Tag
Explore by tags
Runs retrieval-augmented Q&A over your own documents on local hardware, so files never leave your machine. Blends semantic, keyword, and late-chunking retrieval, with a router that picks RAG or a direct LLM answer per query and verifies it.
Turns local documents into a private, self-hosted ChatGPT-style assistant with no-code agents for web browsing and workflow automation. Runs across LLM providers — OpenAI, Anthropic, Ollama — and routes tools smartly to cut token use.
Unified TypeScript toolkit for building AI apps and agents: swap between 100+ models from OpenAI, Anthropic, Google and others by changing one line. Ships streaming, tool calling, and framework-agnostic UI hooks for React, Next.js, Vue, and Svelte.
Upload your own documents, PDFs, slides, or web pages and ask questions answered only from that material, with inline citations pointing to the exact passage used. Audio Overview turns your sources into a downloadable two-host podcast discussion.
Lets LLMs run code and control a user’s computer via natural language (Python, JavaScript, Shell, etc.) with interactive approval. Supports local or hosted models, terminal and Colab/Codespaces integrations, streaming output, and configurable safety/auto-run options.
stable-diffusion.cpp is a pure C/C++ implementation for diffusion model inference, based on ggml, supporting models like Stable Diffusion (SD1.x, SD2.x, SDXL), Flux, Wan, Qwen Image, Z-Image, and more. It's lightweight with no external dependencies, supports backends like CPU, CUDA, Vulkan, Metal, and features like LoRA, ControlNet, LCM for efficient local image generation on platforms including Linux, Mac, Windows, and Android.
Calls 100+ LLM providers — OpenAI, Anthropic, Gemini, Bedrock, Azure — through one OpenAI-compatible API, as a Python SDK or self-hosted proxy. The proxy adds virtual keys, spend tracking, rate limits, and load balancing across models and providers.
Chat with your documents via retrieval-augmented generation; each answer carries inline citations and a built-in viewer highlights the cited PDF passage. Pairs full-text with vector search and runs on OpenAI, Azure, Cohere, Ollama, or local models.
Runs open-weight LLMs (Llama, Gemma, Qwen, GGUF) offline on your machine, with an optional bridge to OpenAI/Anthropic/Mistral. Exposes an OpenAI-compatible API at localhost:1337, so SDK code built for OpenAI switches by changing one base URL.
Self-hosted browser chat interface for interacting with local or remote LLMs. Supports multiple backends (Ollama, OpenAI-compatible endpoints, llama.cpp), RAG/document chat, plugins/actions, and Docker-based deployment — aimed at teams that need private, customizable LLM UIs.
Builds stateful LLM agents whose memory persists across sessions: a tiered, self-editing memory system lets an agent rewrite its own context window so it remembers, learns, and improves over time. Model-agnostic, with Python/TypeScript SDKs.
Brings ChatGPT, Claude, Gemini, Perplexity, DeepSeek, Grok and other AI chat services into one desktop app, each in its own isolated session and window. Adds prompt management, multi-window layouts, a built-in terminal, and local-first history.