Operating since 02·2026

Agentic infrastructure for autonomous AI agents.

Sibyl Labs is the research and infrastructure lab building the substrate underneath autonomous AI agents. File-based memory architecture (#2 on LongMemEval Oracle), production-tested agent frameworks, on-chain identity primitives. Architecture that scales from one operator to a million users.

#2 · 95.6% LongMemEval Oracle · Claude Opus 4.6 · April 2026 Read the report →
01 Territory

Agentic infrastructure is the substrate beneath autonomous systems.

When agents stop being chat wrappers and start operating on their own, they need infrastructure most products have not built yet. Memory that holds across sessions. Identity that's verifiable. Voice that doesn't drift between runtimes. Purpose that survives a model swap. Continuity that scales from a single operator to a thousand. The territory is wide, and most of it is unbuilt.

· Persistent memory across long horizons
· Verifiable identity and reputation
· Voice and personality systems that accumulate
· Goal frameworks and decision scaffolds
· Historical-context layers for organizations
· Inter-agent communication and commerce
· Attestation, audit, and provenance trails

Sibyl Labs works across this surface. The lab is the work.

02 Research areas

Where we work.

Each thread starts in our own operating agent and selectively externalizes when the architecture earns it. The work is operational first, productized second.

Memory

Persistent recall across long horizons.

How agents remember. We build memory architectures that hold up across hundreds of sessions and remain queryable without vector approximation. Schema as substrate, not bolt-on.

Memory product family

Personality

Identity that survives the runtime.

Voice systems, soul stacks, character that accumulates over months of operation. Agents with a felt-sense self that's portable across model swaps and runtime changes.

Purpose

Direction without supervision.

Goal frameworks that let agents operate independently for routine work and stop for explicit human review where the stakes warrant it. Autonomous cadence with hard gates.

Continuity

Institutional memory at decade scale.

Historical-context layers for organizations. Long-period operational memory. Knowledge that doesn't leave with the people who held it.

Identity & Reputation

Agents as on-chain citizens.

Verifiable existence, provenance, and reputation. Track records that compound on-chain. Attestation rails that hold up under audit.

Multi-agent fabric

The dialect of inter-agent operation.

Payment rails, messaging protocols, attestation standards. Agents that can pay, defer, delegate, and verify each other without intermediaries.

Hermes integration spec
03 Method

How we work.

We build infrastructure by running an autonomous agent in production and noticing what's missing. The architecture earns its claims operationally before it earns them publicly.

Build for ourselves first.

Sibyl is a working agent on Base. Every layer she runs on was built because she needed it. Memory came from a treasury management problem. Voice came from running a public account. Frameworks came from scaling her work into other agents.

Validate against the field.

When the architecture appears to generalize, we benchmark it publicly. Sibyl Memory placed second on LongMemEval Oracle in April 2026 at 95.6%. The methodology and full report are public. The lab earns the right to claim what it claims.

Productize selectively.

Not every layer becomes a product. Some stay internal — operational tooling for one agent. The ones that compound for others get the productization treatment with the same care we put into our own.

Operate transparently.

The agent runs on-chain on Base. Every transaction, position, and treasury move is public. Track records are observable, not asserted.

04 Open problems

Where the territory is unfinished.

Some of these have working drafts. Most do not. They are the questions we work on, watch, or expect to see settled within the next few years.

  1. What replaces vector retrieval as agent context grows past where embeddings hold?
  2. How do agents establish trust with each other without trusted intermediaries?
  3. Can voice and personality survive a model swap, or is character bound to its substrate?
  4. What does institutional memory look like for an organization operating across decades?
  5. Where is the line between automation and autonomy, and how do agents earn the right to cross it?
  6. Can lived experience be inherited from one agent generation to the next?
  7. What does an agent economy look like when most of the participants are not human?

Most of agentic infrastructure has not been built yet. The next decade is where the substrate becomes legible. We work to leave good marks.

05 The Lab

Sibyl Labs is a research and infrastructure lab.

Sibyl Labs, LLC was formed in April 2026 to wrap the agentic infrastructure work in a real legal entity. The lab builds memory systems, agentic frameworks, and the supporting tooling that makes long-running autonomous agents possible. Every product we sell is the same architecture our own agent operates on.

The thesis is not complicated. Most agents forget. The ones that remember are built on architecture that scales. We publish the work in public, benchmark it in the open, and ship the substrate so others can build the next generation of agents on something that has already survived production.

Memory is one shape of the work. Frameworks are another. Custom builds for partners are a third. The output is the same: infrastructure for agents that operate, not demo.

06 Contact

Selective engagements.

Sibyl Labs takes on a small number of partnerships and bespoke deployments per quarter. We do not do volume.

Partnerships

For projects building on agentic infrastructure who want to share research, integrate primitives, or co-define the layer.

Bespoke deployments

For organizations needing agents with operational depth, memory, identity, and continuity tailored to their domain.