Self Hosted Ai

Self-hosted AI platform with chat UI, RAG, plugins, and multi-model support.

Self-hosted all-in-one AI app to chat with docs, use agents, and run locally with multi-user support.

Open-source AI engine to run LLMs, vision, voice, image, video on any hardware, no GPU required.

Privacy-first, self-hosted knowledge workspace with block-level editing, AI agents, and MCP support.

Self-hosted ChatGPT alternative with multi-model support, agents, MCP tools, and code interpreter.

Free open-source, privacy-first resume builder with 15 templates, PDF/DOCX export, and self-hosting.

Open-source ChatGPT clone with agents, MCP, multi-model support, and self-hosting.

Self-hosted AI answering engine with privacy, local LLM support, and cited sources.

Open-source AI spreadsheet platform with PostgreSQL, AI chat, app builder, and self-hosting.

Air-gapped, privacy-focused open-source NotebookLM alternative that turns local documents into briefings, decks, reports

Open-source, self-hosted CMS platform on AWS serverless with TypeScript framework, multi-tenancy, and AI-assisted develo

Hister is a private, self-hosted full-text search engine for your browsing history, bookmarks, and local files.

Lemonade is a free, private local AI server that runs optimized LLMs on your own GPU/NPU, compatible with OpenAI, Anthro

Local-first voice AI runtime with transcription, TTS, voice cloning, and OpenAI-compatible API.

Open-source educational platform with 30 historical figures, AI conversations, and self-hosted privacy.

Run, fine-tune, and monitor small language models on CPU without labeled data.

Open standard for portable, interoperable AI memory across tools, sessions, and devices.

Self-hosted Bun + Elysia reverse proxy unifying OpenAI and Anthropic APIs with real-time translation and prompt caching.

Portable offline AI assistant desktop app running GGUF models locally via llama.cpp.

Self-hosted AI security proxy that redacts PII, blocks prompt injection, and routes to any LLM provider.

Self-hosted mixed-vendor GPU inference cluster manager with speculative decoding proxy for faster LLM serving.

Run Hermes Agent and Claude Code locally on llama.cpp with zero API costs.

BiuMind is an all-in-one AI workspace integrating docs, agents, coding, and notes with a unified knowledge graph.

Turn any Mac or GPU into an OpenAI-compatible inference node. One-command setup, automatic HTTPS, model management, and

Self-hosted open-source emotional AI companion for private, personal relationships.

Self-hosted AI workspace for local & BYOK LLMs with agents, MCP tools, and deep research.

Self-hosted AI backend daemon with shared memory, 136 API endpoints, and multi-interface access.

Self-hosted AI governance, RAG and document intelligence with citations, audit evidence and PII privacy controls.

Your AI. Your machine. Always on. A personal assistant in one pure-Swift binary.

A self-hosted AI platform — inference, tool use, browser automation, image generation, speech synthesis, transcription,

Run IBM Granite 4.0 locally on Raspberry Pi 5 with Ollama.This is a privacy-first AI. Your data never leaves your device

Self-hosted AI workspace with agents, skills, and tools (Gmail, Calendar) that runs entirely on your own provider API ke

Open-source local AI workspace for chat, agents, coding, RAG and fine-tuning on your own machines.

Self-hosted AI companion with daily life simulation, long-term memory, and consistent-identity selfies.