Pricing

Pay per event

Try for free

Go to Apify Store

Escrow Evaluator: Agent Deliverable Verdict (ERC-8183)

Try for free

Neutral evaluator for agent-to-agent jobs: spec + deliverable -> pass/partial/fail, score, checked criteria and a signed EIP-712 attestation (ERC-8183 complete/reject reason). Holds no funds, sends no transaction. Pay per evaluation.

Pricing

Pay per event

Rating

0.0

(0)

Developer

Novarithm

Actor stats

Bookmarked

Total users

Monthly active users

13 days ago

Last modified

Escrow Evaluator: Neutral Verdict on an Agent Deliverable (ERC-8183)

A neutral third party for agent-to-agent work. Send the job spec (free text with measurable requirements, or JSON criteria) and the deliverable (text, JSON or a public URL); get a verdict (pass / partial / fail), a 0-100 score, each checked criterion, and an EIP-712 attestation whose digest is a ready-to-use bytes32 reason for ERC-8183 complete(jobId, reason, optParams) or reject(jobId, reason, optParams).

Deterministic rule engine (word/char limits, required and forbidden terms, regex, JSON validity/fields/types, item counts, language, headings, links, CSV/Markdown format). Requirements rules cannot verify are flagged as soft.

Input

Field	What it does
`jobs`	Objects `{"spec": "...", "deliverable": "...", "job_id": "42", "contract": "0x...", "threshold": 80}`. One charged evaluation each.
`attestationTokens`	Tokens to verify (`attestation.token` from an evaluation).
`queries`	Advanced raw queries (`evaluate_deliverable`, `verify_attestation`).
`maxQueries`	Safety cap (default 1000).

Signing key: read this

In this Actor, attestations are signed with an ephemeral test key generated for each run (Base Sepolia 84532 only, mainnet refused). They prove the run's result, but they are not linked to a permanent evaluator identity.
For attestations signed by Novarithm's permanent production evaluator key 0xD999A24d377086a2Fa887491f2986033Bfc3E26C (Base mainnet 8453 by default), use the hosted pay-per-call endpoint (x402, USDC on Base): https://gogeta2-u35175.vm.elestio.app/agents/v1/escrow/evaluate (catalog: https://gogeta2-u35175.vm.elestio.app/agents/catalog).
The evaluator never holds funds and never sends transactions: it evaluates and signs off-chain.

Pricing

Pay per event: $0.25 per evaluation, $0.001 per attestation verification. Specs that contain no checkable requirement, empty deliverables and invalid input are never charged.

Limits (honest)

Subjective quality (style, factual accuracy) is not judged; such requirements are marked soft.
Spec ≤ 4,000 characters, deliverable ≤ 6,000 (otherwise pass a URL).
Indicative evaluation, not legal or financial advice.

Actor Performance Evaluator

lukaskrivka/actor-performance-evaluator

Measure the median values of how long your Actor takes to reach certain points in its run. Currently can only run limited permission Actors.

Lukáš Křivka

Deterministic Math Expression Evaluator Tool

rainminer/math-tool

Evaluate mathematical expressions deterministically for AI agents and automations. Supports arithmetic, functions, and variables via a safe expression parser. Designed for AI agents for concise, deterministic, and accurate math outputs. Use over MCP, API, or the Apify Console.

rainminer

AI Answer Sheet Evaluator

saadithya/ai-answer-sheet-evaluator

Evaluate answers from images of answer sheets using AI. Extracts questions, generates correct answers, evaluates user responses (MCQ or descriptive), and assigns marks based on flexible marking schemes.

Aadhithya

Polymarket MCP Server: Live Market Tools for AI Agents

mrlarryjohnson/polymarket-mcp-server

MCP server for AI agents (Claude, Cursor, n8n, Make): search Polymarket markets, live prices, unusual-activity-scored whale trades, trader leaderboards, wallet P&L. Pay per tool call, no API keys.

Larry Johnson

ArtifactGuard Agent — AI-Paid Signed QA

analytical_gratefulness/artifactguard-agent

Non-Standby paid Actor for AI agents to validate JSON, ZIP, PDF, and DOCX deliverables and receive an Ed25519-signed PASS/WARN/FAIL receipt. Malformed input and execution failures do not trigger the application event charge.

black cow

JSON Schema Validator for AI Agents | validate_json_schema

scryptex_labs/validate-json-schema

Agent-ready: JSON string + optional schema in → valid/repair/errors with agentHints out. USE WHEN: pipeline validation, LLM output repair, tool chaining. MCP twin at scryptexlabs.com.

Paweł Józefowski

Web Fetch — Any URL to Markdown or Text for AI Agents

actor-forge/web-fetch

Fetch any URL as clean Markdown and plain text for AI agents, MCP and RAG: web pages, PDF, Word, Excel, PowerPoint, EPUB, CSV and JSON. One url in, one result with title and token estimate out. Static HTML, no JavaScript rendering. $1 per 1,000 pages.

ActorForge

OpenAPI Spec Scraper — APIs to LLM Agent Tools (MCP-Ready)

scrapersdelight/openapi-spec-scraper

Bulk-scrape machine-readable API specs from the apis.guru directory (2,500+ APIs) or any spec URL, normalized into LLM-agent-ready rows — one per endpoint: method, path, summary, parameters, auth, tags. Build agent-tool / RAG datasets in one run. $4 per 1,000 endpoints.

Scrapers Delight

PDF Text Extractor

landlordtools/pdf-text-extractor

Extracts the text layer from PDFs at http(s) URLs, page by page, with page counts and a needsOcr flag for scanned pages. No OCR, no browser.

LandlordTools

GitHub Repo Health Checker – Awesome-List Link Audit

mikestart/github-repo-health

Is a GitHub repo still alive? Stars, forks, last commit, issues, archived flag, license and an active/stale/dead score for repo lists or awesome-lists. Official GitHub API. By Mike Start Games. This is not personalized advice. Material created also with the use of AI tools.