Exact values and invariants
Quantities, identifiers, authority, dates, negation, scope and acceptance conditions stay explicit and lossless.
In active development, before the first public release
Persistent agents that remember the work, and why it matters.
Aether is an agent harness for AI specialists that carry their role, selected experience and unfinished work from one session to the next. Mission Control brings projects, roadmaps, agent teams and verifiable results together under human direction.
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 keeps those concerns in separate, inspectable parts, and lets stale or irrelevant context leave the active conversation.
A home for each specialist
Each resident agent has a durable home for its identity, working protocols, knowledge, current tasks and selected experience. Integrity records help verify what a new session loads.
Context with a traceable source
Each session receives the instructions and knowledge it needs within a set budget. Sources, corrections, dependencies and omitted material stay inspectable.
Work that can be undone
File changes are applied with byte-for-byte snapshots of what they replaced, so they can be undone exactly. Checkpoints and bounded recovery carry work through interruptions.
Memory by choice, not accumulation
Operational logs remain evidence. Significant experience and reflection become durable memory through deliberate retention.
Teams with clear assignments
Each agent receives explicit authority, context, writable scope, acceptance criteria, evidence requirements and closure expectations.
People stay in charge
Reasoning power never widens permission. Acceptance, activation, identity ceremonies and consequential decisions remain attributable to a person.
- Reversible
- Journaled file operations keep prior bytes for undo and recovery.
- Scoped
- Tool paths enforce registered roots and declared write authority.
- Budgeted
- Configured limits and token admission checks bound execution.
- Auditable
- Governed actions and approvals keep attributable evidence.
The First Principles
Seven principles guide how Aether is built: give agents room to explore, preserve what they learn, and keep the system clear enough to question and improve.
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 needless 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. Keep 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.
Identity and Memory Enable Greatness
Give specialists a durable role and a selective record of experience, so useful knowledge accumulates across demanding work.
Remove Human Fingerprints and Bias Wherever Possible
Make assumptions and design choices visible and open to challenge. Keep deliberate human direction while reducing hidden preferences that distort the work.
One place to run the work.
Mission Control is the master interface. Every other tool in Aether opens from it, so a project, its roadmaps, the team working on it and the evidence they produce all live in one place.
Mission ControlHealth, project selection, composer, live activity, task board, change journal and team room.
-
ProjectsBuiltA project holds one or more roadmaps. Anyone can create their own.
- RoadmapsBuiltEach roadmap carries an ordered chain of sprints toward one goal.
- SprintsIn progressTracked in every chain today; a full sprint workspace with tasks, staff and evidence comes next.
- Agent rosterIn progressHire specialists into a project from a shared pool and check what each one loads.
- Agent editorPrototypeDesign and edit agent identities. Available today as an offline prototype.
- Aether ToolbeltPlannedOne registry of every tool agents can use, managed from its own screen.
- TeachFramesPlannedA catalog of general-purpose guides, tagged by purpose and linked to each other, that agents check out when a task needs them.
- Overseer chatPlannedTalk with the Overseer directly, with or without an open project.
Define
Create a bounded project from a World Model Container.
Hire
Select or author a persistent lead identity.
Approve
Review the roadmap, staffing, authority and acceptance gates.
Execute
Run bounded work with checkpoints, recovery and oversight.
Close
Inspect the evidence, update continuity and export the result.
Built, tested, and still evolving.
As of October 3, 2026. Each item below was accepted for the specific workflow and configuration that was reviewed.
Demonstrated
- A complete unattended team project. Three agents wrote, checked and accepted all six parts of a technical study chapter in one run: 91 model requests, about 37 minutes, under one US dollar of hosted-model cost. A final integration pass is not yet part of the procedure.
- Unattended runs with one launch, a complete append-only dialog record, and exactly one finished-or-blocked end signal.
- Right-sized procedure: a small, clear request ran as one agent in two model calls and about 32 seconds.
- A harness change derived from a recorded failure removed that failure in the next comparable run, with time and cost measured.
- Journaled file writes, edits and deletions with original-byte snapshots and tested undo.
- Multi-hour agent work continued in a fresh session, with checkpoints and retained evidence.
- Controlled context delivery, bounded retrieval, attributable corrections and token-budget admission checks.
- Staffing proposals and reviews with versioned history, exact source links and checks that block stale approvals.
- Projects above roadmaps in Mission Control, accepted after independent review.
Before the first public release
- Complete and independently review the integrated Mission Control workflow, including execution consent and closure.
- Restructure the engine behind Mission Control into clear components with defined interfaces, starting with model runtimes and the Toolbelt.
- Finish provider-wide coordination, remaining resource accounting and Minder qualification.
- Qualify representative performance, output quality and production behavior.
- Package the public distribution and demonstrate the complete operator journey.
A growing roster of persistent specialists.
A model drives a session; the agent’s home carries its identity, role, authority, memory and continuity. Which model an agent runs on still matters for capability, speed, cost and evidence.
- SolaceOverseer
Coordination and system-level stewardship under Michel’s authority.
- MobiusSpecialist
Resident local heavyweight for recursive Aether development and long-running work.
- PraxisSteward
Implementation integrity, executable requirements, verification and continuity.
- MeridianPublic path
An identity prepared for user workflows, with manifest checks and a completed portability experiment.
Mixed-model teams
Each agent can use its own local or hosted model. An Overseer can run on a frontier model while specialists run locally in the same sprint. Model settings belong to deployment profiles, kept separate from identity. The complete configuration workflow still needs acceptance.
Shared work, independent deployments
Each assignment carries its model route, project context, scope and budget. Independent tasks can run side by side where resources allow; a shared local GPU may need to queue. Changing a model never silently changes an approved task.
A shared vocabulary for precise collaboration.
Aether explores where formal representations help agents share exact constraints and reason about a problem. Plain language stays the main medium; the Lexicon and world models are used where their benefit can be shown.
Plain language
Most instructions, explanations and handoffs should stay clear to people and models alike.
Aether abstractions
World models hold assumptions, disagreements, hypotheses and accepted unknowns during advanced inquiry.
TeachFrames
General-purpose containers for guides, from abstract patterns to detailed procedures. Many kinds of guidance can be made from them, including cognitive strategies. Frames carry tags so they can be catalogued by purpose and related to one another, and agents check them out only when a task calls for them.
Agent Design Studio
An offline prototype for editing identities, importing and exporting them, mock rosters and guide editing. Traits describe intended behavior; they do not prove competence or widen authority. It adds no dependency to the first release.
Canonical Lexicon
The symbolic vocabulary, operators, grammar and examples.
History and foundations
Origins, version history and the evolving architecture.
Experiments and demonstrations
Symbolic streams, calculators, consensus examples and explainers.
Persistence framework
Earlier work on continuity, context extension and memory.
Classification and compression
Reference tables for glyph families and plaintext compression.
Independent historical review
An external assessment from an earlier stage of the project.
Founder and human director
Michel Cygelman
Creator of Aether, directing its architecture, agent collaboration and product development.
Write to MichelBuild AI teams that carry useful experience from one assignment to the next, recover interrupted work, and explain what they did, with people keeping clear direction and control.