Self-hosted projects tagged “LLM”
31 open source projects with this tag
31 services found
Ollama
Run and manage large language models locally with an API
Ollama is a local LLM runtime that lets you pull, run, and customize models, offering a CLI and REST API for chat, generation, and embeddings.
Open WebUI
Extensible, offline-capable web interface for LLM interactions
Feature-rich, self-hosted AI interface that integrates Ollama and OpenAI-compatible APIs, offers RAG, vector DB support, image tools, RBAC and observability.
AnythingLLM
All-in-one AI chat app with RAG, agents, and multi-model support
AnythingLLM is an all-in-one desktop and Docker app for chatting with documents using RAG, running AI agents, and connecting to local or hosted LLMs and vector databases.
LocalAI
OpenAI-compatible local AI inference server and API
Run LLMs, image, and audio models locally with an OpenAI-compatible API, optional GPU acceleration, and a built-in web UI for managing and testing models.
LibreChat
Self-hosted multi-provider AI chat UI with agents and tools
LibreChat is a self-hosted AI chat platform that supports multiple LLM providers, custom endpoints, agents/tools, file and image chat, conversation search, and presets.
Khoj
Open-source personal AI for chat, semantic search and agents
Self-hostable personal AI 'second brain' for chat, semantic search, custom agents, automations and integration with local or cloud LLMs.
Perplexica
Privacy-focused AI answering engine with web search and citations
Self-hosted AI answering engine that combines web search with local or hosted LLMs to generate cited answers, with search history and file uploads.
Langfuse
Open-source platform for LLM observability, evals, and prompt management
Langfuse is an open-source LLM engineering platform for tracing, metrics, evaluations, datasets, and prompt management to debug and improve AI applications.
Netron
Visualizer for neural network and machine learning models
Netron is a model graph viewer for inspecting neural network and ML formats such as ONNX, TensorFlow Lite, PyTorch, Keras, Core ML, and more.
Onyx Community Edition
Self-hosted AI chat and enterprise search for any LLM
Open-source platform for AI chat, RAG, agents, and enterprise search across your team’s connected knowledge sources, compatible with hosted and local LLMs.
Activepieces
AI-first no-code workflow automation with extensible integrations
Open-source automation builder for creating workflows with webhooks, HTTP steps, code actions, and an extensible TypeScript-based integration framework with AI features.
Opik
LLM observability and evaluation platform for traces, tests, and dashboards
Opik is an open-source platform to trace, evaluate, and monitor LLM apps, RAG pipelines, and agent workflows with automated evaluations and production dashboards.
Maxun
Open source no-code web scraping and data extraction robots
Maxun is an open source no-code platform to build web scraping robots that extract structured data and expose websites as APIs, markdown, or automated pipelines.
Paperless-AI
AI extension for Paperless‑ngx providing automated analysis and RAG
Extension for Paperless‑ngx that uses OpenAI-compatible backends and Ollama to auto-classify, tag, index, and enable RAG-powered document chat and semantic search.
ezBookkeeping
Lightweight, self-hosted personal finance and bookkeeping app.
Open-source, self-hosted personal bookkeeping app with AI-powered features.
Agenta
Open-source LLMOps platform for prompts, evals, and observability
Agenta is an open-source LLMOps platform with a prompt playground, prompt/version management, LLM evaluation, and production observability for LLM apps.
Basic Memory
Local-first persistent memory for AI chats using Markdown notes
Basic Memory gives AI assistants durable, local-first memory by reading and writing structured Markdown notes, enabling reusable context across conversations and tools.
Speaches
OpenAI API-compatible server for speech-to-text and text-to-speech
Self-hosted, OpenAI API-compatible server for streaming transcription, translation, and speech generation using faster-whisper and TTS engines like Piper and Kokoro.
Willow
Open-source, privacy-focused voice assistant platform
Self-hosted voice assistant platform for ESP32 devices with on-device wake-word and command recognition, Home Assistant integration, and an optional inference server for STT/TTS/LLM.
Scriberr
Offline AI audio and video transcription with transcript chat
Scriberr is a self-hosted, privacy-focused AI transcription app for audio and video, with speaker diarization, word-level timestamps, summaries, and transcript chat.
Beelzebub
Low-code honeypot framework using LLMs for safe system deception
Secure low-code honeypot framework that uses LLMs to simulate high-interaction systems across SSH/HTTP/TCP and MCP, with metrics and cloud-native deployment options.
SecureAI Tools
Self-hosted private AI chat and document Q&A with local inference
Self-hosted private AI tools for chat and document Q&A, supporting local Ollama inference or OpenAI-compatible APIs, with built-in authentication and user management.
File Wizard
Browser-based file conversion, OCR, and audio transcription UI
Self-hosted web UI for file conversion, OCR for PDFs/images, and local Whisper-based audio transcription, wrapping common CLI tools with background jobs and history.
Recommendarr
AI recommendation app for movies and TV using your media libraries
LLM-driven movie and TV recommendation web app that uses Sonarr/Radarr libraries and Plex/Jellyfin watch history to generate personalized suggestions.
Panora
AI-powered back-office automation for purchase order entry
Automates purchase order ingestion, validation, and ERP posting for distributors, manufacturers and wholesalers using AI-driven item matching and configurable workflows.
Operately
Open-source company operating system for goals, projects and reviews
Open-source operating system that connects company goals, projects and check-ins with opinionated workflows, an AI executive coach, and self-hosting options.
Feeds Fun
Self-hosted RSS/news reader with AI-powered tagging and scoring
News and RSS reader that auto-assigns tags (including via LLMs), lets you define scoring rules, and filter/sort feeds; supports single- and multi-user deployments.
Tiledesk
Open-source platform for AI chatbots and multichannel live chat
Open-source conversational platform to build AI chatbots, multichannel live chat, and human-in-the-loop customer support with knowledge base and RAG capabilities.
Overr-Syncerr
Webhook handler for subtitle sync and audio/subtitle preferences
Automates subtitle synchronization and user audio/subtitle preferences via webhooks from Overseerr/Jellyseerr, integrating with Sonarr, Radarr, Bazarr and Plex.
Vanilla Cookbook
Self-hosted recipe manager built with SvelteKit
Self-hosted recipe manager and PWA with web scraping, ingredient parsing, unit conversion, shopping lists, cooking logs, LLM-assisted features, and Docker deployment.