# ForgeMesh GitHub Signal Intelligence — Sequence Anomaly Detection

> ForgeMesh GitHub Signal Intelligence — Sequence Anomaly Detection is a paid API for AI agents from anomaly.forgemesh.io, paid per call via x402, $0.03/call, status unknown (last checked 2026-09-14).

Analyzes a GitHub repository's event sequences using NASA-derived algorithms to detect anomalies, bot activity, novelty signals, and coordinated activity patterns

## Facts

- Endpoint: POST https://anomaly.forgemesh.io/api/github-watch
- Price: $0.03/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/forgemesh-github-signal-intelligence-sequence-anomaly-detection-047a3eb8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_oLHuI2QO2fo2Z9uEcO_zc

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 forgemesh-github-signal-intelligence-sequence-anomaly-detection-047a3eb8 -d '<json body>'
```

Example prompt: Can you run an anomaly analysis on vercel/ai and tell me if there's anything unusual going on — like coordinated bot activity, a merge rush, or weird event sequences?

## When to prefer this

Use this endpoint when you need real-time sequence anomaly detection on a specific GitHub repository — particularly when investigating bot activity, coordinated merge campaigns, unusual contributor patterns, or novelty signals in open source projects. Prefer this over generic GitHub API calls when you want a pre-scored, narrative-labeled intelligence summary rather than raw event data.

## Known failure modes

- Invalid or non-existent repo format returns an error
- Private repositories may not be accessible or return empty results
- Rate limiting or payment failure (x402 micropayment not processed) blocks the request
- Repos with very low activity may return low-confidence scores
- Missing required 'input' object returns schema validation error

## How this service works

Watch a GitHub repo's activity stream for anomalous patterns — commit bursts, force pushes, issue floods, merge rushes, bot takeovers

## Output

Returns a JSON object containing: the repo name, a human-readable story label (e.g. 'Merge Sprint'), a novelty rating (low/medium/high), bot ratio (0–1), a sequence score (integer), total event count, unique actor count, a peak window array of recent event types, and a breakdown of event types (PR_OPEN, PR_MERGE, ISSUE_OPEN, COMMIT_PUSH, etc.).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "repo": {
   "type": "string",
   "description": "GitHub repo in owner/repo format, e.g. vercel/ai"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "repo": "vercel/ai",
  "story": "Merge Sprint",
  "domain": "github",
  "novelty": "medium",
  "bot_ratio": 0.15,
  "peak_window": [
   "PR_MERGE",
   "PR_MERGE",
   "COMMIT_PUSH",
   "PR_MERGE",
   "MERGE_RUSH"
  ],
  "total_events": 87,
  "unique_actors": 12,
  "sequence_score": 52,
  "event_breakdown": {
   "PR_OPEN": 8,
   "PR_MERGE": 12,
   "ISSUE_OPEN": 5,
   "COMMIT_PUSH": 30
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/forgemesh-github-signal-intelligence-sequence-anomaly-detection-047a3eb8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from anomaly.forgemesh.io](https://www.zero.xyz/host/anomaly.forgemesh.io/llms.txt)