This entity is organized as a corporation when revenue is imminent; operations precede formation under the RË operating framework.
The orchestration and memory layer that makes autonomous code change accountable — coordinating twelve rewrite pipelines across Python and TypeScript under a cross-runtime validation contract that Python owns authoritatively.
Read the system argumentMoat: Cross-runtime validation contract with Python as authoritative validator — TypeScript output enters as structured candidate events, never raw writes. Aides neural substrate (weighted-mixture learning, multi-step attractor settle, 8 streams × 128–512 dims) is proprietary trade secret. Hive-mind state (216MB+) compounds with every validated change.
Traction: 12 pipelines operational. Self-programming engine has produced verified rewrites. 11-provider LLM failover ladder tested. UCIP validation gates passing. PyQt workbench separates observation from intervention in live runtime.
Upside: Federal funding eligibility de-risks Phase I across DOE ASCR, NSF OAC, DARPA I2O. UCIP strategic asset value compounds with each validated pipeline. Bond issuance at Year 3 unlocks debt-heavy scaling only after technical proof. Capital Discipline: No external equity dilution before technical milestones. Revenue from powered entities
Enki serves as the orchestration and memory layer — coordinating twelve rewrite pipelines, maintaining the hive-mind knowledge graph, and hosting the Aides neural substrate. UCIP serves as the validation architecture — enforcing the candidate lifecycle, voting protocol, and cross-runtime contract. This separation makes validation authority auditable: the orchestrator cannot grade its own work.
Authority limits: Enki may not accept or reject its own candidates; all validation decisions flow through UCIP's voting protocol. TypeScript producers emit structured candidate events to Python's validation path; no producer receives a private definition of success. Self-programming cycles operate under the same gates as external work — no privileged path exists for self-modification. All external-facing commitments flow through Phronesis for capital coordination.
This page serves multiple audiences. Institutional reviewers (banks, public-sector partners, infrastructure investors, technology collaborators) should start with the Argument block, Capital Lens, KPIs, Governance Boundary, and Factual Status sections for governance boundaries and risk disclosures. General readers can follow the Aides, Runtime, Memory, and Work sections for the operational logic. Aides technical architecture is proprietary and not available for external inspection.
AIDES Operational
Observe Aides live Coordinator status (JSON)
Aides is the proprietary neural substrate of Enki — a living, self-modifying cognitive architecture under continuous operation. It implements a weighted-mixture learning system (Hebbian, SOM, LEABRA, Backprop) with multi-step attractor settle dynamics and cross-modal correlation layers across 8 modality streams (128–512 dimensions). Technical architecture, modality configurations, and learning rules are trade secrets. Aides powers UCIP and all Enki deployments. Not available for licensing or external inspection.
Aides explores a distributed cognitive run in which an Oracle coordinator can remain alive while local computers join, contribute computation and sensorium devices, disappear, and reconnect to the same durable run. The distinction between identity and rank is central. A transient PyTorch process-group rank describes one current communication arrangement; it cannot by itself represent a participant that returns after a network failure. The implemented federation work therefore adds persistent actor identity, coordinator-issued leases, heartbeats, reconnect tokens, checkpoint compatibility, task retry, and explicit sensor and compute channels around the existing Ai.py system. Cameras, microphones, screens, mice, keyboards, CPUs, GPUs, and NPUs remain attached to the local participants that own them. The coordinator preserves run state and work ownership rather than pretending those devices live in Oracle.
This permits local machines to be contributors rather than thin terminals. They can execute model work while also supplying the changing sensorium. When one leaves, its lease expires and unfinished work becomes eligible for reassignment. When it returns, it resumes under the same actor identity if its checkpoint and run are compatible. The design does not create a separate miniature controller that stands in for the intelligence. It extends the existing process with the minimum durable coordination needed for continuity.
THE LIVE RUNTIME
The supported Windows path enters through the visible GUI launcher and starts launch_gui.py. The launcher owns duplicate-instance detection, environment assembly, process preservation, and rotating GUI session logs. This matters because a useful autonomous runtime cannot be tested by starting an ad hoc second copy with different configuration and then drawing conclusions about the first.
The PyQt workbench divides observation from intervention. Main Interface exposes projects, files, agents, generated candidates, and manual actions. System Monitor exposes live services and status. Knowledge Graphs surfaces the hive, Wanderers, memory, performance, and accumulated guidance. Neural Manager holds neural telemetry and utilities. These are not separate products. They are views over a runtime whose authoritative evidence remains in logs, SQLite state, saved state, and the behavior of the project being changed.
The TypeScript MasterControlProgram runs five hosted agents and mounts A2A surfaces. Its output enters the Python validation system through structured events instead of writing around it. External MCP tools enter through the shared Python tool plane. OpenClaw identities receive project-specific work and configured provider routes through the gateway client. This arrangement lets new workers participate without granting each one its own uncontrolled source-writing path.
Operational File-level autonomous agents operating in project working directories with full UCIP validation integration.
Validated Produces verified rewrites that pass UCIP gates; feeds productive guidance back to hive-mind.
Operational Generic TS/JS rewrite pipeline with structured candidate event output to Python validator.
Operational MasterControlProgram runs 5 hosted agents with A2A surfaces; output crosses as candidate events.
Operational Specialized handlers for refactor operations; validated through Python tool plane.
Validated Three-pass validation: syntactic, semantic, behavioral — with hive-mind guidance injection.
MEMORY WITHOUT AMPLIFICATION
Enki maintains project history, candidate outcomes, provider health, conversations, knowledge graph records, and a consumption queue for productive guidance. The architectural boundary: what deserves durability. A completed implementation, a failure pattern, a verified dependency rule, or a project-specific constraint can improve future work. Heartbeats, telemetry samples, internal persistence requests, and recursive bookkeeping usually cannot.
The Wanderer and hive paths classify internal events and merge useful packets rather than persisting every message indiscriminately. This is an architectural defense against feedback amplification. If integrating knowledge produces another knowledge event which produces another persistence request, the system can consume thousands of operations without learning anything. The repair is not a larger queue. It is recognizing which event is the causal producer and keeping bookkeeping on the non-semantic side of the boundary.
Successful self-programming work is stored as searchable guidance and later injected into related improvement prompts. TypeScript rewrite pipelines emit the same kind of productive packet. The value of this memory is tested when it changes later behavior: avoiding a known broken launcher, preserving an established project contract, selecting a viable provider, or running the proof that a previous attempt omitted.
WHAT THE SYSTEM IS FOR
Enki operates across software that does not share a single definition of done. A Django and Godot game needs authenticated server behavior, synchronized catalogues, export integrity, and an actual playable build. A Montessori tracker needs durable SQLite history, server-confirmed timers, backup import, and an accessible browser flow. SEPL needs a parser, compiler, service, and workbench that agree about the language. A remote Oracle service needs the target interpreter, systemd, loopback health, routed health, and external behavior. The system's orchestration must preserve these differences rather than reducing them all to "tests passed."
This is why workingdir/ projects remain real, independent programs. Enki can select work, supply agents, preserve claims, evaluate candidates, and carry lessons between projects, but the project owns its acceptance criteria. The intended outcome is not an autonomous system that produces more autonomous-system activity. It is a system that completes more difficult work while leaving a better account of how the result was obtained.
Read the UCIP validation architecture Read the compute-mesh research
CONTACT