Products

OpenRouter is a unified API gateway that provides developers and businesses with seamless access to a vast array of Large Language Models (LLMs from leading providers such as OpenAI, Anthropic, Google, Meta, and Mistral. By consolidating multiple AI models into a single, standardized interface, OpenRouter simplifies the integration process, allowing users to interact with various models without the need to manage multiple accounts or APIs. This approach enhances flexibility, optimizes performanc

LobeChat - An open-source, modern-design ChatGPT/LLMs UI/Framework. Supports speech-synthesis, multi-modal, and extensible plugin system. One-click **FREE** deployment of your private OpenAI ChatGPT/Claude/Gemini/Groq/Ollama chat application. Features ### 1. Multi-Model Service Provider Support In the continuous development of LobeChat, we deeply understand the importance of diversity in model service providers for meeting the needs of the community when providing AI conversation services. T

Kimiko is a private AI notepad for meetings and notes, for professionals who work on Apple silicon Macs and Windows 11 PCs. During a call, Kimiko records the microphone and the computer's audio, so it works alongside Zoom, Microsoft Teams, Google Meet and other call apps without adding a bot to the meeting. People write notes beside the live transcript, and their notes help shape the summary. Live speaker labels keep up to eight remote voices apart. After the call, Kimiko writes a summary and s

BuilderStudio is a free native MacOS app for building app projects locally with built-in MCP, OpenRouter integration, reusable Skills, source editing, terminal workflows, app previews, source packaging, and deployments via control plane. FEATURES • Build with an AI Coding Agent: BuilderStudio gives you an AI-powered coding workspace designed to help you move from idea to working product faster. Instead of starting from a blank editor, you can describe what you want to build, refine the result,

Bund AI is an AI agent for sales and customer support. It qualifies leads, books calls, issues refunds, changes orders, and looks up accounts directly — then hands off to a human teammate when a conversation needs one. It runs on the web widget and by email, deploys in under a day, and offers a free plan alongside paid tiers for growing teams. The core product is open-source (AGPL-3.0) and model-agnostic, routed through OpenRouter.

Atomic Agent is an open-source, local-first AI agent runtime. It runs on your own machine on top of llama.cpp, drives your desktop — browser automation, file editing, shell commands — with dangerous actions gated behind an approval step, and keeps sessions, memory, and traces on your own disk. It works with local models as well as OpenAI-compatible and OpenRouter providers. CLI and TUI, macOS and Linux, with a Windows developer preview. MIT-licensed. GitHub: https://github.com/AtomicBot-ai/atom

Agentsmith makes it easier for non-technical prompt authors to write templated prompts and hand them off to engineers seamlessly through GitHub. - author flexible and re-usable prompts with jinja syntax - our editor interface automatically extracts typed variables - built on top of OpenRouter, easily test or switch to any LLM - syncs prompts as template files to a pull request in your GitHub repo - sync goes both ways, you push changes to git if you prefer - the sync engine also generates types

OceanToken is an AI model platform that gives developers and teams access to 500+ models across text, vision, image generation, video, speech, transcription, embeddings and more. Users can discover and compare models, start with pay-as-you-go access, and move to enterprise pricing for higher-volume workloads. OceanToken focuses on making advanced AI models easier and more cost-efficient to use, with selected model pricing up to 40% lower than comparable OpenRouter rates. It also supports managed

Atomic Agent is an open-source AI agent runtime that runs locally on a user's own machine, built on top of llama.cpp. It performs desktop tasks such as browser automation, file editing, and shell command execution, with sensitive actions gated behind an approval step. Sessions, memory, tasks, and traces are stored on the local device. It supports local models as well as OpenAI-compatible and OpenRouter providers, and includes a persistent memory system and durable task scheduling with cron and w

PostClaw is an AI-powered social media management platform for solo founders, creators and SMB marketing teams. It combines trend discovery (73 live sources), AI content generation with brand-voice training, multi-platform publishing (17 platforms: 11 social networks, 6 blog engines), scheduling, analytics, and a no-code visual workflow builder with 14 automation tools. Teams can use built-in AI models or bring their own API keys (OpenAI, Anthropic, OpenRouter and others) with no vendor markup.

