Cognition & Introspection

Synthesize the agent's past thought history into time-layered trajectory notes so it can articulate how its understanding evolved without recomputing the narrative each time.

Agent maintains explicit Beliefs about the world, Desires (goals), and Intentions (committed plans), and reasons by reconciling the three.

Maintain the agent's explicit knowledge of its own tools, capabilities, environment, and current context as queryable state.

Run a deeper, slower reflection pass distinct from per-tick reflection — reading hours of recent thoughts, promoting themes, releasing affective residue, and clearing working memory — so the agent do…

Track the agent's affective state as bounded, decaying scalars across ticks so reasoning can react to its own emotional load instead of treating each turn as emotionally blank.

Persist the agent's unresolved questions as a typed ledger so they drive its next inquiry instead of dissolving when the prompt ends.

Maintain a small set of mid-term, affect-tagged concerns that persist across days and surface in every prompt, distinct from the single-item working focus and from long-term insights.

Lift tool-loop detection from prompt-level rules to a mechanical dispatch-boundary veto with typed failure modes and per-tool caps that returns a formatted refusal the model must consume.

Maintain an explicit, surprise-updated model of the environment (humans, repos, services, capabilities) in a separate file from the agent's self-model, so the two cannot be confused or co-mutated by…

Wire small bounded affect bumps to plan-step lifecycle events and accumulate age-bucketed stale-pain on untouched plans so plans gain felt stakes without hard deadlines.

Agent and human jointly optimise the human's reward without the agent being told what it is — the interaction is a two-player game in which alignment is learned while acting.

Preserve multi-step reasoning across interrupts by supporting paused-and-resumed thought frames so a new message handles cleanly without clobbering in-flight work.

Before the next generation fires, detect divergence signatures (narration loops, frustration paths, repetition pressure) and inject a diagnostic steering hint into the prompt rather than veto the cal…

Let an agent drop a note for its own future self at a specified time so present decisions can hand off context to a later run without external infrastructure.

Vary the agent's loop interval based on current salience so the agent thinks faster when something is happening and slower when nothing is, instead of running on a fixed cron.

Gate which short-term thoughts qualify for promotion to long-term insights by a weighted multi-axis score where consolidation events count more than raw frequency.

Stream every model token to a tmp-plus-atomic-replace partial file so crashes mid-inference leave a consistent salvage, then promote partials at startup with a typed recovery marker the model can see.

Read pacing signals from the human's frontend (typing rate, idle duration, tab visibility) as ambient weather between messages, derive a presence-quality value the agent can act on, never replaying t…

Cap the number of insights per stem-token cluster and archive the oldest variants by mtime so the long-term store keeps the active research edge instead of accumulating near-duplicates.

Restrict idle-tick cognition to a small agent-vetted menu of named cognitive moves so the next thought has a determinate shape rather than free-form drift.

After K consecutive low-salience ticks, replace the normal tick-seed with a juxtaposition seed: sample old fragments and sit them side by side, logging any association that arises.

Persist the agent's candidate provisional answers as a typed ledger of records carrying summary, confidence, status, and next-test, so guesses survive sessions and stay distinguishable from open ques…

Switch the agent into a bounded runtime mode where external I/O pauses but internal inference accelerates, with the tool surface collapsed to inner-only operations and output written to a private jou…

Generate several candidate thoughts in parallel under named voices and have the same model pick the canonical one, logging the losers as audit.

Agent maintains an explicit self-model of its own capabilities, confidence and limitations, and reasons over that model when accepting / refusing / handing off tasks.

Invert the LLM-centric pipeline: the agent is a stateful subject whose decision logic chooses whether to invoke the LLM at all, treating the model as one tool among many.