LLM AI Tools

Osmantic deployment system is an on-premises AI server for PC, Mac, and Linux that provides local LLM inference, model management, and service orchestration.It includes a chat-style web UI, voice input/output, agents, and workflow automation for developers, researchers, and homel... Read more →

Portkey is an LLMOps platform that combines an AI Gateway, observability, guardrails, governance, and prompt management into a single interface. It exposes a unified API for accessing multiple LLMs and a model catalog, reducing integration complexity for developers and AI teams.P... Read more →

Otari is an open-source AI gateway and hosted control plane that unifies access to 40+ LLM providers including OpenAI, Anthropic, Azure, and Google Gemini.Provides a single-endpoint LLM routing layer with per-workspace routing rules, model-level selection, and automatic failover... Read more →

DeepSeek Free offers browser access to the DeepSeek-R1 and DeepSeek-V3 language models with 671 billion parameters, enabling advanced reasoning and high-throughput text generation. The chat interface supports conversational Q&A, code assistance, mathematical problem solving,... Read more →

LLMs Work is a visual deep dive into how large language models operate, covering pre-training, tokenization, transformer architecture, attention mechanisms, inference, and retrieval-augmented generation (RAG) pipelines.The resource documents data preparation steps—web crawling, l... Read more →

Heretic is a toolkit for customizing, ablation testing, and evaluating large language models (LLMs).It supports dense models and MoE/hybrid architectures and provides built-in chat, a benchmark runner, and model testing utilities.heretic implements multiple ablation and analysis... Read more →

Wafer provides serverless inference and dedicated endpoints for running open-source LLMs in production.It supports multiple models (glm-5.2, glm-5.1, kimi-k2.6 with a 262k context window, qwen 3.5, and deepseek variants) for coding, reasoning, and long-context tasks.Serverless AP... Read more →