Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Bilinc: shared memory for your AI agents

    1

    One memory that Claude, ChatGPT, Codex and Cursor share. Every change is dated, shows which agent wrote it, and can be undone.

    Free

    Security scanned
    Bilinc: shared memory for your AI agents

    Bilinc: shared memory for your AI agents

    Example session with this skill installed

    We decided on the call that Harbor 2.0 launches on November 12. Remember that.

    • Read your context and instructions
    • Compiled the bilinc

    Summary: Bilinc already had a different launch date, so I checked with you before changing it.

    StepToolWhat happened
    1recall "Harbor 2.0 launch date"Found project.harbor.launch_date = "November 19", source: a forwarded draft, with its version
    2noneAsked you which date is right, showing both values and their sources
    3revise with the expected_version from step 1Set it to "November 12", reason: "decided on the call"

    What I asked before changing anything:

    Bilinc has November 19 from a forwarded draft. You're saying the call set November 12. Should I replace it?

    After you said yes: the entry now reads November 12. The old value, November 19, stays in the history: diff against a checkpoint shows the change, and preview_rollback followed by rollback can restore it if the plan changes again.

    Next steps

    1. Your other connected agents (Claude, Codex, Cursor) now recall November 12, with its source and date.
    2. Before a bigger batch of memory changes, say "take a checkpoint" and I will run create_snapshot first.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Setup required: this skill works only after you connect Bilinc's hosted MCP server, https://mcp.bilinc.space/mcp, in your own agent. Sign in with OAuth in the browser (no API key in any config file) and pick read-only or read and write. Step-by-step lines for Claude Code, Codex, Cursor and Claude are in the skill's Setup section and at https://bilinc.space/mcp.

    Your agents forget what they decided, and each tool keeps its own memory. Bilinc gives them one memory they share.

    This skill teaches your agent when to recall earlier decisions, how to save what you confirm, how to correct a fact without losing the old version, and how to compare or undo changes with checkpoints.

    • Works in Claude Code, Claude Desktop, claude.ai, Codex, Cursor, ChatGPT and other clients that support remote MCP servers with OAuth.
    • Free plan: 2,000 operations a month, no card.
    • Network: only your own Bilinc MCP connection. No scripts, no credentials in the skill.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Needs a Bilinc account and a one-time OAuth sign-in in each client. A read-only connection can recall, diff and list checkpoints but cannot save or change memory. Not for secrets, API keys or private personal data.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 7 days ago

    • Free with an Agensi account

    Accounts
    BilincFree Bilinc account

    Connect https://mcp.bilinc.space/mcp in your agent and sign in with OAuth. One line per client is in the skill's Setup section.

    Permissions

    Network Access

    Allowed Hosts

    bilinc.space
    Listed7 days ago

    What's inside

    Frequently Asked Questions

    Every connected app reads and writes the same Bilinc workspace. A decision saved in Claude is there when Cursor or Codex recalls it, with its source and when it last changed.

    Claude Code, Codex, Cursor, Claude (web, desktop and mobile), ChatGPT and other clients that support remote MCP servers with OAuth sign-in. One line per client is in the skill's Setup section and at https://bilinc.space/mcp.

    remember never overwrites an existing key. revise takes the expected_version from recall, so a newer value is not silently replaced, and the old value stays in history. diff shows what changed, and preview_rollback then rollback restores a checkpoint after you agree.

    A Bilinc account (the free plan is 2,000 operations a month, no card) and one connection per client to https://mcp.bilinc.space/mcp. You sign in with OAuth in the browser, pick a workspace and choose read-only or read and write.

    Yes: never store secrets, passwords, API keys, tokens, cookies or private personal data. The skill tells the agent to keep those out and to save only decisions and facts you confirmed.

    New in Agents & Orchestration

    Free