Overall Product Roadmap#

The Ultimate Vision - By the end of this roadmap, a robot manufacturer (our OEM partner) should only worry about sensors, motors, and batteries (and the interfacing software layer). A robot buyer (our customer) should only be concerned with use-cases that the robot should be deployed to solve. Every ounce of intelligence, from how the robot navigates space to how it executes a mission or communicates with its user, will be a “Receipe/App/Agent” downloaded from the EMOS Library, backed by a world-class enterprise support infrastructure that makes deploying a new robot as simple as unboxing a phone. Sophisticated robot buyers would be able to create their own “Agents” trivially in an Agent Builder.

EMOS Roadmap Towards the “Android of Robotics”#

Shipped in 2026

Foundational Runtime & Distribution

  • v0.5.0 — “The Embodied Operating System” (Mar 2026) — First unified open-source release bundling EmbodiedAgents + Kompass + Sugarcoat under one CLI. Container and native install modes. 20+ recipes. Auto-generated web UI. llms.txt published.

  • v0.6.0 (Mar 2026) — Built-in local models across LLM / VLM / STT / TTS / Vision (Qwen3, Moondream2, Whisper, Kokoro, DEIM). Zero-config fallback_to_local() for cloud→local failover. Native install hardening. CLI self-update.

  • v0.6.1 (Mar 2026) — pixi install mode: rootless, Docker-less, works on any Linux distribution — including Ubuntu 22.04 where ROS Jazzy has no official release.

Zero-Touch Enterprise Onboarding

  • v0.7.0 — “The Agentic Release” (May 2026) — Dashboard pairing code, QR onboarding, mDNS discovery, TLS with fingerprint verify. Hardened systemd unit via emos serve install-service. Licensed install mode with revocable pairing tokens — the plumbing for the future Monetization Engine.

  • Live System Graph in the dashboard (v0.7.0) — real-time visualization of the running recipe’s component graph.

In Flight — Q4 2026 → Q1 2027

Deployment & Enterprise Enablement

  • HAL Plugin Library growth — the framework is shipped across all 4 core repos; the ongoing work is adding partner-specific plugins per OEM.

  • Recipe Registry (beta) — the emos pull / run / info lifecycle and recipe-catalog service are already live; formalising into a public beta.

  • Course + Demo Showcase — video course on recipe development in collaboration with INRIA, alongside the existing documentation and tutorials, showing deployment and demonstration on real robots.

  • Simulation Ecosystem — ready-to-use, optimized virtual environments for testing and validation of EMOS recipes, in collaboration with HuggingFace and Lightwheel.

Hardware Compatibility

  • Expanded Embedded Compute Support — beyond AMD Strix Halo, NVIDIA Jetson, Rockchip, RPi5 (done). Black Sesame and Chengdu Aplux with Qualcomm in the pipeline.

Q2 2027 & Beyond — Automation App Economy & Democratization

Goal: Establish the first-mover ecosystem. Unlock the robot application economy by democratizing development further, launching a public marketplace, and establishing the security and commercial frameworks required for wider adoption.

Democratization & Standardization

  • GUI-Based Agent Builder — Visual orchestration tool for building recipes (apps / agents) while keeping the Python scripting option as the advanced path. The bulk of recipe development effort should go into physical verification; code should be cheap (or free). Customers most likely to deploy general-purpose robots are entities managing large human workforces in the physical space. They aspire to become robot managers alongside people managers — but they are not structured like tech development companies, so they require commodification of the software layer.

  • Standardized Deployment Protocol — Formalising the shipped manifest.json + lifecycle into a unified industry standard for how robots identify themselves, report health, and receive “Apps” — ensuring a consistent experience across heterogeneous fleets and different OEM brands.

  • Automated Recipe CI — Continuous Integration pipelines for automated recipe validation in real environments to ensure behavioral stability. Robotics CI in the real world is hard to scale and requires physical verification that simulation-based testing does not cover. We are starting with pipelines built alongside data-collection partner Heex Robotics, configurable by any recipe developer.

Marketplace & Monetization

  • Open EMOS Registry — Public repository for publishing, versioning, and distributing recipe templates and ready-to-deploy recipes developed by third parties.

  • Monetization Engine — Financial rails for the ecosystem: licensing management and micro-payments for specialized recipes deployed through EMOS. (License-key + pairing-token infrastructure has already shipped in v0.7.0 as prerequisite.)

Trust, Safety & Compliance

  • Formal Recipe Verification (paid enterprise capability, in collaboration with an Inria research team) — A verification compiler for EMOS recipes. A Recipe today is a Python program plus an event-driven graph whose runtime behaviour depends on the interaction of components, fallbacks, and event handlers. The verifier statically analyses a Recipe against its declared behavioural intent — reachability of goal states, absence of deadlock and livelock under event chains, preservation of safety constraints across fallback branches, and bounded resource usage — flagging violations before deployment. Positioned as a paid-tier capability inside the enterprise licence and integrated into the Automated Recipe CI pipeline.

  • Enterprise App Governance — Comprehensive risk-management framework combining automated security auditing and commercial indemnification structures. Ensures that third-party Apps sold on the Marketplace meet enterprise legal standards, de-risking adoption for clients.

  • Safety Evaluation — Deterministic validation processes for new Apps, verifying adherence to constraints and boundary conditions before deployment. Complements Formal Recipe Verification with runtime-shape evidence.