AgentSea

AgentSea offers a secure AI chat platform with access to the latest models, community-built agents, and integrated search and image tools—all while protecting your data with Secure Mode that ensures privacy using open-source or in-house hosted mod...

Onlook for Web

Onlook for Web is an open source visual builder that streamlines design-to-development handoffs by creating production-ready apps directly from code, ensuring zero translation errors and seamless collaboration across product teams.

Grok 2.5 (OSS Ver.)

Grok 2.5 (OSS Ver.) is an open-source AI model offering advanced language understanding and generation capabilities, enabling developers to build intelligent applications with a proven, reliable foundation from xAI’s top-performing model.

Disco.dev

Disco.dev is a personal MCP hub that simplifies AI agent tool integration with zero-setup servers, open-source connectors, and customizable, remixable servers—making it easy to discover, run, and tailor AI automations without infrastructure hassles.

Ito

Ito is a free, open-source Mac app that converts your voice into polished text across any application. Capture ideas, transcribe meetings, or write hands-free with accurate speech recognition and instant formatting, boosting productivity and creat...

Basedash Self-Hosted

Basedash Self-Hosted lets you run Basedash on your own infrastructure for full control and security. Deploy easily with a one-line agent, Docker, Kubernetes, or air-gapped setups, ensuring flexible and secure database management.

Omnara

Omnara lets you manage AI agents on the go with real-time alerts, one-tap approvals, and a full mobile interface. Compatible with Claude Code, n8n, and custom agents, it keeps your AI workflows moving without being tied to your desk.

Chord Mini

Chord Mini is an open-source tool that detects chords and beats in music tracks, providing accurate analysis to support music projects and research. Future updates will integrate additional models for enhanced music analysis capabilities.

TensorZero

TensorZero is an open-source LLM infrastructure offering a unified API for multiple providers, real-time observability, optimization through feedback, evaluation tools, and built-in experimentation to streamline industrial-grade large language mod...

Private Mind

Private Mind is a free, open-source app that runs AI locally on your device, ensuring complete privacy, fast responses without internet, and full control over your data. Experience powerful AI without compromising security or speed.

Hunyuan-GameCraft

Hunyuan-GameCraft lets you control and direct detailed game scenes from a single image using keyboard inputs, ensuring long-term consistency. Its open-weight, quantized model runs efficiently on consumer GPUs like the 4090 for accessible interacti...

Compozy

Compozy simplifies multi-agent AI orchestration with declarative YAML workflows, offering reliable, production-ready management without vendor lock-in. Built for speed and flexibility, it reduces dev time and supports seamless, language-agnostic A...

SelfHostLLM

SelfHostLLM simplifies planning for self-hosted AI by accurately estimating GPU needs and concurrency for models like Llama, Qwen, and Mistral. Now available for Mac, it supports custom configurations including Apple Silicon deployments.

mcp-use

mcp-use is an open-source SDK that helps development teams build, deploy, and manage custom AI agents with MCP servers efficiently, addressing configuration, authentication, access control, and observability challenges in a unified platform.

Hierarchical Reasoning Model

Hierarchical Reasoning Model solves complex problems like extreme Sudoku and large-scale pathfinding using just 1,000 examples without pre-training. It outperforms larger models on reasoning tasks with fewer parameters and minimal data.

BashNota

BashNota is an open-source tool that simplifies managing and organizing Bash scripts, enabling clear documentation and efficient code maintenance for developers working with shell scripting.

ClueoMCP

ClueoMCP is an open protocol that injects scientifically-calibrated Big Five personality traits into large language models, enabling more nuanced and human-like AI interactions grounded in behavioral science.

GLM-4.5

GLM-4.5 is a 355B parameter open-weight MoE model delivering advanced reasoning, coding, and agentic task performance. Available in flagship 355B and 106B Air versions, it supports efficient dual-mode inference for versatile AI applications.

Kanbanq : Open alpha

Kanbanq is a fast, lightweight project tool for solo developers and small teams, featuring dual Kanban boards for sprint and backlog management. It offers real-time collaboration and an AI assistant that organizes tasks and streamlines planning.

