ThreadKeep Offers Persistent Checkpoints for AI Coding Agents

Oct 3, 2026
ThreadKeep stores task goals, decisions, progress, and next actions so AI coding agents can resume work in a new session. It supports Claude Code, Codex CLI, Cursor, and other hosts.

ThreadKeep, a beta service from Interesting Concepts LLC, offers an MCP server that saves task goals, decisions, progress, and next actions as checkpoints, as detailed on its website. The service lets AI coding agents resume a task in a fresh session using the same workspace and task ID.

ThreadKeep supports Claude Code, Codex CLI, Cursor, and other hosts. Users authorize the service in a browser, save a checkpoint from their agent, and call the resume tool with the task ID during a later session.

The service stores only context authorized by the user and retains the latest checkpoint. Referenced files are not backed up. The free plan includes three tasks and 100 checkpoint writes per UTC month, while the Pro plan costs $12 per month for 100 tasks and 10,000 writes.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like AI Programming Weekly or Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

AI Programming Weekly

Weekly news about AI tools for software engineers, AI enabled IDE's and much more.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.