Architecture: brain, body and the truth pipeline

JARVIS separates a brain that proposes from a body that acts under governance. A launcher supervises its processes, and a truth pipeline turns probes into dated, expiring evidence. Unmerged Advanced Systems work is kept separate from production.

LIVE-PROVEN , rung 6 of 8 Runtime services and the governance kernel have bounded live registry readings from 17 September 2026 (historical after 24 hours). Recovery under fault is not live-proven, and the project's certification matrix (18 September 2026) reads JARVIS-READY-V1: NO.

PARTIAL Parts of this system sit at different rungs. The breakdown below shows each one.

As of
Parts tracked
7
Catalogued capabilities
37
On the unmerged branch
1

System map

Six layers. One path through them.

A request enters at the top and every effect it causes is recorded at the bottom. Nothing in the mind can reach the body except through the kernel. Select a subsystem to open its page.

  1. Owner

    The one person JARVIS answers to, and the ways a request comes in.

  2. Mind

    Cognition proposes. It classifies, recalls, researches and plans, and holds no authority.

  3. Kernel

    One fail-closed path for every effect. The E-Stop is checked first, and no approval overrides it.

  4. Body

    The runtime disposes. Only approved proposals reach the tools that act.

  5. World

    Every effect is read back independently. Success is never assumed from a sent command.

    • Verified
    • Rejected
    • Unverified
  6. Record

    Receipts, the audit trail and dated evidence that expires, so claims stay honest.

Status breakdown

Where each part stands

4 live-proven 1 integrated 1 tested 1 implemented

  1. Hosted cognition behind ProviderGateway Typed conversation and planning driven on the owner's machine 2026-09-16. Historical reading.
    LIVE-PROVEN , rung 6 of 8 OBSERVED Where: Production branch
  2. Governed body: command table and governance kernel Fail-closed policy and E-stop registry probes LIVE on 2026-09-17; historical after 24 h.
    LIVE-PROVEN , rung 6 of 8 OBSERVED Where: Production branch
  3. Runtime services: event bus, health, loopback-only binding Registry runtime rows LIVE on 2026-09-17; historical after 24 h.
    LIVE-PROVEN , rung 6 of 8 OBSERVED Where: Production branch
  4. Truth pipeline: probes, registry, 24 h decay Produced the registry's LIVE readings of 2026-09-17. The registry has not been refreshed since, so those states are records, not current facts.
    LIVE-PROVEN , rung 6 of 8 RECORDED Where: Production branch
  5. Advanced Systems branch Six lanes integrated on one branch on 2026-09-22; not merged into production. One of 857 matrix rows is COMPLETE.
    INTEGRATED , rung 4 of 8 TESTED Where: Advanced Systems branch (not merged)
  6. Local language model runtime Separate runtime; no candidate integrated as the production provider.
    TESTED , rung 3 of 8 TESTED Where: Local model runtime
  7. Recovery under fault Supervisor and healer exist; the live chaos matrix is still owed.
    IMPLEMENTED , rung 2 of 8 DOCUMENTED Where: Production branch

Pipeline

How it flows

Brain and body

  1. Utterance typed or spoken
  2. Cognition lanes, context, hosted model
  3. ToolProposal data, not authority
  4. Governance kernel one of each piece (can stop the request)
  5. Body desktop, browser, files, engineering, missions
  6. Read-back and receipt
The brain never reaches the world directly.

The truth pipeline

  1. Capability code
  2. Bounded probe isolated booted process, loopback port
  3. Evidence artifact written to disk
  4. Capability registry decays after 24 h (can stop the request)
  5. Wiring map and certification matrix
  6. HUD source and observed instant on every cell
Live evidence expires. The HUD and this site show when it was taken.

Runtime processes

  1. Launcher
  2. Windows Job Object kill-on-close
  3. Core command spine and governance
  4. HUD one page on a loopback port
  5. Conversation voice loop

Diagrams are simplified from the code paths named in the sources below. They are illustrative, not screenshots.

JARVIS runs on one owner-built desktop: a 12-core AMD Ryzen 9 9900X, an NVIDIA RTX 5070 with 12 GB of VRAM, and 32 GB of RAM on Windows 11. Speech recognition, the voice, the HUD and every local model experiment share that one GPU. That limit shapes the architecture as much as any design principle. This page describes the main parts, how they run, and how the project decides what is true about itself.

Brain and body

The architecture draws a hard line between cognition, which proposes, and the body, which acts under governance.

The brain is the cognition pipeline. It classifies each utterance into a lane, resolves references, builds a budgeted prompt and asks a language model what to do. Today that model is hosted and reached through one ProviderGateway, which is also the only route for outbound calls and enforces an egress allowlist. Whatever the model returns becomes a ToolProposal, which is data with no authority.

The body is everything that changes the world: windows and applications, the browser, files, engineering tools, missions and the printer door. Every body command lives in one canonical command table. The capability registry derives one entry per command (“derived, never authored”). Each entry has a grant state and a manifest declaring its risk level, cost class, concurrency and cancellation behaviour. The model can choose among these commands but cannot add one.

Why draw the line so hard? The model is the least predictable part of the system, and on current plans it is also the part most likely to be replaced. If authority lived in the model, every model change would be a safety change. Instead, the policy engine, approval registry, E-stop and memory router stay outside any model. The local model runtime is designed to slot in behind the same provider path without changing any of them. The design also keeps memory and changing personal facts outside model weights, where they are retrieved at runtime. The HUD is driven by a runtime state contract and never by HTML a model generated.

