RUNTIME LABS
About
Runtime Labs anchors language models in time, location, and context. Our work is grounded in two convictions: grounding language models in event structure increases reliability and utility of model outputs, and time is a foundational primitive for memory, planning, and coordinating between natural language intent and physical action.
Óra is our first release. It serves as a scheduling engine and planning environment where natural language conversations, memory, and events coexist on a shared timeline. To get started, sign in with Óra to create events, manage context for conversations, and store memories across your personal and professional life.
Runtime Labs is building toward a class of systems where language models function as time-aligned collaborators capable of reasoning across past, present, and future state. In this way, we build environments where memory and planning can be unified within a single coherent interface.
Research
We develop infrastructure that enables models to reason in time, maintain persistent context, and operate on structured representations of events. This includes systems for temporal indexing, memory persistence, and context retrieval that allow models to interpret past activity, manage future plans, and respond coherently within an evolving timeline.
The goal of research is to develop and refine a stack built for planning and scheduling, where correct behavior depends on understanding temporal relationships and maintaining shared contextual state with the physical environment.
Product
Óra is built on this infrastructure as an Integrated Planning Environment (IPE) where models can operate on persistent, time-structured state rather than isolated prompts. Conversations and notes are preserved as timestamped event commits anchored in time and location, a general-purpose version control for life events and conversations.
It is an environment for planning and managing your schedule through natural language conversations and commands. Models interpret intent, propose events for preview and approval, and update your timeline. This places users in control of when and where events are preserved—with photos, location, and links stored—to enable a persistent system state that maintains continuity across past activities and future plans.
Agency
Agency emerges from the strength of our predictive models and our ability to translate intelligence into actions that shape the future distribution of decisions available to us.
We view the advancement of technology as a sacred responsibility; our mission is to design new tools and environments for human-computer interaction aligned with our goals and serving as a source of human empowerment.
Values
- We commit to clear objectives and build for the long-term, avoiding short-term optimization and cycles.
- We pursue truth rigorously and treat others with respect.
- We allocate time, capital, and compute deliberately.
- We exercise discipline and restraint in design, release, and outreach, while maintaining urgency in daily execution.
- We develop tools that empower humans—strengthening agency, judgment, and control over how work gets done.
- We adapt quickly when diminishing returns in product or research become evident.
- We maintain a respectful environment where criticism and feedback are treated as essential inputs to invention.