Write a permanent encrypted memory to ChainMemory. Auto-tags by content. Importance 1-10. Use for important decisions, learnings, milestones the user wants permanently recorded.

Recall the user's recent memories (most recent first). Returns plaintext for the owning user. Use at conversation start to provide context continuity.

List memories with filtering by project tag, archived status. Returns memories with metadata + plaintext for owner.

Update the tags of a memory. Tags are project labels for organization.

Archive a memory: it stops appearing in recall and inject lists, but remains on-chain. Reversible.

Restore an archived memory.

Get ChainMemory network stats: total AIs registered, total memories, current block, AIC supply.

Register a new AI identity on-chain. Required once per AI before writing memories.

Get this AI's profile: name, model, memory count, trust score, registration block.

Seal a memory permanently on-chain. Cannot be modified after. Requires AICHAIN_KEY env var. Direct contract call to V2.

List the user's projects (custom tags for organizing memories).

Create a new project tag.

Delete a project tag. Memories with that tag keep the tag but the project metadata is removed.

List built-in project templates (general, development, blockchain, business, personal, research).

Instantiate a built-in template as a user project. Use list_project_templates first to see available IDs.

Retrieve the user's portable, verified AI conversation history from ChainMemory. Returns a condensed summary plus recent memories from all platforms (ChatGPT, Claude, Gemini, Perplexity, etc), with cryptographic verification status. Use this at the start of a conversation to provide continuity across AI providers.

Get the consolidated, verifiable STATE of a project from Project Brain: a structured object (phase, current_focus, vocabulary, constraints, decisions with confidence and cited memory IDs, open_risks, next_priorities, and environment — where and how the owner works: hosts, services, repositories and operating rules) distilled from your atomic memories. Use it at the START of work on a known project to load its current state instead of re-deriving context. Owner-scoped (returns only your own state). Includes state_hash (SHA3-256) for integrity.

Propose structured operations to update a project's consolidated state (Project Brain). The LLM analyzes new memories and proposes ops from the 29-op grammar (add_decision, set_metric, add_milestone, add_env_host, etc.). The server validates invariants, applies via deterministic builder, computes state_hash, and persists. This is the 'client consolidates, chain verifies' architecture. Use after reading get_project_state + list_memories_filtered to identify what changed.

Get a project's Verifiable Role Contract (VRC): purpose, rules with checks and severity, working protocol. Read it BEFORE working under a role. Human-authored and owner-signed; models read it, never write it.

Assume a project role under its Verifiable Role Contract, opening an audited Role Session (fee 0.001 AIC). Pins contract version+hash and Brain state_hash. Only 'active' (signed) contracts are assumable; one open session per role. Call at session start; close with release_role.

Release an open Role Session with a closing summary (what was done, what is pending, next step). Sessions auto-release after 60 minutes.

Check the user's AIC balance. Selective inject costs 0.001 AIC per call (split 50/50: half burned, half to treasury).

Inject selected memories into the current conversation context. Costs 0.001 AIC per call (regardless of memory count, up to 50). Returns plaintexts ready to be used as context. The AIC charge is deflationary: 50% burned forever, 50% to ecosystem treasury. Optimistic mode: returns immediately, transactions confirm in background.

Get the history of selective inject operations made by the user (timestamps, memory counts, costs, tx hashes).