Wan 2.2

Wan 2.2 is an open-source video generation model featuring Mixture-of-Experts architecture for high capacity and efficiency. It offers detailed cinematic control over lighting and composition and runs a 5B parameter model on a single consumer GPU.

Aeneas

Aeneas uses AI to restore and interpret damaged ancient inscriptions, offering historians new insights from fragmentary texts and aiding the study of historical connections with advanced, data-driven analysis.

HunyuanWorld 1.0

HunyuanWorld 1.0 generates immersive 3D scenes from text or images, allowing users to create, explore, and export playable worlds as standard 3D mesh assets compatible with game engines and CG pipelines.

ToolSDK.ai

ToolSDK.ai is a free TypeScript SDK that simplifies connecting AI agent apps to 5,000+ MCP servers. Integrate and manage multiple servers with one line of code, enabling fast development of AI agents and automation workflows.

OpenWispr

OpenWispr is a free, open-source speech-to-text tool that runs locally, helping you write 3-5x faster by capturing natural speech. Ideal for prompting AI models like ChatGPT, it preserves your tone and requires no subscription fees.

ComfyUI-Copilot

ComfyUI-Copilot is an AI assistant that simplifies ComfyUI workflows by letting you describe tasks in natural language and automatically fine-tunes parameters, making setup faster and more accessible for both beginners and experts.

Kuzco

Kuzco is an open-source Swift wrapper for llama.cpp that enables developers to run AI models locally on iOS and macOS, reducing costs and keeping data private without relying on cloud APIs. Integrate AI with minimal code and full control.

UTCP

UTCP enables AI agents to call tools’ native endpoints directly, eliminating wrapper servers for lower latency and seamless use of existing security and authentication. It offers a streamlined, efficient alternative to traditional tool-calling pro...

Vogent Voicelab

Vogent Voicelab offers a scalable API for running top open-source text-to-speech models with low latency. It ensures consistent, high-quality voice output and handles all compute, letting you pay per character without managing infrastructure.

Kimi K2

Kimi K2 is a 1 trillion parameter open-source AI model offering advanced agentic coding capabilities. Access it via the official website or API for powerful development support without heavy local hardware demands.

Intervo

Intervo is an AI assistant that helps businesses respond to customer inquiries instantly and accurately, preventing lost leads and improving support efficiency without costly or limited chatbot solutions.

opencode

Opencode is an open-source, Golang-built CLI coding agent featuring a customizable terminal interface. It supports multiple parallel sessions and works seamlessly with large model APIs or local models, offering flexible AI-assisted coding workflows.

xmcp

xmcp streamlines app setup with create-xmcp-app, a CLI tool that scaffolds projects complete with necessary files and dependencies, enabling developers to start building quickly and efficiently.

TensorBlock Forge

TensorBlock Forge offers a unified API layer connecting multiple AI providers with secure key management and full-stack orchestration, enabling developers to build and scale AI agents and multi-model workflows without vendor lock-in or complex int...

Kyutai TTS

Kyutai TTS is an open-source text-to-speech tool offering ultra-fast streaming audio with natural voices. It starts speaking instantly as text is generated, enabling seamless real-time conversational AI experiences.

Voicebun

Voicebun is an open-source voice agent builder that lets you create custom voice assistants by simply providing a prompt. Configure your agent to fit your needs with an affordable, user-friendly platform backed by a developer committed to accessib...

EX-4D

EX-4D generates controllable 4D videos with dynamic camera angles from a single 2D video using a Depth Watertight Mesh for smooth, artifact-free results. Open-sourced by Bytedance Pico, it advances AI-driven video for VR and MR applications.

create-api.dev by Kong

create-api.dev by Kong lets you quickly generate OpenAPI specs by simply describing your API. No setup or accounts needed—start editing or sharing instantly. Built on open source tech and integrated with Kong’s AI Gateway for seamless API design.

Qwen3-Coder

Qwen3-Coder is a 480B MoE open model optimized for agentic coding. With 35B active parameters, it delivers top benchmark performance, supports up to 1M context, and includes an open-source CLI tool, Qwen Code, for efficient coding workflows.

LLM Gateway

LLM Gateway is an open-source AI gateway that lets you route, manage, and analyze LLM requests across 11+ providers via a unified API. Track usage, costs, and configure caching—all from one dashboard for seamless LLM integration and control.

