Giving an AI agent memory of our Twist threads: building a Twist connector for cognee

Description and use

A Twist connector for cognee was built to sync long, slow Twist threads into a single AI memory document, enabling plain‑language queries and accurate recall of decisions without opening Twist.

Problem

Twist threads are long and slow, making it hard to retrieve decisions later; search finds the thread but not the answer.

Outcome

The connector successfully ingests Twist threads as single documents, handles deletions, and allows accurate recall of decisions without opening Twist.

Workflow

• 1. Set up a Twist workspace with a #launch channel and a thread titled "Checkout redesign". 2. Sync the Twist workspace to cognee using the cognee‑community‑connector‑twist. 3. Ask a natural‑language question via cognee’s recall API. 4. Receive the best matching passage from the synced data.
• 5. Delete a thread in Twist, sync again, and confirm the deleted thread no longer appears in recall results.

Evidence

Twist is built for long, slow conversations. Someone opens a thread with a proposal, people reply over two or three days, and somewhere around the fifth comment the actual decision gets made.

Source

You point it at a Twist workspace, it pulls threads and channels into cognee, and then you can ask questions in plain language.

Source

After a sync, this is the document cognee receives for that thread. This is real output from my workspace: ...

Source

These are the results I got on my workspace. I ran this one without an LLM key, in cognee's keyless mode, so recall returns the best matching passage instead of a written answer:

Source

One document per thread, not per comment.

Source

It goes through dlt, with "merge".

Source

So last_updated_ts misses most edits. There is a version field that catches nearly everything...

Source