Tag
Explore by tags
Run prompts against OpenAI, Claude, Gemini, and dozens of local or remote models from one terminal command, logging every prompt and response to SQLite. Plugins add new providers, tools, and embeddings; supports schema extraction and function calling.
Build LLM apps by chaining nodes on a visual canvas — prompts, branching, RAG, agents, tools — and ship the same graph as an API or hosted app. Bundles a plugin marketplace, model routing across hosted and local providers, and built-in observability.
Streamlines post-training and fine-tuning for large language and multimodal models with a single YAML-driven pipeline. Supports LoRA/QLoRA, full fine-tuning, preference tuning, RL methods, multi-GPU/FSDP/DeepSpeed, and many model backends (Hugging Face, local checkpoints).
Connects a frozen vision encoder to a language model via visual instruction tuning, yielding an open multimodal assistant that follows image-grounded instructions. Released checkpoints span 7B-34B and approach GPT-4V on vision-language benchmarks.
Translates plain-English questions into pandas/SQL code over CSV, Parquet, and SQL databases, returning tables and charts. Combines LLMs with RAG and a semantic layer so non-coders query data; a Docker sandbox isolates generated code.
Self-hosted gateway putting OpenAI, Claude, Gemini, DeepSeek and 20+ providers behind one OpenAI-compatible endpoint. Adds per-token quotas, channel load balancing and usage billing, so teams or resellers meter keys without sharing upstream credentials.
Self-hostable chat UI that connects to any LLM and adds Agents, Web Search, RAG, connectors, code execution and image generation. Ships connectors to 40+ sources and deployment guides for Docker/K8s. Best for teams needing private, extensible chat platforms.
Declarative CLI and library to evaluate and red-team LLM apps: run test cases against prompts and models, compare providers side-by-side, and scan for jailbreaks, prompt injection, and data leaks — with CI/CD and pull-request code scanning built in.
Compiles one LLM into device-native binaries running on CUDA, ROCm, Metal, Vulkan, WebGPU, and CPU — same model from server to browser to phone. On Apache TVM, it ships MLCEngine with an OpenAI-compatible API across Python, JS, REST, iOS, and Android.
Wraps a local, OpenAI-compatible inference server in one messages API so you can build private AI apps with no data leaving your network: document ingestion, retrieval with inline citations, and built-in tools (web search, code execution, MCP).
Blind side-by-side voting site where users send one prompt to two anonymous chat models, pick the winner, and millions of votes become Elo rankings across text, coding, vision, image, and video. Crowd preference, not static benchmarks, decides the order.