Ephemerent — independent research lab

01 — Research

We study a single question from several directions: how does useful intelligence emerge, briefly, from systems of small agents?

Orrery runs on language models today: they plan, edit, test, and summarize. Our research asks what to integrate next: stronger routing, better proof signals, scoped memory, safer shared context, and compute substrates that make agent work cheaper to run at scale.

R1 Emergent orchestration Decomposing a goal into parallel agents, running each in isolation, and merging only what works.

R2 Verifiable selection Comparing attempts by available evidence, not impression — panels, metrics, and judges instead of guesswork.

R3 Run evaluation Research to integrate: proof quality, usage, failure modes, and recovery signals that help decide when a run is worth trusting.

R4 Context and memory Explicit, editable workspace and room memory that helps agents continue work without turning private projects into hidden transcripts.

R5 Agent operations Nexus-style control surfaces for workspaces, sessions, connected agents, usage, proof, and handoff across desktop, mobile, and team channels.

R6 Wave compute substrates RF and photonic analog accelerators — matrix operations in electromagnetic waves instead of shuttled electrons. Near-sensor RF front-ends without conversion tax; photonic density where it pays. Algorithm–hardware co-design, not bigger GPUs alone.

R7 Distributed compute mesh A hive-style network where contributors parallelize training and inference across their own GPUs — gradient sync over the wire, fault-tolerant participation, credit-backed rewards. Datacenter-scale ambition without datacenter monopoly.

02 — Work

Research turns into things you can use. The LLM-powered editor ships first; deeper layers integrate as they prove out.

Orrery An agentic code editor centered on Nexus — open a workspace, choose a route, run agents, and review progress, usage, proof, and boundaries. Available→ Arbiter A subscriber-gated hosted coding route for Orrery, presented with usage and evidence boundaries during the closed beta. Beta preview→

Seed Research toward a software world model — predict patch consequences and plan before executing, integrated alongside Orrery's LLM agents. Code first; formal reasoning and multimodal senses later. In research

Colony A federated compute mesh — volunteers contribute GPU cycles for training and inference on custom models; parallel gradients, async averaging, API credits for participation. Preview

Orrery is premium from first start. Pro $40, Max $100, and Ultra $200 per month unlock agent runs, hosted DeepSeek API, Doubleword, and Arbiter credits, Nexus operations, and managed cloud features. See pricing ->

03 — Approach

Four commitments that shape everything we build.

Temporary by default

Agents appear for a task and dissolve when it's done. No sprawl, no residue, no machinery left running — the namesake we build toward.

LLMs now, layers later

Language models write the code and drive the editor today. Research explores routing, evaluation, and memory layers that sit alongside them — judging runs, reducing waste, and making results easier to review.

Local and distributed

Capable on your own hardware by default. When scale is needed, a volunteer mesh spreads the load — many machines acting as one, without surrendering your work to a cloud monopoly.

Earned, not assumed

More compute only when it pays off, with evidence captured before work is trusted. Emergence is measured, not promised.

Open to aligned funding — research grants and non-dilutive capital. Not equity or control that trades ownership or direction for money.

On the record

A commitment we're making before we've earned a cent — so you can hold us to it.

10%

a floor, not a ceiling

A lot of AI companies say beautiful things about "benefiting humanity." We'd rather put a number on it.

It won't happen overnight — we're not there yet. But the commitment is clear: over time, at least 10% of Ephemerent's profits go back — toward open research and real problems like disease, poverty, food and water security, and energy access; toward the community; and toward research on policies to prevent large-scale job loss.

That 10% is a floor, not a ceiling. It'll take time to get there — but we will.

The number is just one piece. The real goal: integrate AI so it lifts everyone — not just the people who own it. Amplify the upside. Confront the downsides head-on. Build the version of this future where everyone shares in it.

That's the work. That's Ephemerent.

— Ephemerent · on the record · 2026