AI chatbots & assistants — page 2186 resources

Free, open-source Windows desktop toolbox for local file search, document previews, OCR batch renaming, and an optional AI assistant.

C

Local AI engine in Rust: run GGUF and ONNX models for chat, vision, speech and embeddings on your own GPU, RAM and CPU, with automatic placement and OpenAI-compatible APIs.

G

🐧 A native GNOME knowledge workstation that turns documents into evolving AI-assisted knowledge bases.

Pure-Go, no-cgo local LLM inference — run Gemma, Qwen, Llama and friends from safetensors or GGUF in a single static binary.

Secure, local, offline database for Garmin Connect health data. Windows desktop app, no setup needed. Built for long-term local analysis, dashboards, local AI and MCP-Server.

AL

An AI tool with a limited free plan, listed under “AI chatbots & assistants”, available on the web.

A

Set one RAM ceiling. Run bigger sparse language and vision models on Apple Silicon — experts stream from SSD when they don't fit, without hidden quantization.

A free and open source software, listed under “AI chatbots & assistants”, available on Windows.

H

Use Home Assistant from Claude, ChatGPT, Codex, and other AI apps, safely. Each device pairs on its own, and risky changes wait for your OK.

V

Free, local-first, on-device dictation for macOS (Apple Silicon). Hold a key, speak, and Velora types polished text in any app — with agentic actions and fully offline. Superwhisper/Wispr Flow alternative.

Open-source Windows AI IDE built with .NET 10 WPF, featuring a fine-tuned local AI router (1.5B), live Blender & Unity copilots, self-healing agent loops, and multi-tool execution.

An open-source, offline-capable agentic IoT runtime with physical actuation trust. Ori gives physical devices the brain to reason about sensor data via tiered LLM reasoning + graduated authority model for safe…

W

Whisper+ is a speech-to-text mobile app, available on Android: offline use, voice input and commands.

T

Your proactive AI assistant: reads your email, chats, calendar and phone, turns what matters into to-dos, prepares the work, and only sends what you approve. Open source, self-hosted or hosted.

C

Local-first AI filmmaking workbench on ComfyUI: consistent characters across every still and clip, plan a Day or a Story, talking clips with kept voices, and a real editor to cut, subtitle and finish the film.

Chatgpt like GTK Linux Client for AI large language models.

Find what open-weight Large Language Model (LLM) can fit into your hardware and run it.

DeepSeek is an AI chat assistant, available on the web: open-weight models (Llama, Mistral…).

K

Open-source multi-cluster Kubernetes console with an AI assistant that works within each user's permissions. Alert investigation, secret masking, audit log, MCP server, one-line Helm install.

P

Your prompt vocabulary, one hotkey away, in every window.

A local-first app that turns your documents into a personal knowledge base you can read, search, and actually retain — with the LLM running on your own machine.

KDE Plasma 6 widget for local AI provider usage, spend, limits, and coding-tool activity.

Your portable AI memory — preferences, decisions, and corrections that follow you across models, tools, and devices. Zero-dependency, local-first, 85% PrefEval accuracy.

Free, open-source AI assistant for macOS. Talk about your screen, get spoken step-by-step guidance and visual answers, and delegate tasks to specialist mates.

Chain-of-agents system to develop software.

Playwright-style MCP server for PySide6 apps — lets Agents see, control, and debug your Python desktop GUI.

An open-source, on-device AI assistant for Android. Chat with GPT, Claude, Gemini or your own local models, keep long-term memory on your phone, and let the AI use real tools. No account, no tracking, no telemetry.

E

One binary to rule them all: model-agnostic local LLM inference for AMD Strix Halo (Ryzen AI MAX+ 395) on Linux. Radeon 8060S iGPU (gfx1151) via HRX + our HIP kernels, XDNA 2 NPU via our NPU runtime, inside Lemonade…

M

Local-first AI assistant with real memory, agent tool use, and proactive habits — built with Go + Flutter. Runs fully offline via llama.cpp, recalls context across sessions with local RAG, edits files/runs commands as…

Free, open-source AI lecture recorder and note-taker for students on Mac and Windows. Records and transcribes lectures on your computer (Whisper, Parakeet) and writes study notes with diagrams using Claude, ChatGPT,…

People and AI agents write living documents together. Native for macOS and Windows, and on the App Store for iPhone and iPad; offline-first, syncing through iCloud Drive or Supabase, and open to agents over MCP.

Record your screen while you talk. Transcribed on your Mac with whisper.cpp. Readable by AI agents over MCP.

Self-hosted, privacy-first AI home companion with voice, touch and long-term memory.

Emergency SOC/NOC gateway for Raspberry Pi — deterministic triage + local AI assist (Ollama).

FileCollector - A modern file collection utility featuring project management and phrase organization. It is ideal for quickly consolidating key code snippets or documents from a project into a single TXT file for…

Nova is a private, proactive AI assistant for Home Assistant with local and cloud LLM support.

Cross-platform security reconnaissance for Windows and Kali/Linux, with 12 scanner adapters, optional local AI, and HTML/PDF/JSON/SARIF reports.

Free and open source software for macOS, listed under “AI chatbots & assistants”.

Offline-first fiction writing environment. Import a novel, let a local model read it into a story bible, then ask "What if...?": branch the book, rewrite the chapters the change reaches, and check every later scene for…

CodeRag RAG stack: PDFs→Docling→Ollama→pgvector. Windows/macOS/Linux. Docker Compose. Graph-aware code search + scanned PDF OCR.

An MCP server for managing kids' sports activities on Spond. Built for parents who want to give AI assistants access to upcoming matches, training schedules, and attendance — so you can ask "what's on this week?" or…

C

Cognate is a local-first, privacy-focused day planner. It auto-schedules tasks as time blocks, re-flows on disruption, syncs E2E encrypted via CRDTs, and runs AI locally. Your data never leaves your device.

Local-first AI chat, roleplay, and fanfic app for desktop, Raspberry Pi, or your own server, with any model. Unofficial fork of Marinara Engine.

O

Free, open-source live captions for people who are deaf or hard of hearing, on iPhone, iPad and Android. Runs on the phone, in Hebrew, English and 10 more languages.

A

WebView wrapper for Mistral Le Chat with URL blocking and privacy features.

IE

Euria, your sovereign AI assistant that respects your privacy and the planet.

R

AI roleplay chat and story writing client.

A

🐱 Self-hosted RAG chatbot that researches company documents and cites every claim. Hybrid search (FAISS + BM25, RRF, OpenVINO rerank), a ReAct agent that creates and edits Word, Excel, PowerPoint and PDF files in chat,…