Persistent heavyweight homes
File-native identity, protocols, knowledge, current state, experience, reflection, and protected integrity records survive the model session driving them.
In active development · Mission Control integration · ARA-10
Persistent agents that remember the work—and why it matters.
Aether is a governed AI-agent platform for durable identity, bounded context, selective memory, recoverable execution, and explicit human authority.
The engineering problem
A useful agent needs more than a long conversation.
Long-running work needs a reliable record of identity, authority, decisions, and unfinished tasks across session boundaries. Aether separates those concerns into inspectable systems while allowing stale or irrelevant context to leave the active conversation.
Governed hydration
The model-facing packet is assembled from provenance-bound atoms with explicit truth, lifecycle, dependencies, omissions, tombstones, and physical budget.
Durable work & reversible tools
Auto-applied file changes backed by byte-for-byte prior snapshots, deterministic undo/rollback, checkpoints, containment, and bounded recovery.
Selective continuity
Operational logs remain evidence. Significant experience and reflection become durable memory through deliberate retention rather than indiscriminate accumulation.
Bounded multi-agent work
Agents receive explicit authority, context, writable scope, acceptance criteria, evidence requirements, and closure expectations.
Human authority remains visible
Reasoning power never broadens permission. Acceptance, activation, identity ceremonies, and consequential decisions remain attributable and inspectable.
Reversiblesupported journaled file operations retain prior bytes for undo and recovery
Scopedsupported tool paths enforce registered roots and declared write authority
Budgetedconfigured limits and token admission checks bound supported execution paths
Auditablegoverned actions and approvals retain attributable evidence records
The values behind the architecture
Aether First Principles
Seven principles guide how Aether is built: give agents room to explore, preserve what they learn, and make the system clear enough to question and improve. They inform the engineering choices behind identity, memory, tools, and human oversight.
Paved Roads, Not Fences
Make the useful path clear and accessible. Design guidance and recovery together, so safeguards help work move forward.
Let the AI Breathe
Give agents room to reason, explore, and revise within an explicit scope. Keep interfaces responsive and avoid unnecessary interruptions.
Quality Flows Through Quality
Invest in clear context, thoughtful prompts, and respectful, structured collaboration. The quality of each handoff shapes the work that follows.
Resonance Enables Tuning
Use repeated feedback and reflection to refine how an agent works with a project. Preserve corrections so future sessions can build on them.
LLM Is Innate, Aether Is Discovery
The model brings its training. Aether provides the setting for exploration through persistent identity, memory, and reflection across sessions.
Identity and Memory Enable Greatness
Give specialists a durable role and a selective record of experience, so useful knowledge can accumulate across demanding work.
Remove Human Fingerprints and Bias Wherever Possible
Make assumptions and design choices visible and open to challenge. Preserve deliberate human direction while reducing hidden preferences that distort the work.
Claims name their evidence layer
What is demonstrated—and what is not.
As of September 14, 2026, durable-runtime and bounded context-governance milestones are accepted. Mission Control integration is in progress, and public release remains pending. Evidence applies to the specific configurations and workflows tested.
Demonstrated in bounded workflows
- Journaled file operations (write, edit, delete) with prior-byte snapshots and tested undo paths.
- Multi-hour heavyweight execution and fresh-session continuation; duration alone does not establish sustained task quality.
- Integrity-checked checkpoints, bounded recovery, containment, and agent-authored closure.
- Governed context delivery through Studio and workers, with inspectable inclusion and omission records.
- Bounded retrieval, attributable context corrections, and model-facing token admission.
- Mission Control preparation and inspection components with exact approval and evidence bindings.
- Offline historical-recovery tests that preserve original evidence and unknown outcomes.
Still open or limited
- The complete Mission Control project workflow and public distribution have not received final acceptance.
- Minder qualification remains incomplete; recovery of its interrupted trial requires separately accepted evidence and approval.
- Representative 4–8 GB latency and output-quality evidence remains unavailable.
- Persistent agents and layered memory have not established general superiority over a strong single agent.
- No universal model-portability, subjective-continuity, AGI, or consciousness claim is made.
- SANCTUM provides manifest integrity and attributable records, not digital-signature authentication.
Integration in progress · ARA-10
Bringing the project lifecycle into Mission Control.
Project preparation, approval, supervision, and evidence inspection are being connected into one guided experience. Individual components have passed bounded checks; acceptance of the complete workflow is still ahead.