Noah's Arch DBChat is an on-premise AI desktop application for businesses that need to query their data in plain Arabic or English — without sending it to the cloud. Connect SQL Server, Oracle, MongoDB, REST APIs or Excel files, then chat: the AI translates your question into a deterministic, read-only SQL or MongoDB query and explains the result. Documents work the same way — drop in PDFs and contracts, ask questions, compare versions, generate reports. PII is auto-redacted before any cloud cal

Keln is a reliability layer for open-weight language models such as DeepSeek, Kimi, Qwen, GLM and gpt-oss. Built for teams that run open models in production. You call one OpenAI-compatible endpoint at one published price per model, and Keln routes each request across a pool of GPU providers that it verifies continuously. Slow routes are raced and billed once, a stream that dies part way continues on another node, and nodes serving degraded output are removed until they pass again. Keln also a

Most AI tools put the model at the centre and wire your systems into it. Holiday flips that: your business - its systems, records and permissions - sits at the centre of a custom single-tenant AWS environment, and the AI models you choose (ChatGPT, Claude, OpenRouter) plug into it. Built for mid-size and larger companies. Staff get Business Chat across connected systems like Outlook, HubSpot, Procore, Xero and OneDrive, with permission-aware answers. Agentic Managers take on defined jobs with re

EUrouter is a European AI routing service that provides a single API endpoint to access 100+ of the best AI models, including Mistral and other leading providers. All routed through European infrastructure. Built for European teams that need GDPR compliance without sacrificing model choice, EUrouter runs entirely on EU infrastructure with EU data residency as the default configuration. The OpenAI-compatible API format means existing applications can switch from OpenRouter or direct provider API

N-Recruit is an applicant tracking system (ATS) built in Brazil for people who recruit on behalf of clients: HR consultancies, recruiting agencies, headhunters and independent recruiters. It replaces spreadsheets, personal WhatsApp and manual LinkedIn work with one place for jobs, candidates and interviews. Each job has its own Kanban pipeline with custom stages. Clients follow the process through a client portal and receive blind CVs branded with the agency's logo. AI does the first resume scr

Accelerate your AI SaaS development with Vibe44, the 100% agent-native Next.js boilerplate. Stop wasting valuable time on repetitive infrastructure setup and focus on building the core features that will drive revenue. Vibe44 provides a comprehensive, production-ready foundation designed to help you ship high-performance SaaS and AI-powered products in days, not months. • Rapid Development: Skip months of tedious coding with a starter kit engineered for AI agents. • Full Stack Features: Includ

DeepState is a desktop investigation analysis platform for OSINT analysts, investigative journalists and corporate security teams. Everything in a case (people, organisations, events, documents, social posts, locations, blockchain wallets) lives as a typed node on one infinite canvas, joined by reasoned connections like funds, controls and contradicts, with a timeline, narratives and full-text search. Beside the board sits an AI agent with 70+ research tools: web search, page capture, the Wayba

We started LinkFilm in early 2026 with a simple belief: creative industry intelligence will be multi-model. No single model will win every task, and the frontier will move rapidly. That freedom is critical infrastructure for the creative industry. AI has become the single largest driver of economic growth in the world, and inference is quickly becoming the largest line item for every creative company. We're building the world's best canvas for creatives, designed around your freedom. There's no

Zeus-code is an innovative AI coding agent that emphasizes code reuse over generation, offering a more efficient and reliable approach to software development. By vector-searching both private GitLab repositories and public modules, it composes full systems using existing, tested code, thereby reducing bugs and enhancing organizational knowledge with each deployment. Key Features and Functionality: - Fine-Grained Vector Search: Indexes functions, modules, and tests at an appropriate granularit

Inferagate is an open-source AI gateway designed for production teams seeking enterprise-grade control over their AI deployments. It serves as a centralized control layer, enabling seamless integration with various inference providers, efficient model management, and comprehensive oversight of AI operations. By offering a unified interface, Inferagate simplifies the complexities associated with managing multiple AI services, ensuring consistent performance and security across applications. Ke