Loading...
Agentic video understanding with Gemini enables selective video analysis for better accuracy and lower token usage via the Gemini API in Google AI Studio and Gemini Enterprise Agent Platform.
Experiential Labs is an open source AI gateway routing hosted providers, your keys, and GPUs via one OpenAI-compatible endpoint with access control, budgets, attribution, and caching.
Gemini 3.8 Flash and 3.8 Flash Cyber are Google Gemini models for agentic coding, multi-step reasoning, and cybersecurity defense through the Fairwind Program.
Discover Claude Fable 5.1 and Claude Mythos 5.1 for coding, knowledge work, and long-running problem-solving, with enterprise safeguards and lower estimated token pricing.
TrustedRouter is an OpenAI-compatible AI router for hundreds of models through one API, with verifiable privacy, provider failover, and BYOK support.
oMLX is a native macOS inference server built on MLX for local models on Apple Silicon Macs, with SSD-backed KV caching and OpenAI/Anthropic endpoints.
Revalvo is a browser-based, local-first LLM eval workbench for running prompts across multiple models, scoring results, versioning prompts, and batch-testing datasets.
GLM-5.3-Flash is Z.ai’s native multimodal model for coding, agentic workflows, and visual tasks, available via the Z.ai API platform and coding plan.
IQ Routing routes each request to the cheapest model tier that still meets quality needs for chatbots, RAG, agent loops, and finance workloads.
Speko is a voice AI router that benchmarks speech models by language and routes STT, LLM, and TTS through one API. It also offers packaged infrastructure and enterprise contracts.
Local is a macOS app for private, on-device AI chat, coding and meeting workflows, with model recommendations for your Mac and optional cloud access via your API key.
Router by Ramp is an AI routing product with one endpoint and one bill for multiple models, helping cut inference spend without sacrificing performance.
NobodyWho is an on-device inference engine for running LLMs locally without API keys or cloud calls. Supports multiple app frameworks and GGUF models from Hugging Face or any URL.
Grok 4.6 is xAI’s latest model for long-running agents, coding, research, and visual project drafting, available in Cursor, Grok Build, API, and partners.
Gemini 3.7 Flash is Google’s Flash-series AI model for coding, agent workflows, web development, and document-heavy work.
Statewave is an open-source memory runtime for AI agents and LLM apps, storing durable, structured context with provenance across sessions.
Cohesor is an AI gateway and control plane for agents that routes requests, compresses tokens, brokers MCP tool calls, and enforces policy from one endpoint.
Unsloth is a free, open-source desktop app for running and training AI models on local hardware, with model downloads, agent connections, media generation, and private research.
Soup CLI is a command-line tool for LLM fine-tuning and post-training on your own hardware, with low-VRAM training, data checks, config generation, preference optimization, and checkpoint gating.
What's my local AI? helps you detect your hardware locally and find AI models that may run with Ollama or LM Studio—without uploading machine data.