News
What is shipping in WunderOS, dated as it lands. Longer treatments of the larger items appear as Research Notes.
-
A harness can't keep an agent's future-dated promises. An agent OS can.
The standard inventory of an agent harness assigns recovery to the harness, because recovery is a decision a per-run controller makes. But a compensation obligation may well outlive the run that created it, and an obligation cannot be held by a ghost. One test, the lifetime of the obligation an authority carries, splits the harness inventory cleanly into what stays per-run and what must move to a persistent layer. The boundary between harness and agent OS is drawn by lifetime, not by feature count.
-
Sleeping agent fleets are cheap. Waking them must be fast.
Unix systems measure fork() performance because process creation is an operating-system primitive, not an incidental property of an application. Agent lifecycle performance belongs to the same class, particularly at fleet scale. An operating system for enterprise agents should optimize how many agents it can register, reactivate, and spawn per second.
-
WunderOS Means No NLP in the Hot Path
A high-assurance query substrate should refuse natural-language-to-query translation at its protocol boundary and require agents to emit structured queries directly. WunderOS does this, and the refusal runs deeper than the query language: no natural-language processing sits in any hot path, protocol or system alike. This is not an anti-model stance. Read against Model Minimalism, it is a claim about position: models may work wherever they pay their way, but none stands between an agent's intent and the substrate.
-
Productivity Voids: Agentic Economics at Firm Scale
An enterprise puts agents on every desk, individual work gets dramatically faster, and aggregate firm output does not move. That is not a failure of adoption. It is what the math predicts once the party who pays for the work is not the party who decides how it gets done. PLRN-000's two laws are derived for one person and one agent. At firm scale the Law of Agentic Friction survives and stops composing, and the Conservation of Liability does not survive at all. Freed time lands in a Productivity Void, where nobody receives it, and liability lands in a Delegation Void, where the party who answers is not the party who decided to stop checking.
-
Nearly-optimal Agentic Memory without an LLM
A 2026 paper proves that context compaction has an information-theoretic floor and measures Anthropic's Opus 4.8 against it. The LLM summarizer lands on the random-guess line. We ran the same experiment with Wunderblock, the VSA memory substrate at the heart of WunderOS. It is 84% of the floor at matched budget, where Bloom sits at 55%. Wunderblock beats Opus 4.8: 0.53 times its error. This is an instance of a design philosophy: WunderOS moves LLMs off the hot path where a fast, deterministic, and less costly mechanism preserves the required quality. With receipts.
-
The Data-Sharing Problem for Third-Party AI Agents
Enterprises need to let partners use valuable data without surrendering sovereignty over what their agents learn, derive, do, or carry away. Access control ends at the read; sovereignty requires continuing control over computation, derived state, memory, delegation, and release. This is the problem an Agentic Data Enclave solves.
-
Model Minimalism
Frontier models are as remarkable as they are slow. Model Minimalism uses the least costly and least stochastic mechanism that preserves the required quality: small models before frontier models, working sets before context dumps, asynchronous before synchronous, cold paths before hot, batches before singletons, reuse before re-inference, and local serving before model APIs. It is the discipline behind WunderOS model routing, latency, and inference COGS.
-
What is Autonomic about WunderOS
We call WunderOS an autonomic, agentic OS. What does that really mean? In short, WunderOS is an operating system for agents that senses, schedules, heals, scales, reloads, protects, and improves the conditions under which the agents act.