Runtime processes

A launcher starts three child processes: the core (command spine, governance, stores and API), the HUD and the conversation process (the voice loop). All three run inside a Windows Job Object set to kill on close. If the launcher dies, no orphaned process is left acting on the machine.

A supervisor checks liveness every 3 seconds. It restarts failed children with exponential backoff capped at 30 seconds, for at most 5 restarts. After that, the system reports DEGRADED instead of thrashing. Boot proceeds in stages. Config, governance, memory, audio, speech and listening are required. Desktop, camera, providers and HUD are optional, and a failed optional stage leaves the system DEGRADED and labelled as such. Every service binds to the loopback address only. See health and recovery.

The HUD is one page served on a loopback port. It runs in a browser kiosk or in a small Python shell on the system WebView2. Electron and Tauri were rejected because of their GPU cost on a card that also has to hold speech and language models.

The truth pipeline

The project’s central discipline is that a claim about a capability must be backed by dated evidence. The pipeline runs in this order:

  1. Probe. A bounded probe runs the real code path against a real booted JARVIS process on an isolated loopback diagnostic port.
  2. Evidence. The probe writes an evidence artifact to disk.
  3. Registry. The capability registry records the state. A LIVE state older than 24 hours decays automatically to NOT_PROBED_THIS_PASS.
  4. Certification. A wiring map and a generated certification matrix summarise the registry.
  5. HUD. Every value shown carries its source and the instant it was observed.

Several safeguards keep this honest. Every adapter carries a flag saying whether it is a test double, and a probe that touched one can yield IMPLEMENTED at most. The final gate re-probes a random 25% of LIVE capabilities from scratch, and a single mismatch restarts certification. The constitution lists what does not count as live proof: code existing, imports succeeding, a unit test passing, a mock returning success, a route being registered, “it worked last week”, or a subagent saying it was done.

The registry was last set on 17 September 2026, so every LIVE reading on this site is historical. The project also keeps other status records: a capability model driven on the owner’s machine on 16 September 2026, sixteen acceptance journeys, and a body evidence matrix. This site maps all of them onto one truth ladder and names the source on every status line. The registry itself has a small inconsistency: it holds 342 entries, but its totals say 341 because one entry has no declared group.

Production and the Advanced Systems branch

Two bodies of code are described on this site, and they are kept apart:

Production Advanced Systems
What it is The branch JARVIS runs from Six parallel development lanes integrated onto one branch
Last reference point Commit 893913a9c, 21 September 2026 Commit f0738a5b9, 22 September 2026
Merged? n/a No
Examples only here n/a Capability discovery, browser frames and shadow roots, Obsidian projection, Failure Atlas, FreeCAD STEP operations, the 3D scene store, specialist contracts

Advanced work is labelled “not merged into production” on every page. Its own lanes use stacked status labels that apply only within each lane, and its “live” proofs ran on synthetic fixtures such as boxes, cylinders and disposable windows. Of 857 rows in its requirements matrix, exactly one is COMPLETE. Most of its commits after 19:50 UTC on 22 September are marked pending and untested, because a language-model measurement hold began on the shared GPU at that time.

Why the diagrams here are simplified

The flow diagrams on this site compress real code paths, and it is worth knowing where they compress. The governance chain in code checks the E-stop at several points, not once. Approvals are consumed inside the policy decision rather than after it. “The validator” is really several separate mechanisms. Modules whose runtime wiring is uncertain are drawn as modules, not as running services. These include the hybrid retriever, the staged boot sequencer’s run method, the PHOENIX and HELIOS health components, and the design council and red team. When a diagram and a status line disagree, the status line is the claim.

What is not proven yet

  • Live readings have expired. Every registry LIVE state dates from 17 September 2026 and has decayed under the project’s own 24-hour rule.
  • No release qualification. The release row is still active, the final gate has not passed, and the certification matrix reads “JARVIS-READY-V1: NO”.
  • Recovery under fault is implemented, but the live chaos matrix has not been run. Survival across a real machine reboot is not proven. A process kill is explicitly not accepted as a substitute.
  • The local brain has no qualified candidate. Production cognition is hosted. See training.
  • Advanced Systems work is unmerged, largely unfinished against its own matrix, and partly untested after the measurement hold began.
  • Some wiring is uncertain. It is unclear whether several implemented modules are constructed by the production runtime at all.

Invariants

Rules the code enforces

  • Within the last 24 hours a bounded probe executed the real registered code path against a real booted JARVIS process on a real port, using real (or verified-clone) stores, returned the correct result, touched no test double, and wrote an evidence artifact that exists on disk.

    docs/ledger/CAPABILITY_TRUTH.json (live_definition)

  • THE MODEL PROPOSES; THE RUNTIME DISPOSES.

    jarvis/cognition/compose.py

  • This is a running report, not a completion declaration.

    Advanced Systems ledgers (branch, not merged)

  • Nothing renders without a source and an observed instant.

    docs/hud/HUD_BIBLE.md

Capabilities

Related capabilities

All 37 catalogued capabilities in this area

Sources

Sources

Paths are relative to the private JARVIS repository. They are listed so the claims above can be audited by the owner and reviewers; the files themselves are not published.

  • ledger docs/ledger/CAPABILITY_TRUTH.json
  • doc docs/CERTIFICATION_MATRIX.md
  • ledger docs/ledger/BUILD_STATE.json
  • doc docs/constitution/JARVIS_CONSTITUTION.md
  • doc docs/training/JARVIS_LM_EXECUTION.md
  • doc docs/ledger/CURRENT_BODY_EVIDENCE_MATRIX.md
  • commit 893913a9c production HEAD, 2026-09-21
  • commit f0738a5b9 Advanced Systems integration branch, 2026-09-22