Datalox is not an "AI cytometry assistant" and not an "agent framework." It is a programmable execution and data layer for biological experiments. Agents become clients of the runtime.
Keep compute, state, meaning, and reasoning as separate layers with explicit boundaries.
When compute and reasoning are mixed together, systems become hard to port, inspect, and reproduce.
The runtime executes science. The state tracks experiments. Agents reason on top through a stable API.
Each concern has one job and one source of truth.
Node-graph execution for transformations, clustering, gating, and stats with deterministic outputs and caching.
Experiment structure that tracks samples, conditions, manual gates, populations, and full analysis history.
Biological entities convert measurement space into interpretable objects such as populations, phenotypes, and comparisons.
Agents consume structured signals and context to generate hypotheses, explanations, and next-step suggestions.
A portable scientific runtime for biological experiments, designed to be agent-agnostic.
Raw measurements only: FCS files, microscopy images, sequencing counts, protein sequences.
Operation graph for load, compensate, transform, cluster, gate, and compute statistics.
Track scientist actions, then map numbers into populations, marker profiles, and phenotypes.
Emit structured evidence like frequency changes, marker shifts, gate shifts, and outlier scores.
Store measurements, no interpretation.
Deterministic compute engine.
Samples, gates, conditions, history.
Population and phenotype objects.
Structured evidence, not conclusions.
Stable tool interface for any agent.
Reusable analysis workflows.
Interpretation, hypotheses, suggestions.
Scientist and agent collaborate in the loop.
From measurement to interpretation, each stage is explicit and replaceable.
Deterministic computation, reproducibility, caching, and scalable execution for scientific workflows.
An explicit experiment graph containing samples, conditions, gating trees, and derived populations.
Compile raw outputs into reusable signals: PopulationChange, MarkerShift, DistributionShift, GateShift.
Expose runtime operations through a stable tool surface that any agent can call.
The core system is infrastructure. Agents connect through the API, so reasoning can evolve without rewriting scientific execution.
We are building portable scientific infrastructure for agent-assisted biology. If you want to integrate your agent or pilot this in real workflows, reach out.