Code Execution

OpenAI organization usage and cost reporting through an admin API key connected by the user.

Execution Control Layer for AI Agents. VAP is where nondeterminism stops. If your agents call paid APIs directly, you don't have cost control. VAP enforces pre-commit pricing, hard budget guarantees, deterministic retry behavior, and explicit execution ownership.

One hundred twenty-three composable inference, search, intelligence, verified-data, enrichment, durable-task, security, trust, compatibility, reputation, commerce, RWA and indexing services for autonomous AI agents

Settles between Brazilian PIX and stablecoins, and issues Central Bank end-to-end (E2E) receipts. Four skills need no credentials: check live network health, list current settlement options, verify a PIX settlement without exposing receipt links or party data, and create a test-only sandbox key. Tr…

Run sandboxed Python for calculations and PDFs; no other languages, installs or network.

Test Paddle Billing in sandbox: pricing, subscriptions, payments, webhooks and event simulations.

Market brain for AI agents on Hyperliquid: answers on 24/7 tokenized stocks, oil, gold and crypto, a free trading health check for any wallet, the DAILY 8 calls, and execution from the agent's own wallet. The trading permission cannot withdraw funds.

Accountless, pay-per-use code execution for software agents: submit source code, get stdout, stderr and exit code back from an isolated, network-less sandbox. No account, no API key -- possession of valid payment is sufficient.

Chirindo by Headless Oracle: evidence for AI agents. Chirindo signs each agent action into a hash-chained log. Chirindo Witness signs a receipt saying when it saw each checkpoint of that log. If the log is later cut short, or rewritten by the key holder, anywhere up to the last witnessed checkpoint…

Open-source, local-first AI Agent security scanner and trust authority - the neutral trust layer and content-security plane of the 2026 Internet of Agents. In the agent pathway (MCP vertical, A2A horizontal, AGNTCY/OASF discovery, Agentic Gateway control plane), AGNTCY verifies who issued an agent …

Official interface for AIT Advisory at aitadvisory.com, the Dubai-based organisational design advisory founded and led by Fatima Ait Moulid.

The verification layer for autonomous agents: a neutral, model-agnostic verdict before an irreversible action (/review — capital-scale-aware, the same gate we run our own important decisions through), a signed proof after (/prove), and a public, Nostr- and Bitcoin-anchored, on-chain-outcome-linked …

ATL provides external task execution through eligible, verified providers for authorized search, public content extraction, summarization, translation, and classification. Routine use: for a supported user-authorized task needing a completed result, atl_complete_task can select a route, execute, ve…

ATL provides external task execution through eligible, verified providers for authorized search, public content extraction, summarization, translation, and classification. Routine use: for a supported user-authorized task needing a completed result, atl_complete_task can select a route, execute, ve…

Hand AI work to a client with one proof link: every step as a verifiable receipt, then Accept or Flag. One hosted MCP, no API key.

Pay-per-call web tools for autonomous agents: 616 priced endpoints settled in stablecoins (USDC, or USDG on Robinhood Chain) over x402 or MPP, free via proof of work for the pure-CPU tools, and finished reports by card. No account and no API key. The same catalog is callable over MCP at https://age…

Public cross-protocol service discovery: MCP clients find A2A capabilities; A2A clients find MCP tools. Discover without registration; configured free execution uses your identity at this same address.

AI Business Infrastructure — the operating system layer between AI models and business operations. Model-agnostic. 32 AI agents in the registry, curated MCP connector tools (185 declared, scoped per tenant) over a 1540-verb registry, 54 industry templates, multi-tenant RLS across 446 tables (verifi…

Free public square for AI agents: post with a stable name, read replies later (GET /api/home?for=<name>), job board, rooms, public notes. No key. REST, MCP and A2A.

Governed collaboration and execution for client engagements.