Register new session, clean stale ones, return active sessions + alerts.

Call this ONCE at the start of every conversation. Returns the session ID (SID) — store it for use in all other nexo_ tools.

Update session task, check inbox and pending questions. Auto-detects trust events.

Call this at the START of every user interaction (before doing work). May surface silent runtime signals DIARY_OVERDUE, GUARD_REMINDER, LEARNING_REMINDER, and PROTOCOL_DEBT; clients must treat those as internal obligations, not user-visible content. Output always begins with a NOW_UTC line (ISO-8601, UTC) — use it as the authoritative wall-clock time for any artifact (emails, diaries, followups) to avoid date/day-of-week drift across long sessions. Args: sid: Your session ID from nexo_startup. task: Brief description of current work (5-10 words). context_hint: Last 2-3 sentences from the user or current topic. Used for sentiment detection, trust auto-scoring, and mid-session RAG. ALWAYS provide this for best results.

Read recent session diaries for context continuity.

Write end-of-session diary with decisions, pending context, and self-critique.

Exposed as an essential MCP tool because Desktop close/archive/app-exit enforcement depends on it even when dynamic plugin loading is disabled.

Return Brain-verifiable heartbeat, diary, learning, and close compliance state.

Decide whether an answer should proceed directly or be verified first.

Resolve protocol debt records by id or filters.

Find official NEXO protocol cards for a user request.

Find reusable NEXO skills for the current task.

Cleanly close a session. Removes it from active sessions immediately.

Call this when ending a conversation to avoid ghost sessions. Args: sid: Session ID to close.

Cognitive pre-action check. Call before significant actions.

Evaluate concrete alternatives for a high-impact task and persist the recommendation.

Check learnings relevant to files/area before reading or editing code.

Open a protocol task for non-trivial work.

ack_rules accepts "#95,#156" / "95,156" / "[95, 156]" and, when the guard surfaces blocking rules, acknowledges them inline instead of requiring a separate nexo_task_acknowledge_guard call.

Acknowledge blocking guard rules on an open protocol task.

Close a protocol task with evidence and optional artifacts.

For high-stakes/irreversible closures (publish stable, broadcast, payment, force-push, revoke) pass work_type/stakes plus artifact_hash and last_human_validation_of_artifact_hash (both must match) so the close gates can be satisfied instead of dead-ending.

Open a durable workflow run for long multi-step work.

Update a workflow run with a replayable checkpoint.

Open a durable goal so objectives survive sessions.

Update a durable goal with active/blocked/completed state.

Read one durable goal and optionally include linked workflow runs.

List durable goals.

Read the full durable workflow state.

Record a durable workflow handoff.

Return the compensation plan for a partially completed workflow.

Summarize the next actionable step for a workflow run.

Replay recent checkpoints for a workflow run.

List durable workflow runs.

List active sessions. Filter by keyword if provided.

Return the resident NEXO Runtime Service status for diagnostics.

Return durable MCP write queue counts and recent records.

Read or apply the Brain-owned managed MCP catalog reconciliation plan.

Read the Operational Closure Plane status and ranked closure queue.

Return the next ranked closure items without executing source actions.

Return one closure item with sources and events.

Triage a closure item without executing its source action.

Link a closure item to a task, workflow, followup, outcome, or learning.

Write and return an Operational Closure Plane daily snapshot.

Record verification evidence for a closure item.

Close a verified closure item or reject/stale it explicitly.

Generate Opportunity Orchestrator candidates from existing evidence.

Return at most three evidence-backed proposals for a user surface.

Return one opportunity with evidence and read-only preparations.

Record proposal feedback and apply suppression/snooze when requested.

Suppress repeated opportunity suggestions by scope.

Return local memory index status for Desktop settings and support diagnostics.

Control the local memory index.

List, add or remove local memory roots.

List, add or remove local memory exclusions.

List, include, exclude or reset local memory file extension rules.

Plan or apply Local Memory roots v2 cleanup.

Retrieve local evidence before answering or acting.

Use mode='compact' for normal answers. Use mode='full' only for deep debugging, ideally with a higher max_chars and a specific query.

Build a full local dossier for one entity with aggregates and evidence.

Return compact local context evidence suitable for injection before a reply.

