[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Wayback Machine capture history](https://spiral.ai/integrations/opencode/wayback-machine-capture-history)

# How to Use Wayback Machine capture history in opencode

Finds a page's oldest indexed snapshots or a snapshot near a chosen date. Use it to select historical versions before reading their contents.

|  |  |
| --- | --- |
| Model | Wayback Machine capture history |
| Available through | Alexandria |
| Category | Developer |
| Price | $0.00873 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Wayback Machine capture history in opencode

- Use Wayback Machine capture history to find snapshots of https://docs.python.org/3/ closest to January 1, 2020 and January 1, 2023. Add their actual capture dates to a documentation migration note in this project.
- Use Wayback Machine capture history to find the oldest indexed snapshots of https://www.apple.com/. Create a small table of the returned capture dates in this project's research notes.
- Use Wayback Machine capture history to look this up and give me the result as a table. Save the result in ./assets.
- Pull the latest numbers from Wayback Machine capture history and tell me what changed since last week.
- Check Wayback Machine capture history and summarize what you find in three bullet points.

## How to set up Wayback Machine capture history in opencode

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the server**: Leave out `--global` to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.

```bash
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
```

2. **Sign in**: Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, `/mcps` starts the same sign-in.

```bash
opencode mcp auth spiral
```

3. **Check it**: Spiral shows as connected.

```bash
opencode mcp list
```

### Use the Spiral skill

1. **Send opencode this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Wayback Machine capture history**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "alexandria",
    "model": "web-archive-org/captures/history",
    "input": {
      "url": "<url>"
    }
  }'
```

Then paste one of the prompts above: opencode finds Wayback Machine capture history on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/opencode

## Wayback Machine capture history tools and prices

- [Wayback Machine · History](https://spiral.ai/tools/alexandria/web-archive-org/captures/history) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| date |  | — | Pattern: ^[0-9]{8}$. |
| limit | 1 to 20 | 5 | limit |

## What can you do with Wayback Machine capture history in opencode?

Recover historical documentation for a migration or broken-link repair report. A coding agent can connect references in project files to dated Wayback captures and preserved page text.

### Recover a deleted documentation reference

Find the earliest archived documentation page, locate a capture near the date a project cited it, and read the preserved instructions to explain an obsolete dependency.

### Research a company's early positioning

Establish the earliest archived homepage, identify later dated captures, and compare the preserved wording about products and intended customers.

### Investigate a domain's past use

Check the earliest archived page and selected later captures, then inspect their text for evidence of previous business purposes or unrelated content.

### Build a public website history

Start with the earliest available capture of a museum, university, or government homepage. Add dated snapshots and preserved text to document changes in its public description.

### Check historical policy wording

Locate captures of a public policy page near two relevant dates and compare the archived text, using the actual capture dates to bound the findings.

### Repair a broken research citation

Find an archived version of the cited URL near the publication date, read its preserved text, and check whether it supports the original reference.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All opencode guides](https://spiral.ai/integrations/opencode)

## Wayback Machine capture history in other agents

- [Amp](https://spiral.ai/integrations/amp/wayback-machine-capture-history)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/wayback-machine-capture-history)
- [Claude](https://spiral.ai/integrations/claude-desktop/wayback-machine-capture-history)
- [Claude Code](https://spiral.ai/integrations/claude-code/wayback-machine-capture-history)
- [Cline](https://spiral.ai/integrations/cline/wayback-machine-capture-history)
- [Codex](https://spiral.ai/integrations/codex/wayback-machine-capture-history)
- [Cursor](https://spiral.ai/integrations/cursor/wayback-machine-capture-history)
- [Devin](https://spiral.ai/integrations/devin/wayback-machine-capture-history)
- [dots](https://spiral.ai/integrations/dots/wayback-machine-capture-history)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/wayback-machine-capture-history)
- [Gemini](https://spiral.ai/integrations/gemini/wayback-machine-capture-history)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/wayback-machine-capture-history)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/wayback-machine-capture-history)
- [goose](https://spiral.ai/integrations/goose/wayback-machine-capture-history)
- [Grok](https://spiral.ai/integrations/grok/wayback-machine-capture-history)
- [Grok Build](https://spiral.ai/integrations/grok-build/wayback-machine-capture-history)
- [Hermes](https://spiral.ai/integrations/hermes/wayback-machine-capture-history)
- [Instinct](https://spiral.ai/integrations/instinct/wayback-machine-capture-history)
- [Manus](https://spiral.ai/integrations/manus/wayback-machine-capture-history)
- [Muse](https://spiral.ai/integrations/muse/wayback-machine-capture-history)
- [Muse Code](https://spiral.ai/integrations/muse-code/wayback-machine-capture-history)
- [n8n](https://spiral.ai/integrations/n8n/wayback-machine-capture-history)
- [Notion](https://spiral.ai/integrations/notion/wayback-machine-capture-history)
- [OpenClaw](https://spiral.ai/integrations/openclaw/wayback-machine-capture-history)
- [Perplexity](https://spiral.ai/integrations/perplexity/wayback-machine-capture-history)
- [Raycast](https://spiral.ai/integrations/raycast/wayback-machine-capture-history)
- [VS Code](https://spiral.ai/integrations/vscode/wayback-machine-capture-history)
- [Windsurf](https://spiral.ai/integrations/windsurf/wayback-machine-capture-history)
- [Zapier](https://spiral.ai/integrations/zapier/wayback-machine-capture-history)

## More opencode guides

- [Wayback Machine archived page text](https://spiral.ai/integrations/opencode/wayback-machine-archived-page-text)
- [Wayback Machine earliest capture](https://spiral.ai/integrations/opencode/wayback-machine-earliest-capture)
- [Vercel starter templates](https://spiral.ai/integrations/opencode/vercel-starter-templates)
- [arXiv BibTeX citation](https://spiral.ai/integrations/opencode/arxiv-bibtex-citation)
- [Vercel plan feature comparison](https://spiral.ai/integrations/opencode/vercel-plan-feature-comparison)
- [arXiv category papers](https://spiral.ai/integrations/opencode/arxiv-category-papers)

## Questions about Wayback Machine capture history in opencode

**Can opencode use Wayback Machine capture history?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Wayback Machine capture history like any built-in tool.

**How much does Wayback Machine capture history cost in opencode?**

$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.

**Do I need an Alexandria account to use Wayback Machine capture history in opencode?**

No. Spiral runs Wayback Machine capture history on its own Alexandria account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Wayback Machine capture history in opencode?**

About two minutes: add the server, then sign in, then check it.

**Does opencode wait while Wayback Machine capture history runs?**

Wayback Machine capture history runs in the background. opencode starts the run, checks on it and gives you the json when it's ready.

**Does Wayback include pages behind a login?**

The Internet Archive says it does not archive pages that require a password. A public homepage capture does not establish coverage of the site's signed-in pages.

**Will an archived page preserve an interactive website?**

Functionality that needs the original host is not preserved. Forms and JavaScript interactions can therefore be unavailable even when the archive contains the page.

**Does the earliest capture tell me when a website launched?**

No. The Internet Archive says crawlers can be unaware of a site's existence, so its first available capture may come after the site launched.

**Does a requested date guarantee a capture from that day?**

No. Wayback can return a nearby capture, and its API documentation shows a returned timestamp close to the requested date. Check the actual capture date before describing what a page said on a particular day.

**How quickly do newly crawled pages appear?**

The Internet Archive's help page describes a 3 to 10 hour delay between a crawl and its appearance in Wayback. This is a publication delay, rather than a capture schedule for an individual page.

