PhoneVoice proves the B2B voice stack
Call handling, audio streaming, WebSockets/SSE, transcription, routing and business integrations keep us grounded in real telephony production constraints.
We don't just consult — we ship and operate our own products end-to-end. Four are shown here; more are on the way.
AI voice agents for enterprises: qualification, routing and call handling, real-time audio, CRM integrations and human supervision.
Voice-first AI assistant. Real-time voice, email, calls, web agent, multi-LLM. Cloud commercial + open-source self-hosted edition.
Task orchestrator for AI coding agents. Workspace, claims, runs, and a metered AI proxy. CLI + SDK open source, cloud is paid.
Universal linter with AI-powered code review. One CLI for ESLint, RuboCop, Ruff, Biome, Stylelint and more. Open source.
These are not portfolio mockups. They are Osmove products with real constraints: auth, billing, observability, support, open-source releases and ongoing roadmap decisions.
Call handling, audio streaming, WebSockets/SSE, transcription, routing and business integrations keep us grounded in real telephony production constraints.
Realtime speech, calls, web agents, local/self-hosted mode and device firmware make Twoody the reference project behind our voice and AI delivery.
Workspaces, claims, runs, CLI/SDK and paid cloud features exercise the same multi-tenant SaaS patterns we use for client products.
A public npm package with AI code review, multiple linters and CI ergonomics gives us hands-on feedback from real developer workflows.
Each product follows the same pragmatic playbook: short framing, readable architecture, progressive delivery, observability and continuous maintenance.
We bring the same level of rigor we use on our own products to client work — voice agents, hardware, AI-heavy SaaS.