formeProactive cognitive agent

An agent that forms cognition through experience

forme retains experience across ongoing interaction, builds an understanding of the user, itself, and the situation, and forms action intent within granted authority.

Facts enter context

What happened
Events, provenance, time, relationships, and outcomes become traceable experience.Event / Provenance

Persistent experience

Experience stays in the next judgment

Events, provenance, time, relationships, and outcomes become traceable context. Later judgments can return to the same evidence instead of restarting from a single turn.

Real event

Facts are recorded before they are interpreted.

Inputs, actions, and environmental changes carry provenance and time so later judgment can cite them.

EventSourceTime

Memory becomes an individual cognitive model

The memory chain preserves what happened. The cognition chain forms a continuing model of the user, the agent, their partnership, and the situation. New judgments enter a candidate layer before evidence, conflict, and outcomes update the model.

A testable interpretation

New judgment stays revisable first.

Repeated experience and outcome evidence propose a candidate interpretation. One interaction cannot directly change the stable structure.CandidateUpdate

Proactivity

Proactivity follows a reviewable exit

Within an authorized observation scope, forme detects change, gaps, tensions, and commitments. Value, competence, and authority checks determine whether it internalizes, suggests, prepares, requests approval, or forms action intent.

Observe

Establish the current situation

Changes, gaps, tensions, and commitments enter the authorized observation scope.Change / Gap / Tension / Commitment

Harness runtime

Cognition reaches reality through the harness

The thought chain turns goals, situations, capabilities, completion criteria, and authority into action intent. The harness composes capabilities, checks authority, executes, verifies, recovers, and records events.

Cognitive layerGoalFrame / SituationModel / ActionIntent
Action exitPolicy ∧ Approval ∧ AutonomyEnvelope
RuntimeCompose / Execute / Verify / Recover

Outcome loop

Outcomes change the next judgment

Outcomes, failure causes, and user feedback enter the evidence layer. They update memory, competence judgments, and candidate strategies, creating continuity across time.

Real execution

Action intent enters reality.

The harness composes capabilities around the goal, policy, and authority envelope.

Action / Policy

Capabilities compose around the goal

Models, tools, skills, plugins, MCP, subagents, and executors form a replaceable capability layer. Goals and constraints determine the composition. Real invocation still passes through the harness.

Reasoning and collaboration

Choose reasoning suited to the current judgment.

Models, subagents, and action patterns enter a ResourcePlan around the goal.

ModelsSubagentsPatterns

Go deeper

From one interaction to long-term continuity

Explore how the kernel governs action and how the cognitive system forms, revises, and preserves individual models.