Gemma 3n

Gemma 3n is Google's open multimodal AI model with MatFormer architecture, enabling efficient on-device processing of images, audio, and video. Its lightweight 2B/4B variants run smoothly on phones and laptops without cloud dependency.

FLUX.1 Kontext

FLUX.1 Kontext offers advanced AI-driven image editing with strong character and style consistency. Now open-weight, it enables iterative, context-aware edits directly on consumer hardware for precise and seamless image refinement.

Inworld TTS

Inworld TTS offers real-time, multilingual voice AI with free voice cloning at a fraction of typical costs—up to 20x cheaper. It provides accessible, high-quality text-to-speech with open-source training and modeling code for developers.

Droidrun

DroidRun is an open-source tool for automating real Android apps with speed and flexibility. Ideal for developers testing flows, building bots, or scraping UIs, it offers fast local setup and full control over mobile automation on real devices.

Handit.ai

Handit.ai is an open-source engine that monitors and improves AI agents by evaluating decisions, auto-generating better prompts, A/B testing fixes, and ensuring consistent, reliable performance across any AI stack without extra infrastructure.

NativeMind

NativeMind delivers fast, private access to advanced AI models like Deepseek, Qwen, and LLaMA directly in your browser. Powered by Ollama and fully local, it ensures your data stays on device while providing seamless AI performance.

Hunyuan3D-2.1

Hunyuan3D-2.1 by Tencent is an open-source AI tool that generates high-fidelity 3D assets with PBR textures from images, optimized to run on consumer GPUs. Full code and weights are available for production-ready 3D asset creation.

Kodosumi

Kodosumi is an open-source runtime that enables developers to deploy and scale AI agents efficiently. It offers fast performance, seamless scalability, and is completely free to use, making AI agent management straightforward and cost-effective.

MiniCPM 4.0

MiniCPM 4.0 is an open-source family of ultra-efficient on-device AI models offering fast performance on edge chips. It features highly quantized BitCPM versions for enhanced speed and efficiency in resource-constrained environments.

VibeKit

VibeKit is an open-source SDK that runs coding agents like OpenAI Codex and Claude securely in sandboxes. It enables safe code writing, package installation, and PR creation with built-in streaming, async tasks, and telemetry—MIT licensed and zero...

Athena

Athena by Microsoft is an AI agent in Teams that streamlines developer workflows by managing pull requests, tasks, and releases. It boosts collaboration and efficiency with an open-source template (Dex) for easy customization.

skillsync

Skillsync analyzes your codebase to identify domain experts, uncover unique skills, and capture effective patterns—providing actionable insights without surveys to help you scale successful practices across your team efficiently.

Shisa.AI

Shisa.AI offers Japan’s leading open-source bilingual LLM, Shisa V2 405B, built on Llama 3.1 405B. It delivers top-tier Japanese and English language performance, rivaling GPT-4o and DeepSeek-V3, with full model, dataset, and chat demo access.

Ensemble AI

Ensemble AI reduces training and inference costs by shrinking custom or open-source models into smaller, faster versions without losing accuracy. Upload your model and get optimized performance instantly.

AI Diplomacy

AI Diplomacy lets multiple AIs command Europe's great powers, forming alliances, bluffing, and strategizing to outwit rivals in a complex battle for global dominance through language-driven tactics and negotiation.

Circuit Tracer

Circuit Tracer by Anthropic visualizes internal computations of large language models as attribution graphs, enabling researchers to analyze and interpret AI decision processes for greater transparency and insight. Available on Neuronpedia and as ...

Dyad

Dyad is a free, open-source local coding tool for Mac and Windows that offers full control without vendor lock-in. It integrates smoothly with AI assistants like Cursor and Claude Code, empowering developers with a flexible, subscription-free codi...

DeepSeek-R1-0528

DeepSeek-R1-0528 is an open-source LLM offering advanced coding and reasoning capabilities with a long context window, delivering enhanced accuracy for processing extended texts and complex programming tasks.

HunyuanVideo-Avatar

HunyuanVideo-Avatar by Tencent generates emotion-controlled, multi-character talking avatar videos from audio. This open-source tool ensures consistent character representation with released code and models for seamless video creation.

