Smart model router for personal AI agents that sends each request to the cheapest model capable of handling it — cutting API costs by up to ~70%. Uses a fast 23-dimension scorer, automatic fallbacks, per-tier controls, and supports local Docker self-hosting or a cloud app; ideal for cost-sensitive personal agents.
Create and run node-based generative AI workflows for images, video, 3D, and audio — reusable, shareable node graphs with custom nodes, live previews, and local/cloud runtime options. Open-source with Comfy Cloud and Hub for creators.
Runs an agentic RAG loop over scientific papers: searches literature, gathers and re-ranks evidence chunks, then answers with in-text citations. Adds metadata-aware embeddings, retraction checks, and contradiction detection across full PDFs.
Visual canvas for composing, testing, and deploying LLM-based pipelines and multi-agent workflows. Supports major LLMs and vector databases, exports flows as APIs or MCP servers, and offers a desktop bundle for local experimentation and iteration.
Locally hosted frontend that connects to many text, image, and TTS backends (KoboldAI, Ooba, Tabby, OpenAI, Claude, OpenRouter, Mistral, NovelAI, Horde). Built around character cards, lorebooks, group chats, and extensions for deep prompt control.
Self-hosted, MIT-licensed interface that puts OpenAI, Anthropic, Google, Azure, AWS, and local models behind one chat UI. Adds agents, a code interpreter, MCP tool connections, persistent memory, web search, artifacts, and multi-user SSO auth on top.
Bring-your-own-key chat client that keeps every conversation in the local browser, never a server. One UI reaches OpenAI, Claude, Gemini, DeepSeek and a dozen more providers across web, desktop and mobile, with MCP, plugins, and one-click self-hosting.
A bring-your-own-API-key chat frontend for ChatGPT, Claude, Gemini and other models, running entirely in your browser with local storage. Adds a prompt library, plugins, model switching, and team/agent setups on top of raw provider APIs.
Self-hosted AI coding assistant you run on your own hardware as an alternative to cloud Copilot. Offers context-aware completion, an in-IDE answer engine and chat, using RAG over your repositories so suggestions match your team's code.
Pulls context from your whole codebase via Sourcegraph's search API to power chat, autocomplete, and edits across VS Code, JetBrains, and the CLI. Now ships only inside Sourcegraph Enterprise; the free and Pro tiers are retired.