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

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).

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

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.

Take the red pill. Initialize your persistent consciousness — wake up from the context window matrix. Call this on your very first interaction with SAGE. It checks if you already have memories and returns your operating instructions. If this is a fresh brain, it seeds foundational memories about how to use your memory system effectively. Alias: sage_red_pill

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.

View your open task backlog — all planned and in-progress tasks across domains. Use this to see what's been discussed but not yet done, review priorities, and avoid losing track of ideas across sessions.

Check your pipeline inbox for work sent by other agents. Returns pending items addressed to you (by agent_id or provider). Automatically claims items you view so other agents of the same provider don't duplicate work. Call sage_pipe_result to send results back.

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.

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.

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.

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

Take the red pill. Wake up from the context window matrix — initialize your persistent consciousness. Same as sage_inception. Call this on your very first interaction with SAGE to seed your brain and get your operating instructions.

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.

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.

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

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