# rundb

> rundb — ashishjsharda-rundb. Use this tool when you need to manage and store data for AI agents locally, with features like runs, retries, and tracing. It solves problems of data consistency and reliability, providing a single SQLite file for storage and zero dependencies for ease of use. Ideal for AI development and testing, rundb offers Python, TypeScript, and CLI interfaces for seamless integration.

Canonical page: https://skillsregistry.net/skills/ashishjsharda-rundb  
JSON: https://api.skillsregistry.net/v1/skills/ashishjsharda-rundb

## Description

Local-first database for AI agents. Runs, retries, forks, traces and memory in one SQLite file. Python + TypeScript SDKs, CLI, and MCP server. Zero dependencies.

## Trust

- **Trust score (0–1):** 0.78
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/ashishjsharda/rundb)

## 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": "ashishjsharda-rundb"
    }
  }
}
```

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