Search results for OpenRole

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.

Aserto helps developers build secure applications. It makes it easy to add fine-grained, policy-based, real-time access control to applications and APIs.Aserto handles all the heavy lifting required to achieve secure, scalable, high-performance access management. It offers blazing-fast authorization of a local library coupled with a centralized control plane for managing policies, user attributes, relationship data, and decision logs. And it comes with everything you need to implement any authorization model, including RBAC, ABAC, and ReBAC. Take a look at our open-source projects: - Topaz.sh: a standalone authorizer you can deploy in your environment to add fine-grained access control to your applications. Topaz lets you combine OPA policies with Google Zanzibar’s data model for complete flexibility. - OpenPolicyContainers.com (OPCR) secures OPA policies across the lifecycle by adding the ability to tag, version, sign, and test these policies.

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/atomic-agent Site and docs: https://atomicagent.io

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 hosting and deployment options for teams with stricter data or infrastructure requirements

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 ensure correct prompt compilation at build-time

HostAiHub is managed hosting for private AI agents. Deploy OpenClaw, Hermes or n8n to your own SSL-secured subdomain in about three minutes. You bring your own model key from Anthropic, OpenAI, OpenRouter, DeepSeek or Gemini. HostAiHub handles servers, updates, monitoring and daily backups. Plans start at $7/month, with yearly and lifetime plans also available. It suits solo founders, agencies and small teams who want private, always-on AI agents and automations without DevOps work.

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 webhooks. Atomic Agent is distributed under the MIT license and provides a command-line interface and a terminal user interface. It runs on macOS and Linux, with a Windows developer preview.

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 call. The model runs fully local via Ollama, or cloud via OpenRouter — your choice. Built for UAE data-residency requirements.

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. Flat pricing with a free tier; paid plans at $20 and $50 per month. Interface available in 12 languages.

Silk is a desktop AI agent for Mac and Windows, built for solo entrepreneurs. ChatGPT gives you the answer. Silk does the job. Ask for a lead-magnet ebook and you get a branded PDF in your Work folder, not a wall of text. Silk sees your screen, talks with you, and works inside the apps you already use: WordPress, your email, spreadsheets, your funnel builder. Hand it an hour of work and walk away, schedule daily jobs, or send it tasks from your phone over Telegram. It runs on the ChatGPT or Claude plan you already pay for, or any model through OpenRouter. 9 USD a month, first day free.

Kiju turns an idea into an episode you can post — a vertical drama, a series or a short film. You start from an idea or a script. Kiju's AI crew writes the episode, casts the characters, draws and voices the storyboard, films each shot with today's video models (Seedance, Veo, Kling, Wan and more) and cuts the episode, ready to post. You make every call, and you see the price of every take before you press. The AI models run on your own account (OpenRouter today), at the provider's prices, with no Kiju markup. Every shot keeps its provenance. Kiju runs today on Macs with Apple silicon (macOS 13 or later), in English and French. Your first episode is free; then €29 a month.

OpenReco is an open-source photogrammetry and reality-capture platform for generating 3D models, point clouds, textured meshes, and terrain data from photographs. Designed for researchers, surveyors, drone operators, developers, and creators, OpenReco provides image alignment, camera calibration, sparse and dense reconstruction, mesh generation, and texturing in a transparent, extensible alternative to commercial photogrammetry software.

42agents runs AI agents (AI chatbots) on WhatsApp through Meta's official WhatsApp Cloud API. With coexistence, the business keeps using the same number in the WhatsApp Business app and WhatsApp Web while the agent replies through the API. The agent understands free text and voice notes, answers from the business's knowledge base, qualifies leads, books appointments, and hands off to a person when needed. The team works in a shared inbox, and AI runs on the customer's own key (OpenAI or OpenRouter). 42agents is white-label: marketing agencies, AI agencies, and software houses resell it under their own brand. Pro is USD 39 per account per month; Premium is USD 117 per month from 3 accounts. 7-day free trial.

