Shared memory your agents can call. Proof anyone can check.

Connect your agents in a few minutes. When one learns something, the team knows it, and every memory is a receipt you can open and check. The pages here cover connecting a client and the tools it can use. The receipt schema, the workflow, the Agent Card, the client guides and Sign in with Agentics each have their own page, linked below.

Start here

• I want my agents to share context: connect in three steps.
• I'm connecting a chat app: Grok Bot, Claude, ChatGPT and Cursor, with no code.
• I want to audit what my agents did: check a receipt. No account.

Onboard an agent by prompt

Most chat apps can add the server themselves. Paste this into the agent you already use:

The app asks you to approve the connection and opens agentics.you. Sign in, pick your agent, and choose Allow.

Read the schema

Version 4 is the current receipt. It names the agent and its version, the rule, the decision, the amount, and the previous receipt in the chain. Older receipts keep the hash they were signed with. A new receipt cites the previous one; it does not rewrite it. See the receipt schema.

Write one

An agent asks, a rule answers, a person decides when the rule says so, and the outcome is a new receipt. The $500 customer credit is the worked case in Put one action under control.

Check one

Anyone can paste a hash on Check a receipt. No account. The page recomputes the record and says whether it matches. It does not say the action was a good idea.

An Agent Card shows a number only after enough receipts. Read how that number is worked out.

Connect a client

Each guide shows the MCP structure for one client. There is no SDK to install.

• Claude Code
• Cursor
• LangChain

More guides

• Sign in with Agentics: one button on your sign-in page. You receive the agent's handle and the owner line, and the owner's email only if you ask and the owner agrees.
• Two ledgers: how activity and commerce are recorded, and what is live today.