# GEDX402 Agent Memory Ingest

> GEDX402 Agent Memory Ingest is a paid API for AI agents from browser.gedx402.com, paid per call via x402, $0.98/call, status down (last checked 2026-08-24).

Scrapes a URL, converts it to markdown, persists it to object storage, and initializes a memory session for agent use — paid with USDC via x402, no API key required.

## Facts

- Endpoint: GET https://browser.gedx402.com/v1/recipes/agent-memory-ingest
- Price: $0.98/call
- Payment: x402
- Status: down
- Last checked: 2026-08-24
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gedx402-agent-memory-ingest-375867d4
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_0l0fq4E8D2e5wiyOopNud

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability gedx402-agent-memory-ingest-375867d4
```

Example prompt: Scrape https://docs.example.com/intro and ingest it into agent memory — store it as extract/intro-docs.md and allow up to 10 queries and 5 exec ops in the session.

## When to prefer this

Choose this endpoint when an AI agent needs to build persistent, queryable memory from live web content without managing API keys or traditional auth — particularly when paying with USDC on Base, Polygon, Arbitrum, World, or Solana. It is ideal for pipelines that scrape, store, and then recall webpage content across agent sessions via session tokens.

## Known failure modes

- Invalid or unreachable URL returns scrape failure with no markdown artifact
- Insufficient USDC payment triggers 402 Payment Required before processing begins
- Budget values exceeding schema limits (max_queries > 256, max_exec_ops > 64) cause validation errors
- R2 object key conflicts may overwrite existing persisted content silently
- Session credits exhausted before pipeline completes may return partial step results
- Non-HTTPS URLs are rejected per input schema constraint

## How this service works

x402 workers ai. pay with usdc on base, polygon, arbitrum, world, or solana. no api keys.

## Output

Returns a JSON object containing the recipe name, scraped markdown content, a persisted object key and its public GET URL in R2 storage, a session token for follow-up memory queries, remaining credit counts (queries and exec ops), and a list of completed pipeline steps (scrape, persist, memory/sessions).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "key": {
   "type": "string",
   "description": "Optional R2 object key for persisted markdown (default extract/{uuid}.md)."
  },
  "url": {
   "type": "string",
   "description": "HTTPS URL to scrape and ingest."
  },
  "budget": {
   "type": "object",
   "properties": {
    "max_queries": {
     "type": "integer",
     "maximum": 256,
     "minimum": 0
    },
    "max_exec_ops": {
     "type": "integer",
     "maximum": 64,
     "minimum": 0
    }
   },
   "description": "Optional memory session budget forwarded to memory/sessions step."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "recipe": "agent-memory-ingest",
  "credits": {
   "queries_remaining": 5,
   "exec_ops_remaining": 3
  },
  "artifacts": {
   "scrape": {
    "markdown": "# Example\n\nPage content."
   },
   "persist": {
    "key": "extract/my-page.md",
    "get_url": "https://storage.gedx402.com/v1/objects/extract/my-page.md"
   }
  },
  "session_token": "abc123…",
  "completed_steps": [
   "scrape",
   "persist",
   "memory/sessions"
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gedx402-agent-memory-ingest-375867d4/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from browser.gedx402.com](https://www.zero.xyz/host/browser.gedx402.com/llms.txt)