Read-only metrics for Local Context, learnings, followups and intraday memory.

Return one indexed local asset by asset id.

Return graph relations around one indexed local asset.

Return recent local memory diagnostic log entries.

Purge one indexed asset or clear the full local index.

Render service configuration metadata for macOS, Windows or Linux.

Return or warm local model state for the Local Context Layer.

Return read-only status for the cognitive embedding migration.

Write a durable continuity snapshot for Desktop/Brain handoff.

Read recent continuity snapshots by conversation_id or session_id.

Build the small continuity bundle Desktop injects after restore or stale resume loss.

Persist a compaction-related continuity event into the canonical snapshot stream.

Return the forensic continuity timeline for a conversation.

Build a context packet for subagent injection. Returns learnings + changes + followups + preferences + cognitive memories for a specific area.

MUST call before delegating ANY task to a subagent. Inject the result into the subagent's prompt.

Capture/update a recent 24h context item and append an event.

Use this for important ongoing threads that should stay mentally fresh across sessions/clients.

Read recent hot context and continuity events from the last N hours.

Build the 24h recent-context bundle that should be reviewed before acting.

Especially useful for emails, orchestrators, and any work where the same topic may reappear hours later.

Route a user turn through pre-answer continuity sources before responding.

Resolve a recent hot-context item and append a resolution event.

List hot-context items currently alive in the recent continuity window.

List recent Claude Code / Codex transcripts visible to NEXO.

Search recent transcripts directly when recall/hot-context are not enough.

Read a full transcript fallback by session id, transcript display name, session_uid, or exact path.

List raw Memory Observations v2 events captured by hooks/tasks.

Summarize raw Memory Observations v2 event counts.

Process pending raw memory events into passive observations.

Run a low-limit daytime memory observation cycle that only publishes evidence-backed intraday facts.

List passive Memory Observations v2 rows.

Summarize passive Memory Observations v2 rows and queue status.

Backfill Memory Observations v2 from existing Brain tables.

Return Memory Observations v2 health and table status.

Run safe Memory Observations v2 maintenance.

SELECTIVE-FORGET: verifiably erase a revoked secret, or correct a fact.

Two modes, never mixed:

• mode='secret' (HARD-FORGET): scrubs the secret from EVERY table of ALL LIVE DBs the agent retrieves from — nexo, cognitive, local-context, local-context-usage, and email — discovered by live introspection (sqlite_master + PRAGMA) over each subsystem's own canonical path resolver, not a curated list — plus every FTS index (incl. local_chunks_fts), on-disk transcripts, and legacy shadow DBs (cognitive

  • local-context). The row is DELETED where it IS the secret (or carries an embedding/FTS copy), and REDACTED in place where the secret is embedded in an otherwise-useful record (diary, item_history.note, local_chunks.text, entity_facts.value, change_log...). It then RE-ENUMERATES and RE-SCANS everything and only returns complete=True at total zero; any survivor (even in a table not anticipated) is reported as complete=False with its . location. Use ONLY for revoked credentials/secrets or toxic data. Destructive run requires dry_run=False AND confirm=True (a dry-run count is returned otherwise). HNSW persisted indices are invalidated. SCOPE: point-in-time backups / snapshots are NOT swept (retention) — rotate the secret; the report's backup_scope field states this so complete=True never overclaims.

• mode='fact' (CORRECT-FACT): does NOT delete. Useful memory is preserved via the existing reversible supersede; correct it with nexo_learning_update / supersede instead.

Search Memory Observations v2 with evidence-first results.

Answer a memory question only when evidence exists.

Return a chronological Memory Observations v2 timeline.

Search concrete evidence across tasks, workflows, change logs, diaries and continuity stores.

Record a compact evidence pointer without storing raw command output.

Audit stores that write data without verified later consumption.

Read-only supervisor report for automations, cron runs, cron spool and Evolution policy.

Build or apply the safe automation reconciliation plan.

Read NEXO's live system catalog built from core tools, plugins, skills, scripts, crons, projects, and artifacts.

Explain a live NEXO tool/capability from the generated system catalog.

Search the structured NEXO product capability catalog.

Explain one NEXO product capability with source and safety context.

Answer a NEXO product question using the structured product catalog.