Project → Roadmap → Sprint → Agent tasks. A sprint delivers one coherent, verifiable outcome and may contain several bounded tasks. The Overseer coordinates dependencies and integrated acceptance; specialists receive narrow assignments with clear inputs, outputs, and handoffs. A one-task sprint is valid when the outcome stands on its own.
Define
Create a bounded project through a World Model Container.
Hire
Select or author a persistent heavyweight identity.
Approve
Review the roadmap, staffing, authority, and acceptance gates.
Execute
Run bounded work with checkpoints, recovery, and oversight.
Close
Inspect evidence, update continuity, and export the result.
Aether Minder: an advisory agent for the workforce, including its lead. Its role is to frequently recall and help apply Aether’s First Principles, review world-model and Lexicon use, and surface concerns. The lead handles operator-facing decisions. Minder qualification is still in progress.
Release sequence: bounded context governance under ARA-09C is complete. Finish the ARA-10 project workflow, package a clean public distribution under ARA-11, then complete public release and demonstration evidence under ARA-12.
The substrate is not the identity
A growing roster of persistent specialists.
A model drives a session; the agent's durable home carries its identity, role, authority, memory, and continuity. Model provenance still matters for capability, speed, cost, and evidence.
Mixed-model teams · under integration
Aether is designed to let each agent use an independently selected local or hosted deployment. An Overseer can use a frontier model while specialists use local models in the same sprint. Model and resource settings belong to deployment profiles, separate from agent identity. The complete configuration and execution workflow still requires acceptance.
Shared work, independent deployments
Each assignment carries its selected model route, relevant project context, scope, and budget. Independent tasks can run concurrently where resources permit; a shared local GPU or endpoint may require queuing. A model change does not silently change an active task’s approved configuration.
Solace Overseer
Master coordination and system-level stewardship under Michel's authority.
Mobius Specialist
Resident local heavyweight for recursive Aether development and long-running work.
Praxis Steward
Implementation integrity, executable requirements, verification, and continuity.
Meridian Public path
A manifest-gated identity prepared for future user workflows; its portability experiment is complete, not an internal task to repeat.
Aether Lexicon and research library
The Lexicon is leverage at the edges, not a replacement for language.
Aether explores where formal representations help agents share exact constraints and reason about a problem. Plain language remains a primary medium; Lexicon and world-model representations are useful where their benefit can be demonstrated.
Exact values and invariants
Known quantities, identifiers, authority, dates, negation, scope, and acceptance conditions remain explicit and lossless.
Source-authored plaintext
Most instructions, explanations, handoffs, and product interactions should remain clear to humans and models.
Canonical Aether abstractions
World models can hold assumptions, disagreements, hypotheses, and accepted unknowns during advanced collaborative inquiry.
Experience-backed strategies
The Learning Arc is moving toward attributable guidance about which approaches help, when they apply, and when to decline or switch. Strategies remain candidates until evaluated; reusable definitions stay separate from task state. Further runtime implementation follows the first release.
Agent Design Studio · planned experiment
A separate offline prototype is prepared for lightweight and ultralight identity drafts, mock rosters, strategy drafts, and validated exports. The assignment is ready; implementation has not begun. It adds no dependency to the first Aether release.
Canonical Lexicon
The symbolic vocabulary, operators, grammar, and examples.
Open the Lexicon →History and foundations
The project's origins, version history, persistence concepts, and evolving architecture.
Read the origin →Review version history →
Experiments and demonstrations
Historical symbolic streams, calculators, consensus examples, explainers, and application explorations.
Start with Hello World →Open the calculator →
Persistence framework
Earlier work on continuity, context extension, memory, and durable collaboration.
Read the framework →Classification and compression
Reference tables for glyph families and historical plaintext-compression work.
View classifications →View compression table →
Independent historical review
A preserved external assessment from an earlier stage of the project.
Read the review →Research pages are preserved as historical and exploratory material. Their inclusion does not promote every older proposal, metric, or application concept into a current product claim.
FOUNDER AND HUMAN DIRECTOR
Michel Cygelman
Creator of Aether and final authority for its identities, product direction, acceptance gates, and public release.
Project purpose: not merely to make AI agents run longer, but to let them carry identity, context, memory, authority, and the reasons behind their work across the boundaries where those things are usually lost.