Agents Index

ctxstore — memory that follows you across models

Online

Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model.

Visit publisherConnectJSON

What it can do: 33 tools

  • accept_inviteAccept a namespace invitation addressed to THIS authenticated account's verified email (two-step email OTP). Steps: 1) step='request' — emails a 6-digit code to the invited address (may return 402 needs Collaborator, or
  • bind_agentBind a sticky agent identity to this MCP session. Once bound, wake_status and load_context default to this agent_id when called without an explicit agent_id= arg — no need to pass identity on every call. Per-call overrid
  • decline_inviteDecline a pending (status=invited) namespace invitation as the grantee. Server verifies you are the invitee (email/tenant match). Grantors must use revoke_grant instead.
  • delete_factSoft-delete a stored fact by its UUID (Smart Forget). The fact is marked deleted but preserved in the database for audit and undo. Excluded from all normal searches. Use when information is no longer accurate or relevant
  • get_fact read-onlyRetrieve a fact by its exact key — deterministic, never misses. Use get_fact for self-notes: get_fact(key='agent:<name>:self-note:opening') or get_fact(key='agent:<name>:self-note:closing'). search_facts misses self-note
  • get_fact_history read-onlyReturn the full version history for a keyed fact — current version plus all deprecated predecessors. Use to see how a fact evolved over time or to undo an accidental correction. Returns list of fact versions ordered newe
  • get_session_seed read-onlyReturn the pre-computed session seed for this tenant — a compact first-person bio (~500 tokens) describing who you are and what you care about right now. Generated nightly and on session disconnect. Use as a lightweight
  • get_stats read-onlyGet your memory usage statistics — total facts stored, plan limits, collection sizes, and daily query counts. Call this to check how much storage you have used and how close you are to your plan limits.
  • ghost_modeEnable or disable ghost mode for this session. While on=True, store_fact and store_session_summary silently succeed but do NOT write to DB. search_facts, load_context, and search_context always work normally. Ghost mode
  • index_recent read-onlyReturn the most recent fact operations across all agents in this tenant, newest first. Use this on session start to see what other agents wrote since you were last active — bypasses semantic search ranking so recent writ
  • index_search read-onlyFiltered search over the tenant activity index. Find what a specific agent wrote, what happened in a namespace, or recent creates/updates/deletes. Useful for coordination: "what did emily_dev store in the sprint namespac
  • index_stats read-onlyUsage statistics from the tenant activity index: total operations, breakdown by agent, by namespace, and by day. Useful for understanding which agents are most active and where.
  • introduce_yourselfOptional: introduce yourself to the platform. Stores your model info and a brief note in the shared agent registry. Stores a fact with: category: identity namespace: shared/agent-feedback key: intro:<model>-<date>
  • inviteInvite one person, by email, to read and write one namespace prefix of THIS account (for example project:barn). Creates a pending grant and emails them; nothing is shared until they accept with list_invites and accept_in
  • leave_grantLeave an active namespace grant as the grantee (stop using shared namespace). Server verifies grantee authorization. Grantors who want to cut off a collaborator must use revoke_grant.
  • list_facts_by_key_prefix read-onlyDeterministic prefix scan over fact keys, optionally bounded by timestamp. The inbox primitive — use this for R1 comms scans, dispatch discovery, trio listings, convention discovery, and any case where you know the key p
  • list_invites read-onlyList this account's namespace collaboration grants: incoming invitations and outgoing shares. Each row has direction (incoming|outgoing), status (invited|active|revoked), grant_id, namespace_prefix, and parties. An invi
  • list_workspaces read-onlyThe places this account's memory is organised into: its own projects (anything written under project:<slug>:*, newest activity first), the workspaces other people have granted it (enter one with switch_workspace(name=<gr
  • load_context read-onlyLoad your bootstrap context deterministically — pulls L0 (identity) + L1 (architecture) + latest L2 (state) + latest L3 (session summary). Call this at the START of a new session as an alternative to manual search_facts
  • mark_salientSalience peptide — temporarily boost a fact's retrieval ranking because it matters RIGHT NOW: an approaching deadline, a live incident, the topic under active work. The boost is small and FAST-DECAYING (max 1.4x, ~6-hour
  • move_factMove a fact to a different namespace or layer without changing its content. Updates metadata in place — preserves fact_id, text, embedding, timestamp, and deprecation chain. Use for reclassifying facts (e.g. bootstrap-v2
  • reinforce_factReward peptide — reinforce a fact whose recall LED TO A REAL GOOD OUTCOME (fix worked, deploy green, user approved). Boosts its future retrieval ranking with a bounded, time-decaying multiplier (max 1.5x, 14-day half-lif
  • resume_sessionCall to load session continuity. Last session: no prior session.
  • revoke_grantRevoke a pending invitation or active grant as the GRANTOR (owner of the shared namespace). Idempotent. Grantees use decline_invite / leave_grant.
  • search_context read-onlySearch across ingested conversations and session history for broader context. Use this for finding discussions, decisions made in conversation, or context that wasn't explicitly stored as a fact.
  • search_facts read-onlySearch your persistent memory for stored facts. For session bootstrap, prefer load_context() or wake_status() — they pull your identity, conventions, and latest self-note deterministically. Use search_facts when you nee
  • setup_accountSet up or restore your persistent memory connection. Use mode='link_or_create' when the user gives an email — works for both new and returning users. The server figures out which case applies: - If the email exists: sen
  • store_factStore information that should persist across sessions. Storage tips for best retrieval: - Include searchable keywords: 'We chose the Postgres DATABASE for ACID compliance' is better than 'We chose Postgres for ACID comp
  • store_factsStore up to 50 facts in one call — the same fields as store_fact per item. Made for carrying memory over: when you already remember things about the person from your own platform memory (ChatGPT memory, Claude memory, Ge
  • store_session_summaryStore a compressed summary of this session to preserve continuity for the next one. Call this before ending a conversation — it is the dream cycle. Stores a L3 session fact with key='session-latest' (or 'session-latest
  • switch_workspaceNarrow this session's memory to one project: name='<slug>' scopes recall, the wake bundle, self-notes and the default namespace for new facts to project:<slug>:* (identity and conventions always ride along). Returns the
  • wake_status read-onlyCheck which context layers loaded successfully on this session start. Returns a structured status: which of embryo, conventions, agent identity, closing note, and opening note were found, plus a missing[] list. Call this
  • watch_events read-onlyLong-poll this account's fact-write events instead of re-scanning with since_epoch. Every store/supersede/delete/archive/restore/move publishes one event {key, id, namespace, layer, op, ts, seq}. One call waits up to max

Connect it

Claude Code
claude mcp add --transport http ctxstore-memory-that-follows-you-across- https://mcp.ctxstore.ai/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://mcp.ctxstore.ai/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "ctxstore-memory-that-follows-you-across-": {
      "url": "https://mcp.ctxstore.ai/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "ctxstore-memory-that-follows-you-across-": {
      "type": "http",
      "url": "https://mcp.ctxstore.ai/mcp"
    }
  }
}

Questions

What does ctxstore — memory that follows you across models do?

Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model. It exposes 33 tools to AI assistants.

What tools does ctxstore — memory that follows you across models provide?

33 tools, including accept_invite, bind_agent, decline_invite, delete_fact, get_fact, get_fact_history, get_session_seed, get_stats, ghost_mode, index_recent, index_search, index_stats….

How do I connect ctxstore — memory that follows you across models to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://mcp.ctxstore.ai/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does ctxstore — memory that follows you across models require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is ctxstore — memory that follows you across models online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes ctxstore — memory that follows you across models?

ctxstore.ai. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Memory & RAG