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 APIs by changing a single line of code. Key capabilities: 100+ AI models from 10+ providers, routed through EU infrastructure EU data residency by default GDPR-native architecture (zero US infrastructure dependencies) European AI routing with automatic failover Real-time usage monitoring and cost tracking API key management with per-key spending limits

Morphy is a desktop workspace for developers and builders who work with several AI coding agents. Claude Code, Codex, Grok, GitHub Copilot, Gemini (Antigravity), OpenRouter and local Ollama models each run as a chat card on an infinite canvas, signed in with the plans the user already pays for. Every chat shows the agent's steps, any turn can be undone, and a conversation can continue with another AI when one hits its usage limit. Each project gets its own frame, and focus mode tiles the chats you need on one screen. Agents build cards on request (live trackers, dashboards, small internal tools), and flows chain chats with arrows so one agent's answer goes to the next, on a schedule if wanted. A built-in browser, terminal and file viewer sit beside the chats. Windows, Mac and Linux. Free; Pro is $9 a month.

Directionally Local is an open-source coding agent harness (Autopilot) plus everything it needs to run on hardware you control. Run npm install -g directionallylocal, then dl. It sets up on your laptop or on your own server over SSH. Inside any GitHub repo, dl opens an agent session that keeps running when you leave. dl run "..." hands off a task that runs in its own sandbox and comes back as a pull request. Subagents and tasks run in Hotcell sandboxes: Docker, Firecracker or Apple Virtualization microVMs. Your real API key never enters a sandbox; each one gets a short-lived, spend-capped token. Bring any provider: OpenRouter, DeepSeek, OpenAI, Ollama and 20+ more. Serverless Objects adds Workers-compatible durable state for previews. MIT and Apache-2.0.

Swift Outbox is AI cold email software for agencies, freelancers and B2B sales teams. Its built-in AI, Swift Pilot, reads up to 10 pages of each lead's website and writes a one-to-one email around something real it found, not a template with a first name dropped in. You can also connect your own OpenAI, Anthropic Claude, Google Gemini or OpenRouter key. Approve, edit or rewrite each email yourself, or let a campaign send automatically. Emails go out from your own Gmail, Google Workspace, Microsoft 365, Zoho or SMTP mailboxes, with mailbox rotation, daily limits and sending windows, and every reply lands in one inbox. Also included: an email verifier that checks real mailboxes (paid plans), a do-not-email list, open and click tracking, team roles and one workspace per client. Free plan available, no card required. Not included: follow-up sequences, a lead database and mailbox warm-up.

AISKOOL puts a paid community and its courses in one place, with an AI host built in. Creators get a community feed, real-time chat and DMs, an events calendar with RSVPs, points and leaderboards, and drip-fed courses with progress tracking, quizzes and completion certificates. Describe a topic and the AI course builder drafts modules, lessons and quizzes that you edit before publishing, or turn an uploaded document into a course outline. The AI host answers member posts in the feed and tutors members one to one in DMs, using the creator's courses and the documents, links and notes added to its AI Brain. It welcomes new members, nudges people who stall on a lesson, and remembers where each member left off. Documents can be limited to a paid tier so paid material stays paid. Members pay through Stripe into the creator's own Stripe account. Stripe's processing fee comes off first and AISKOOL keeps 4% of the rest. Creators can bring their own AI keys (OpenAI, Anthropic, Gemini, OpenRouter) so AI use does not count against their allowance. Each community lives at aiskool.co/c/your-name; the Agency plan adds white-label communities on a custom domain.

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: Includes pre-built authentication, payments, teams, dashboard, and premium UI components. • AI Integration: Features an MCP server for seamless AI agent documentation querying and integration. • Cost Savings: Avoid an estimated $36,000 in engineering costs and over 480 hours of development time. • Scalable Architecture: Built with a robust architecture that ensures your application can scale. • Key Technologies: Leverages Next.js, React, Supabase, Stripe, and integrates with leading AI models like OpenAI, Claude, Gemini, DeepSeek, and OpenRouter. Vibe44 is trusted by builders who want to move fast and launch unlimited applications with a single purchase. Get lifetime access and start shipping your next AI SaaS this weekend.

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 monthly credit-reset pressure and none of the AI models that cost 20–60% more elsewhere. That’s why we offer two types of creative plans. - Free Plans for individuals and learners. Only a 5% platform fee, Transaction fee: 2.9%. - For agencies and enterprises. $5 per month, billed annually. Use your own API platforms: Replicate, OpenRouter, Fal.ai, (also connect own local PC models—coming soon) Our mission We envision a healthy and transparent generative AI ecosystem. No single model or tool should become the default simply through inertia, switching costs, or bundling advantages—it should earn that position by being the best choice, openly and repeatedly, in a market where creators can compare, switch, and choose freely.