Memory for
AI agents

• Decisions

  What was chosen and why. When the team changes its mind, the old decision is marked superseded and the new one says what it replaces, so the reasoning is never lost.

• Events

  Shipped changes and incidents, with the time they happened and a link to the commit or pull request.

• Tasks, risks and blockers

  What is still open, with status and priority, until someone closes it. The next session starts from this list instead of from scratch.

• Metrics

  Numbers that were actually checked, with their unit and when they were observed.

• Sources

  The Slack message, email thread or document a fact came from, cited by the events and decisions that rely on it.

• Links

  Records point at each other: a change implements a decision, a blocker holds up a task, a new decision replaces an old one. A link can also point into another .gram document.

1. One memory per project

   Each git repository uses the Thegram folder with the same name, and its worktrees share it. Any directory can be mapped to another folder in ~/.config/thegram-memory/projects.json.

2. A brief when the session starts

   Before a coding agent answers for the first time, the plugin gives it the project's brief: its documents, the open risks and tasks, and the records that match your first prompt. Later prompts bring what other agents and people changed in the meantime. In ChatGPT, once you pick the plugin in a chat, it reads the memory before it answers.

3. Look up, then read only what is needed

   The agent searches the memory and reads the few records or sections it needs, instead of loading a whole notes file into its context.

4. Every write is a revision

   A write names the revision the agent read. If someone else changed the file in between, the write is refused instead of overwriting, and the agent reads again first. Several agents can work on the same project without losing each other's records.

5. One reminder, not a nag

   If a coding agent's turn edits files or makes a commit without recording anything, the plugin reminds it once to write down what changed.

6. Ask about the past

   The agent can read the project as it was on any date, or see when and why a decision changed before it reopens the question.

1. Install the plugin

   For Claude Code, run these two lines in Terminal, then start a new session. The install guide has the lines for Codex, OpenCode and OMP, and a button in the app that does it for you.

   claude plugin marketplace add clab-one/thegram-mcp claude plugin install thegram-memory@thegram-memoryCopy

2. Or hand it to your agent

   Paste this into a new session. The agent checks your Mac, installs the plugin and tells you what it needs from you.

   Install Thegram by following https://thegram.one/install/agents.mdCopy

3. Check that it remembers

   Start a session inside a project folder and ask:

   What does Thegram remember about this project?Copy

Full Mac install guide

1. The server

   Streamable HTTP with OAuth sign-in. In ChatGPT, add it as a custom MCP server; the install guide shows every click.

   https://vault.thegram.one/mcpCopy

2. Claude Code off your Mac

   Add the same server, then sign in from /mcp.

   claude mcp add --transport http thegram https://vault.thegram.one/mcpCopy

Add Thegram to ChatGPT, step by step

• gram_projects · gram_brief

  Which folders, vaults and Google Drive accounts the agent can reach, and one call to get oriented in a folder or a document.

• gram_recall · gram_context

  Search by relevance with date filters, then read many records in one call.

• gram_read · gram_get · gram_list

  One section of a document, one record, or the records that match a type, status, tag or date.

• gram_create · gram_patch

  Create a document, or change one against the revision the agent read.

• gram_changes · gram_range

  What changed since a time or revision, and when and why one thing changed.

• gram_state · gram_relations

  A document as it was at a revision or a date, and the links around one record.