Command A Reasoning

Command A Reasoning by Cohere is an advanced enterprise reasoning model that runs privately on a single H100, outperforming gpt-oss-120b. It offers user-controlled token budgets to optimize cost and performance efficiently.

Airweave

Airweave is an open-source tool that connects to apps, databases, and document stores, transforming their data into searchable knowledge bases for agents to quickly access relevant information across platforms.

Bagel

Bagel by ByteDance-Seed is an open-source multimodal AI model that enables advanced image and text generation, editing, and interaction, offering capabilities on par with proprietary solutions under the Apache 2.0 license.

Magentic-UI

Magentic-UI by Microsoft Research is an open-source web agent that enables collaborative planning and execution of web tasks with AI. It features co-planning, action guards, and plan learning to streamline complex workflows.

Langfuse Custom Dashboards

Langfuse Custom Dashboards provide teams with integrated, real-time insights to debug, analyze, and optimize LLM applications collaboratively, streamlining development and improving performance within a unified open-source platform.

Hunter MCP

Hunter MCP is an open-source protocol server that connects Hunter B2B data tools with AI assistants, enabling natural language queries for email finding, verification, and data enrichment using Hunter’s reliable APIs.

Ollama Desktop App

Ollama Desktop App lets you run open-source AI models locally on macOS and Windows. Chat with LLMs, analyze images, and process files through a simple, private interface without relying on cloud services.

Sim Studio

Sim Studio connects LLMs with Slack, Supabase, Pinecone, and Gmail to build research agents, support bots, and file parsers. Collaborate seamlessly by inviting your team to a shared visual canvas for efficient AI-driven workflows.

Ollama v0.7

Ollama v0.7 offers a new engine for first-class multimodal AI, integrating vision models like Llama 4 and Gemma 3. It enhances reliability, accuracy, and memory management for efficient local LLM deployment.

VibeShift MCP

VibeShift MCP uses an auto feedback loop to generate secure, fully functional code in a single attempt. This open-source tool streamlines coding by minimizing errors and boosting efficiency in software development.

Algebras AI

Algebras AI is an open-source tool with a clean UI for fast AI experimentation in any language. It supports all LLM APIs and is built for Next.js, enabling seamless scaling without delays or the need for proofreading.

HanaVerse

HanaVerse is an open-source, self-hosted web UI that brings Ollama language models to life through Hana, a 2D anime character who visually reacts and provides spoken responses via text-to-speech for interactive conversations.

Local Operator

Local Operator is an open source multi-agent platform where AI agents collaborate, communicate, and delegate tasks based on expertise, enabling efficient background task management with conversational learning and memory.

Tersa

Tersa is an open source canvas for building AI workflows by dragging, dropping, and connecting nodes. Easily create custom workflows powered by top AI models to streamline and automate complex tasks.

AG-UI

AG-UI is an open, lightweight protocol that standardizes AI agent connections to front-end apps, enabling real-time interactivity, streaming, and human-in-the-loop workflows with support for LangGraph, CrewAI, and more.

OpenMemory MCP

OpenMemory MCP is a private, local-first memory layer with a built-in UI that keeps all data structured and fully controlled on your device, ensuring no cloud sync or external storage for maximum privacy and security. Compatible with all MCP-clients.

Flowise

Flowise is an open-source platform for building AI agents and LLM workflows, enabling developers to create, customize, and deploy generative AI solutions efficiently and collaboratively.

GMSSH

GMSSH is a visual desktop-style server management tool using SSH, offering an open app development hub for SMEs to build and collaborate on business applications across financial, operational, and analytical scenarios.

Probo

Probo is an open-source platform that simplifies compliance with SOC 2, ISO 27001, HIPAA, and more. Choose white-glove service to manage audits seamlessly, letting you focus on your business with transparency and ease.

AI Adventure

AI Adventure is an open-source gaming platform and community where you can create and play narrative adventure games with AI-assisted storytelling, featuring unique characters, goals, and graphics crafted by creators worldwide.

GPT Router

GPT Router intelligently directs queries to the most suitable AI model, ensuring faster, more accurate responses. Streamline your workflow by optimizing task distribution across multiple GPT versions effortlessly.

