local-ai-agent

Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp.

Lightweight local bridge for running an mlx-lm model behind an OpenAI-compatible API and exposing it through a LiteLLM proxy.

Portable desktop AI agent in a single .exe. LangGraph + MCP: files, shell, web search, processes. Safe by design — human-in-the-loop approvals for critical actions. Self-correcting, auto-retry, API-key rotation. Multimodal & multi-model (OpenAI-compatible, Anthropic, Gemini). No Docker, no installers — copy and run.

A local AI-powered OS assistant for Windows that organizes files, monitors system pressure, suggests cleanup actions, and stays privacy-friendly by running with local tooling such as Ollama.

A Factorio 2.0 mod that spawns an autonomous AI character in your game. The AI perceives the factory, decides what to do, and acts — building, mining, smelting, researching, and responding to chat — all driven by an LLM of your choice.

An intelligent local AI agent powered by open-source LLMs, featuring free web search, hybrid memory, and context-aware query rewriting for real-time, grounded answers.

An AI-powered command-line interface that bridges natural language and shell execution.

Run DeepSeek Harness locally on Android phones and tablets. One APK with Debian, Node.js, DSH, and WebView — no root or Termux required. 在安卓手机和平板上本机运行完整 DSH。

tripleF (3F) monorepo — an agentic, open-source AI workbench: conversation harness + dashboard, local-first via Ollama or Ollama Cloud.

Local AI Assistant working with Ollama and Python | Локальный ИИ Ассистент, работающий на Ollama и Python

CLI based Local Coding Agent Written in Python

A local AI assistant built with Python, Qwen3:8B, Ollama, RAG, persistent memory, and tool calling.

A privacy-first, high-performance semantic file search engine for Windows. Combines local ONNX embeddings, LanceDB vector search, BM25 lexical search, and NTFS indexing to deliver fast natural-language search entirely offline. Built with C# WinUI 3, Python, gRPC, and native Windows APIs.

Description: All-in-one Windows desktop AI toolkit. Local model management, prompt library, batch processing, image generation helpers, text tools and productivity utilities. Clean interface, lightweight and regularly updated for creators and developers.

Local-first AI assistant for files, reminders, and document generation

The intelligent command-line interface directly powering the Toolpack SDK

Run local LLMs on limited VRAM safely. Dynamic model sharing and OpenAI API drop-in replacement.

🤖Local AI agent in charge with your finance, health, documents and household.

OpenMindAI is an open-source, local-first AI desktop assistant with offline chat, GPU acceleration, persistent local memory, portable deployment, and no paid AI API required

An evidence-based journey of experimenting with Hermes Agent, multi-provider LLM routing, Telegram and WhatsApp gateways, MCP Trello, voice workflows, and approval-based coding automation.