{"name":"AgentAleph: Local-First AI Coding Agent and GGUF Model Manager","description":"AgentAleph is a desktop application that combines a local-first AI coding agent with a GGUF model manager. It allows users to download, load, and manage local large language models, and then use an AI agent to interact with their projects, all without relying on cloud services or API keys. This tool emphasizes privacy and offline capability, running models directly on your machine.","github":"https://github.com/matiasA/AgentAleph","url":"https://osrepos.com/repo/matiasa-agentaleph","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/matiasa-agentaleph","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/matiasa-agentaleph.md","json":"https://osrepos.com/repo/matiasa-agentaleph.json","topics":["AI Agent","Coding Agent","Local LLM","GGUF Models","Rust","Tauri App","Offline AI","Privacy"],"keywords":["AI Agent","Coding Agent","Local LLM","GGUF Models","Rust","Tauri App","Offline AI","Privacy"],"stars":null,"summary":"AgentAleph is a desktop application that combines a local-first AI coding agent with a GGUF model manager. It allows users to download, load, and manage local large language models, and then use an AI agent to interact with their projects, all without relying on cloud services or API keys. This tool emphasizes privacy and offline capability, running models directly on your machine.","content":"## Introduction\n\nAgentAleph is a powerful local-first AI coding agent and GGUF model manager, built with Rust and powered by `llama.cpp`. This desktop application offers a complete solution for developers who want to leverage AI without relying on cloud services, API keys, or external accounts. It integrates both a robust local model manager, inspired by tools like LM Studio, and a sophisticated coding agent, taking cues from Codex and Claude Code.\n\n## Why Use and Key Features\n\nAgentAleph stands out for its commitment to privacy, local execution, and comprehensive functionality.\n\n*   **Local Inference:** All prompts are processed by your local model, ensuring privacy. While web searches and fetches use the network, approved shell commands can also access it, always with user control.\n*   **An Agent, Not Just a Chat Box:** Beyond simple chat, AgentAleph can read, search, edit, and create files, as well as run shell commands, all with your explicit approval.\n*   **Simple by Design:** The application features a streamlined, single-window interface for downloading, loading models, and working, eliminating the need for hosted endpoints or complex server setups.\n*   **Safe by Default:** It incorporates per-tool `allow`, `ask`, or `deny` permissions and a read-only **plan mode** that prevents project edits and shell commands, giving you full control.\n*   **Built for Imperfect Local Models:** The agent includes features like GBNF grammar-constrained tool calls, native tool calling, loop detection, and context compaction to optimize performance with various local models.\n*   **Extensible with Skills:** You can easily add task-specific local instruction packs, known as \"Skills,\" without modifying the core code.\n*   **Comprehensive Model Management:** Browse a curated catalog of GGUF models from Hugging Face, download them with resumable transfers, and manage them locally. The app provides hardware fit badges to estimate performance on your system.\n*   **Flexible Inference Settings:** Fine-tune model behavior with configurable settings for system prompt, temperature, context size, GPU layers, and more.\n*   **Edit Previews and Undo:** Review proposed file changes before approval and undo the latest file edits, providing a safety net for your work.\n\n## Installation\n\nAgentAleph is primarily designed for **Linux x64** (Ubuntu/Debian with `webkit2gtk-4.1`, `gtk-3`). It requires **Rust 1.77+** and **Node 18+**.\n\nTo get started, follow these steps:\n\nbash\ngit clone https://github.com/matiasA/AgentAleph.git\ncd AgentAleph\nnpm install\n./scripts/setup-llama.sh   # downloads the llama.cpp binary; it is not committed because of its size\nnpm run tauri dev          # development with hot reload\n# or\nnpm run tauri build        # production build (.deb / .AppImage)\n\n\nFor CPU-only operation, you can specify the `LLAMA_FLAVOR`:\n\nbash\nLLAMA_FLAVOR=x64 ./scripts/setup-llama.sh\n\n\nThe project also supports building installers via GitHub Actions. You can trigger a build manually or by pushing a version tag:\n\nbash\ngit tag v0.1.0 && git push origin v0.1.0   # triggers build + Release\n\n\n## Examples\n\nGetting started with AgentAleph is straightforward:\n\n1.  **Download** a model from the Catalog tab, typically a Q4_K_M variant by default.\n2.  **Load** it from the Models tab and await the progress indicator.\n3.  **Choose a mode**: Select \"Chat\" for general conversation or \"Agent\" for project-specific work.\n4.  **Work with the agent**: If in Agent mode, select a project folder, describe your task, and then approve or deny any write or execute actions as prompted by the agent.\n\n## Links\n\n*   **GitHub Repository:** [AgentAleph GitHub Repository](https://github.com/matiasA/AgentAleph){target=\"_blank\"}\n*   **License:** [MIT License](https://github.com/matiasA/AgentAleph/blob/main/LICENSE){target=\"_blank\"}","metrics":{"detailViews":0,"githubClicks":0},"dates":{"published":null,"modified":"2026-09-25T15:11:09.000Z"}}