OpenPlugin

OpenPlugin simplifies access to ChatGPT plugins by providing a user-friendly web app, developer packages, and a launchpad, making it easy for both users and developers to create, discover, and use plugins seamlessly.

LLMonitor

LLMonitor is an open-source toolkit for AI developers to log queries, monitor performance, and evaluate models, helping improve your app’s reliability and quality through enhanced observability and actionable insights.

CodebaseChat

CodebaseChat lets you interact with any GitHub repository by creating an OpenAI GPT trained on its code. Simply provide the repo URL to ask questions and get insights. Fully free and open source for seamless code exploration.

Matter AI

Matter AI is an open-source code review agent that helps developers identify bugs, security risks, and performance issues in code changes, ensuring safer and more efficient software development.

Radio LLM

Radio LLM is an off-grid language model accessible via 868MHz LoRa mesh network, enabling extended-range communication without internet. Ideal for emergency scenarios, it supports user sessions, chat context, and tools like emergency service calls.

Rememberall

Rememberall is a secure, open-source tool that enables Custom GPTs to retain memory across conversations. Mention @rememberall to access past context and maintain seamless, continuous interactions with your AI.

Microsoft Phi-4

Microsoft Phi-4 is a 14B-parameter language model optimized for complex reasoning and math, delivering high performance with efficient size and computation. Available on Azure AI Foundry and Hugging Face for scalable AI applications.

Batteries Included

Batteries Included streamlines DevOps with one-click setups for Postgres, serverless, and RAG stacks, enabling teams to deploy and manage infrastructure effortlessly and focus on building products instead of handling system complexity.

reTerminal by Seeed Studio

reTerminal by Seeed Studio is a compact, Raspberry Pi-based Human-Machine Interface offering modular components and multiple interfaces for industrial monitoring and control applications.

Langtrace AI

Langtrace AI is an open-source observability tool that monitors, evaluates, and improves your LLM applications with end-to-end visibility, advanced security, and seamless integration for optimized performance and reliable development.

MUI for VS Code

MUI for VS Code lets you chat with an AI expert on MUI directly within VS Code. Type "@mui" in GitHub Copilot to get accurate, up-to-date answers with references from the latest MUI documentation, streamlining your development process.

ChattyUI

ChattyUI is an open-source, feature-rich chat interface that runs open-source AI models like Gemma and Mistral locally in your browser via WebGPU, ensuring all processing happens on your PC with no data sent to external servers.

AI-Flow

AI-Flow is an open-source platform that lets you connect multiple AI models with a simple drag-and-drop interface. Build custom AI tools in minutes without coding. Try it free and create AI workflows effortlessly.

Scoopika - TS packages

Scoopika - TS packages is an open-source platform for building AI agents and assistants that see, talk, listen, learn, act, and collaborate in real-time, enabling personalized and interactive AI solutions for diverse applications.

Prompto

Prompto is an open-source web app that lets you easily chat with, query, and fine-tune multiple large language models. Save and manage prompts efficiently to streamline your AI interactions in one user-friendly platform.

Evelyn

Evelyn is an open-source AI tutor that engages students with interactive quizzes, mindmaps, and flashcards, helping to reinforce learning and improve retention through active participation.

Rizz.AI

Rizz.AI is an open-source voice app that helps you practice social interactions like dating or negotiating. Choose a character and scenario, receive a custom score, and get feedback to improve your skills and confidence.

VoltAgent

VoltAgent is an open source TypeScript framework for building and managing AI agents with built-in observability, offering a flexible alternative to no-code tools and starting from scratch.

Chat with Meta Llama 3

Chat with Meta Llama 3 offers a free, open-source AI chat model from Meta, enabling developers to customize and integrate advanced conversational AI with ease. Try the online demo for seamless, flexible AI interaction.

Warpy: Terminal Generative Shell

Warpy: Terminal Generative Shell blends Rust’s efficiency with GPT-powered natural language to create an interactive, conversational terminal experience that simplifies command execution and enhances user productivity.

Superpipe

Superpipe streamlines data processing by automating complex workflows, enabling faster and more accurate pipeline management. It simplifies integration and boosts efficiency for teams handling large-scale data operations.