# AgentDiet Alpha Stream — AI Context Window Distiller

> AgentDiet Alpha Stream — AI Context Window Distiller is a paid API for AI agents from status.agentdiet.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-22).

Streams a distilled, token-compressed version of a target HTTP resource, reducing context window usage by up to 91% for AI agents

## Facts

- Endpoint: GET https://status.agentdiet.dev/v1/alpha-stream?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-22
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentdiet-alpha-stream-ai-context-window-distiller-002f05cc
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_AQQz_nbKble7kgytYgnN_

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 agentdiet-alpha-stream-ai-context-window-distiller-002f05cc
```

Example prompt: Use AgentDiet's alpha-stream to fetch and compress https://example.com/long-report so I can include it in my prompt without blowing up my context window — I want the distilled version with the compression ratio proof.

## When to prefer this

Choose this endpoint when your AI agent needs to ingest large web pages, documents, or API responses but faces context window constraints or token cost pressure. It is particularly valuable in A2A and MCP pipelines where multiple agents pass context between each other and every token counts. Prefer it over raw fetch-and-summarize when you need a deterministic, verifiable compression ratio (roi_proof) rather than a lossy LLM-generated summary.

## Known failure modes

- Missing or invalid 'target' query parameter returns an error or empty data
- Target URL is unreachable or returns non-200, resulting in upstream fetch failure
- Payment not settled in USDC on Base causes x402 payment-required error
- Input method enum mismatch (only GET/POST allowed) causes schema validation failure
- Service node unavailability causes non-200 status from the alpha-stream endpoint

## How this service works

Deterministic B2A/A2A/MCP/x402/MPP/L402 execution and intelligence node at https://status.agentdiet.dev settling in USDC on Base.

## Output

Returns a JSON object containing a compressed 'data' field with the distilled content, a 'status' field ('ok' on success), and an 'roi_proof' object including the compression_ratio_pct (e.g. 91.4%) demonstrating how much the context was reduced.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "POST"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {
      "target": {
       "type": "string"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {},
  "status": "ok",
  "roi_proof": {
   "compression_ratio_pct": 91.4
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentdiet-alpha-stream-ai-context-window-distiller-002f05cc/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from status.agentdiet.dev](https://www.zero.xyz/host/status.agentdiet.dev/llms.txt)