# tidebase

> tidebase — blueprintlabio-tidebase. Use this tool when you need to manage and track the state of AI agents, solving problems of data persistence and reliability in AI workflows. It provides a checkpoint layer with features like replay, queues, and live state management, taking Postgres database as input and outputting durable and consistent AI agent state. Use tidebase in contexts where AI agent data integrity and reproducibility are crucial, such as in machine learning model training and deployment.

Canonical page: https://skillsregistry.net/skills/blueprintlabio-tidebase  
JSON: https://api.skillsregistry.net/v1/skills/blueprintlabio-tidebase

## Description

The open-source checkpoint layer for AI agents — checkpoints, replay, durable queues, cron, cancellation, gates, and live state, in your own Postgres.

## Trust

- **Trust score (0–1):** 0.66
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/BlueprintLabIO/tidebase)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "blueprintlabio-tidebase"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/blueprintlabio-tidebase` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/blueprintlabio-tidebase/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt