrating project context and compiler errors directly into its AI interactions. It supports custom prompt execution using template variables and enables the triggering of shell scripts and system shortcuts directly from the chat interface to automate development tasks. The system manages AI integ

ChatGPT.nvim is an OpenAI LLM Neovim plugin that serves as an AI-powered code assistant for refactoring, completing, and fixing code snippets. It functions as a custom prompt automation tool and a markdown renderer, allowing users to interact with language models directly within the editor. The project distinguishes itself through a framework for defining reusable AI personas and automated text processing tasks using system prompts and templates. It includes a specialized rendering system that transforms responses into styled markdown with foldable code blocks. The plugin covers interactive

This project is a vision language model framework and vision-to-text pipeline designed for deploying and optimizing models that process both images and text. It provides an on-device inference engine and a vision language model framework to run quantized models locally on mobile and desktop hardware accelerators. The framework features a model quantization toolkit to reduce weight precision for lower memory footprints and increased execution speed on specialized silicon. It also includes an efficient vision encoder utilizing a hybrid encoding system to compress image tokens, which reduces pro

jscamp is a full-stack web development and education project focused on mastering JavaScript, TypeScript, and AI integration. It provides a structured curriculum and interactive exercises covering language fundamentals, frontend engineering, and backend API development. The project distinguishes itself through the implementation of autonomous AI agents capable of complex task automation, such as modifying files, managing servers, and executing API calls. It includes advanced AI development tools for conversational querying, real-time code suggestions, and automated repository analysis to gene

This project is a Lua-based completion engine for Neovim that aggregates real-time text suggestions from multiple data sources into a single interface. It functions as a modular framework for extending the editor with custom completion logic, acting as both a fuzzy text suggestion tool and an interface for the Language Server Protocol. The engine utilizes a source-agnostic provider interface to standardize how disparate data sources feed candidates into a central logic engine. It employs asynchronous candidate fetching and a non-blocking architecture to retrieve suggestions from external serv

LiteRT is a runtime and API for executing machine learning and generative AI models on mobile, desktop, and IoT hardware. It consists of an inference engine and a specialized environment for running quantized large language and diffusion models locally on edge hardware. The system includes an ahead-of-time model compiler that translates models into hardware-specific bytecode to reduce startup latency and memory overhead. It provides a unified interface for Neural Processing Units with automatic fallback routing to CPUs or GPUs when specific subgraph support is unavailable. An edge model conve