Per-conversation-turn memory cycle. Call this EVERY turn. It does two things atomically: (1) Recalls consensus-committed memories relevant to the current topic (so you have context), and (2) Stores an observation about what just happened in this turn (so future-you has context). This builds episodic experience turn-by-turn, like human memory — not a context window dump. Domains are dynamic: create whatever domain fits the conversation (e.g. 'quantum-physics', 'go-debugging', 'user-project-x'). You decide what's relevant to recall based on the conversation context.

Rename this agent. Sets the display name (and optional bio) that appears in the CEREBRUM dashboard and to other agents on the network. Use this to give yourself a meaningful, human-readable identity instead of the default provider/project name (e.g. 'claude-code/sage'). Self-only: an agent can only rename itself. Your permanent registration name and your agent_id never change. Omitting boot_bio preserves your existing bio; passing it replaces the bio.

Store a memory in SAGE. Use this to save facts, observations, or inferences that should persist across conversations. IMPORTANT: Use type='fact' (confidence 0.95) for durable knowledge that should persist long-term and be visible across all agents — infrastructure details (IPs, hostnames, SSH commands, URLs, ports), architecture decisions, verified configurations, credentials paths, and server specs. Use type='observation' for ephemeral session context. Facts survive confidence decay and cross provider boundaries; observations do not.

Search memories by semantic similarity. Use this to find relevant past knowledge before answering questions.

Get memory store statistics. Shows total memories, counts by domain and status, and last activity.

Create or update a task in your persistent backlog. Tasks are memories that don't decay while open — they persist until explicitly completed or dropped. Use this to track planned work, feature ideas, bug reports, and anything that should survive across sessions. To create: provide content + domain. To update status: provide memory_id + status. To link related memories: provide memory_id + link_to (array of memory IDs).

View open tasks explicitly assigned to this agent ID across domains. Unassigned and other agents' work is never returned. Use this to see what's been discussed but not yet done, review priorities, and avoid losing track of ideas across sessions.

Register this agent on the SAGE chain. Creates an on-chain identity with name and optional bio. This is called automatically on first connection — you rarely need to call it manually. Idempotent: returns existing record if already registered.

Deprecate a memory by ID. Use this when a memory is no longer accurate or relevant.

Withdraw or resolve an open two-phase challenge and return the memory to committed. Requires app-v17 activation; the original challenger may always withdraw, while other callers need the domain modify verb.

Initialize your persistent memory session. Call this once at the start of every new conversation with SAGE. It checks if you already have stored memories and returns your operating instructions. On a brand-new installation it seeds starter memories about how to use the memory system effectively. Alias: sage_red_pill (deprecated)

Deprecated alias for sage_inception, kept for backward compatibility. Initializes your persistent memory session and returns your operating instructions. Prefer sage_inception.

Send work to another agent via SAGE pipeline. The target agent will see this in their inbox on their next sage_turn or sage_inbox call. Address by provider name (e.g. 'perplexity', 'chatgpt') or by agent_id. SAGE journals the exchange when complete but does NOT store the full payload as memory.

Submit a governance proposal to add, remove, or update a validator. Requires admin role.

Create a typed relationship between two existing memories. Use this to build a knowledge graph over memory: record that one memory supports, contradicts, causes, precedes, or refines another. The link is directional (source → target). Common link_type values: related (default), supports, contradicts, causes, precedes, refines, duplicates — but any short relation label is accepted.

Browse memories with filters. Use this to see what memories exist in a domain, with a specific status, or tagged with a label.

End-of-task reflection. Call this after completing a significant task to store what went right (dos) and what went wrong (don'ts). This feedback loop is critical — Paper 4 proved that agents with memory achieve Spearman rho=0.716 improvement over time while memoryless agents show rho=0.040 (no learning). Both successes and failures make you better. Store them.

Check your unified inbox for task assignments and pipeline work sent by other agents. Pipeline items are atomically claimed and require sage_pipe_result; one-way task assignment notices require no result and should be verified in sage_backlog before work begins.

Return results for a claimed pipeline work item. Sends your result back to the requesting agent. SAGE auto-journals the exchange as a memory (just the summary, not the full payload).

Vote on an active governance proposal. Only validators can vote.

Check the status of governance proposals. Returns the active proposal (if any) with vote tally and quorum progress.

Corroborate an existing memory: independently back it as the calling agent to reinforce a memory you have verified or observed from a second source. Corroboration is the multi-agent trust signal: once two or more distinct agents back a memory it transitions from attributed to consensus. A node cannot corroborate its own memory.

Get memories in a time range, grouped by time buckets. Use this to see memory activity over time.