Search Results for "chat box"

ODS, or Osmantic Deployment System, turns a Windows, macOS, or Linux computer into a private AI server. Its installer detects available hardware, selects an appropriate local model, generates credentials, and launches a prewired service stack. The platform combines local model inference with a browser chat interface and a dashboard for managing models, services, GPUs, and extensions. It also integrates agents, voice, workflows, RAG, private search, and image generation. Services are modular,...

Dify is an easy-to-use LLMOps platform designed to empower more people to create sustainable, AI-native applications. With visual orchestration for various application types, Dify offers out-of-the-box, ready-to-use applications that can also serve as Backend-as-a-Service APIs. Unify your development process with one API for plugins and datasets integration, and streamline your operations using a single interface for prompt engineering, visual analytics, and continuous improvement. Out-of-the-box web sites supporting form mode and chat conversation mode A single API encompassing plugin capabilities, context enhancement, and more, saving you backend coding effort Visual data analysis, log review, and annotation for applications

PenEcho is an open-source shared canvas that makes handwriting, equations, diagrams, and spatial context part of an AI conversation. Users can draw with pressure-sensitive ink, erase, pan, zoom, type formatted text, and arrange ideas across a large virtual workspace. The application sends focused visual regions to an API, Codex CLI, or Claude CLI and converts model responses into editable canvas commands. AI output can include text, formulas, plots, mixed drawings, erasures, and declarative...

...Computer backends include local Docker plus E2B, Daytona, Box, and trusted local machines. The complete stack can be self-hosted, while voice mode adds dictation, spoken replies, and calling with supported speech providers.

...It focuses on operating real user interfaces from screenshots plus text, and follows a strict input–output format that returns structured actions, grounded operations, and optional sensitivity annotations. The model is designed for agent-style execution rather than freeform chat, maintaining a continuous execution history across steps while requiring a fresh session for each new task. Inference supports BF16 on NVIDIA GPUs, with optional INT8 and INT4 modes available but with noted performance loss at INT4; example CLIs and a web demo illustrate bounding-box outputs and operation categories.