447 results. Find your next favorite, with a little help from the community.
Meta Superintelligence Labs' flagship model replacing the Llama line. 1M token context, 131K max output. Ranked #1 on TaxEval v2 out of 123 models.
ProductFair-code workflow automation platform with native AI agent capabilities. 195k GitHub stars, 1500+ integrations, visual builder with custom code support.
NVIDIA's 120B open-weight MoE reasoning model (12B active) with 1M context and 350 tok/s output speed. Open weights on HuggingFace.
NVIDIA's 550B parameter MoE model with 55B active parameters, delivering frontier-level performance for enterprise AI deployments and inference optimization.
Google's AI research assistant that analyzes uploaded documents, generates audio overviews, and answers questions grounded in your sources.
AI workspace toolkit with autonomous agents, AI Meeting Notes, Research Mode, multi-model support (GPT-5, Claude, Gemini), and external agent integration.
ProductSelf-hosted AI interface supporting Ollama and OpenAI APIs with RAG, voice calls, image generation, and plugin support. 144k GitHub stars.
AgentOpen-source personal AI assistant running on any OS and platform. 382k GitHub stars, 65k commits, 220 releases. MIT licensed, community-driven with plugin ecosystem.
AI meeting agent with real-time transcription, live chat, automated summaries, insights, and action items for Zoom, Meet, and Teams meetings.
Open-source AI code editor forking VS Code with integrated Continue, aider, and Roo Code agents for a unified AI coding experience.
On-device AI developer tool capturing live context from browsers to IDEs, managing snippets with multiple LLM support and infinite artificial memory.
AI video generation platform with near-real-time generation, creative unreal effects (squish, melt, cake-ify), and text-to-video capabilities.
Poolside AI's coding-focused foundation models (M.1 flagship 225B MoE and XS.2 open-weight) built specifically for agentic software engineering.
MCPOfficial MCP server for read-only PostgreSQL database access with schema inspection. Enables AI agents to query databases and analyze data without write access.
Alibaba's Qwen 3.6 family released in six variants including Max Preview, scoring 51.81 on the Intelligence Index. Open-weight with strong multilingual support.
Alibaba's efficient 35B MoE model (3B active) ranked #1 on six coding/agent benchmarks including SWE-bench Pro and Terminal-Bench 2.0.
ProductOpen-source RAG engine combining deep document understanding with agent capabilities for enterprise knowledge retrieval. 84.5k GitHub stars.
macOS launcher with integrated AI providing extensions ecosystem, developer tools, and system-wide AI assistance across all applications.
Runway's latest AI video generation model combining visual references with text instructions for consistent cinematic styles and camera control.
ByteDance's frontier language model released June 2026, part of their Seed foundation model series powering Doubao and internal AI products.
ByteDance's AI video generation model producing native 30-second 4K clips with up to 50 multimodal reference inputs. Strong temporal coherence and character consistency.
MCP server for Sentry error tracking allowing AI agents to triage issues, fetch stack traces, and manage releases from the coding environment.
MCPOfficial MCP server for dynamic and reflective problem-solving through structured thought sequences with revision capabilities for complex reasoning tasks.
MCPIDE-like MCP toolkit giving AI coding agents semantic code retrieval and editing. Supports symbol navigation, refactoring, rename across 40+ languages via LSP.