447 results. Find your next favorite, with a little help from the community.
An Agent Skill that guides compatible AI agents through a constrained workflow for creating simplified rounded mascot-style logo concepts.
An MCP server for searching and analyzing Fireflies.ai meeting transcripts, summaries, soundbites, and analytics.
A coding and knowledge-work model designed for long-running agents, multi-step reasoning, and visual or interactive tasks.
An always-on AI teammate that runs on a persistent computer and works across connected apps with approval checkpoints.
A generally available multimodal Gemini model for coding and agentic workflows with a one-million-token input context window.
A small coding model with native image understanding, tool use, and agentic workflow support in GitHub Copilot.
Anthropic's platform for building and running agentic workflows in production; adds scheduled runs, environment vaults, built-in memory, and sandboxes.
Anthropic's invitation-only Claude Mythos Preview model powering Project Glasswing; focused on finding and patching vulnerabilities in critical software.
Mistral's 7.3B code model using Mamba2 SSM architecture instead of transformer; Apache 2.0, up to 256k tokens context, linear-time inference for code tasks.
OpenAI's Codex extension for VS Code, Cursor, and Windsurf providing an in-editor coding-agent UI with mode/reasoning-effort switching and sign-in with ChatGPT.
Self-hosted MCP server as a single Rust binary providing persistent agent memory, vector/hybrid search, knowledge graph, and session management.
Google's second-generation multimodal model family, built for the agentic era with native tool use, multimodal input, and image plus audio output.
Gemini 2.5 image generation and editing model (Nano Banana) with character consistency across edits, multi-image blending, and natural-language transforms.
OpenAI's non-thinking fast variant within the GPT-5.3 series that powers most ChatGPT queries, tuned for lower latency with reduced hallucinations and fewer refusals.
Multi-agent high-compute variant of Grok 4 delivered via the SuperGrok Heavy tier; runs parallel agents on the same query for advanced reasoning benchmarks.
xAI's terminal-based coding agent CLI in early beta for SuperGrok and X Premium+ subscribers; supports plan mode, parallel subagents, plugins, MCP servers, and skills.
Mistral's 8B dense edge LLM with 128k context and sliding-window attention; released with Ministral 3B under a Mistral Research License, weights research-only.
Google DeepMind's Gemini 3 Pro Image model for studio-quality generation and editing, with improved text rendering and better world-knowledge grounding.
Microsoft's 14B dense small language model in the Phi-3 family, trained on curated textbook-quality data; released on Azure alongside Phi-3-small and Phi-3-vision.
Reasoning-tuned variant of Microsoft's Phi-4-mini SLM for math and step-by-step chain-of-thought, released with Phi-4-reasoning and Phi-4-reasoning-plus.
Unified multimodal understanding-and-generation preview from Alibaba's Qwen team; text-to-image and instruction-based image editing accessible via Qwen Chat.
2.4T-parameter sparse MoE from Alibaba. Natively multimodal (text, image, video, docs) with 1M-token context. Positioned as frontier-class for long-horizon coding, document work, and agentic tasks.
Perplexity's agentic web browser with a built-in AI assistant that summarizes pages, fills forms, and executes multi-step browsing tasks on the user's behalf.
355B/32B-active MoE with 128K context, MIT license; hybrid thinking model with toggleable reasoning modes for agentic/reasoning/coding (ARC) tasks.