Reading
TerminusAI is an open-source AI assistant designed for Termux, enabling Android users to directly use large language models in a terminal environment, supporting over 25 functions such as code execution, web search, and file management.
Section 01
TerminusAI is an open-source AI assistant designed for Termux, enabling Android users to directly use large language models in a terminal environment, supporting over 25 functions such as code execution, web search, and file management.
Section 02
With the rapid advancement of Large Language Model (LLM) capabilities, more and more developers and users hope to access these powerful AI capabilities conveniently on mobile devices. However, on the Android platform, most LLM applications are closed commercial products—users neither have control over their own data nor can they easily perform deep customization.
The emergence of TerminusAI fills this gap. As an open-source AI assistant specifically designed for Termux, it brings the powerful capabilities of large language models to the Android terminal environment, allowing users to enjoy an AI experience comparable to that on desktop devices right on their phones.
Section 03
TerminusAI is a feature-rich terminal AI assistant optimized specifically for the Termux environment. Termux is a powerful Android terminal emulator and Linux environment app, favored by developers and advanced users. Building on this, TerminusAI provides users with the ability to interact directly with large language models.
Section 04
TerminusAI offers more than 25 commands covering the following functional areas:
In addition to core functions, TerminusAI also provides a rich set of auxiliary commands:
Section 05
One of the technical challenges of TerminusAI lies in adapting to the special environment of Termux:
Through a carefully designed architecture, the project provides a smooth user experience under these constraints.
Section 06
TerminusAI supports multiple LLM access ways:
This flexibility allows users to choose the most suitable solution based on their needs and resources.
Section 07
As an open-source project, TerminusAI has the following advantages:
Section 08
For developers who need to work on the go, TerminusAI provides strong support:
Keep going with more reads from the same topic.
Splinter is a minimalist, high-performance key-value (KV) and vector storage system enabling zero-latency inter-process communication via shared memory and atomic operations. With only 766 lines of core code, it supports millions of operations per second and 768-dimensional vector storage, offering a new architectural approach for local LLM inference and data-intensive applications.
Folkering OS is the world's first AI-native bare-metal operating system, entirely written in Rust no_std without relying on Linux, POSIX, or libc. It can generate commands from scratch, compile them into WASM, and run them in 10 seconds, achieving true self-evolution.
This project explores how to use Large Language Models (LLMs) to detect logical vulnerabilities in Ethereum smart contracts, especially business logic flaws that are difficult for traditional static analysis tools to capture, such as economic manipulation and execution order errors.
This article introduces an open-source project for building modern large language models from scratch. The project evolves from a GPT-2-style basic architecture to a Llama 2/3-style production-level implementation, covering complete tutorial implementations of key technologies such as RMSNorm, RoPE, SwiGLU, GQA, and MoE.