How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
ODS is a self-hosted platform that turns a personal computer into a private AI server. It bundles local language model inference, a browser-based chat interface, voice, web search, workflow automation, and image generation into one containerized stack, so prompts and files stay on your own machine rather than passing through cloud services. It runs models on a GPU, Apple Silicon, or CPU, and installs with a single command on Windows, macOS, or Linux.
The main features of osmantic/ods are: Local Model Serving, Self-Hosted AI Platforms, LLM Gateways, Local Model Chat Interfaces, Self-Hosted Chat Interfaces, Hybrid Local-Remote AI Routing, Private AI Deployments, Private AI Infrastructure.
Projects with overlapping indexed features include: 11cafe/jaaz — Jaaz is a self-hosted AI design suite and multimodal workspace used for generating and editing images and videos. It… ericlbuehler/mistral.rs — mistral.rs is an inference engine for large language models that runs locally and exposes models behind OpenAI and… danswer-ai/danswer — Danswer is an LLM application framework and RAG engine that provides a self-hosted interface for connecting large… maziyarpanahi/openmed — OpenMed is a local-first healthcare AI toolkit for clinical text. It finds diseases, drugs, anatomy, genes and… coaidev/coai — CoAI is an enterprise-grade, self-hostable AI gateway platform that unifies access to over 200 AI models from more… abetlen/llama-cpp-python — llama-cpp-python provides a Python interface for the llama.cpp library, enabling the execution of large language…
Jaaz is a self-hosted AI design suite and multimodal workspace used for generating and editing images and videos. It functions as a design workspace where users can produce visual content and assets through a combination of local and cloud-based AI models. The project features a hybrid model orchestrator that routes requests between local model runners and remote APIs to balance data privacy with processing performance. It utilizes an infinite canvas collaborative tool for organizing storyboards and assets, and includes an image prompt optimizer to translate rough ideas into detailed generati
mistral.rs is an inference engine for large language models that runs locally and exposes models behind OpenAI and Anthropic-compatible APIs. It serves as a multi-model serving platform, capable of loading several models in a single server process with per-request routing and on-demand loading and unloading. The engine supports multimodal inference, processing text alongside images, video, audio, and speech inputs, and includes a quantized model deployment runtime that reduces memory use and speeds up inference on consumer hardware. The project distinguishes itself through an agentic tool exe
Danswer is an LLM application framework and RAG engine that provides a self-hosted interface for connecting large language models to private data. It serves as an enterprise AI chat interface and agent orchestrator, enabling the creation of specialized assistants with custom instructions and knowledge bases. The platform differentiates itself through an observability dashboard for tracking query history and token consumption, as well as a white-labeled interface for customized branding. It includes a multi-step research workflow for producing long-form reports and a sandboxed environment for
OpenMed is a local-first healthcare AI toolkit for clinical text. It finds diseases, drugs, anatomy, genes and personal identifiers in medical notes, then masks, replaces, hashes or date-shifts the identifiers under HIPAA, GDPR and research-style policy profiles. It also turns extracted entities into terminology-coded FHIR resources and OMOP records. A curated registry of specialized medical entity-recognition models, selectable by name, sits underneath all of this. Its de-identification work covers dozens of languages and scripts. It uses locale-aware fake replacements, checksum-valid nation