Part I · Overview

A nervous system for coding agents.

Single-purpose organs give an agent an accurate map of a codebase, memory that outlives the session, verification gates that refuse to go green by skipping work, and one routed path to private inference. Each organ is useful alone. The composition is worth more than the sum.

Public binary distribution is pending. Explore the documentation now. Checkout installation requires existing repository and release access.
Fig. 1   Organ map, sagittalTable 4.0 ↗
Cortex 01 Prefrontal executive / orchestrationTypeScript · Web :3333 · cortexd :4319
Thalamus 02 Sensory relay / model routerRust · HTTP / SSE · :18000

Intelligence · Verification · Knowledge
Compute behind the relay, never a hard-coded host

Fig. 2   Task lifecycle, five stages Full architecture ↗

  1. 2.1

    Orient

    Provision a seat, render the memory block and read the repository's structural maps.

  2. 2.2

    Retrieve

    Search anchors, trace call tracts and recall memory. Remote retrieval goes through the Knowledge plane.

  3. 2.3

    Execute

    Reason over the Intelligence plane, with session affinity for KV-cache reuse.

  4. 2.4

    Closeout gate

    Verify structure and concerns. The live System 1 rubric runs only after explicit opt-in.

  5. 2.5

    Consolidate

    Record outcomes, refresh maps and consolidate memory through cns curate.

Part II · Method

Rules the organs
are held to

  1. One organ, one faculty.

    Bounded repositories and independently verifiable responsibilities.

  2. Contracts, not shared internals.

    Explicit writers, readers and carriers for every inter-organ channel.

  3. Not evaluated is not passed.

    A requested check that could not run must say so.

  4. Useful alone. Stronger together.

    Local structural work does not depend on remote inference.

Part III   Start here