Model access, evaluation and agent infrastructure.
Settlement rail and intelligence API native to AI agents. Any agent can discover capabilities, price a cross-border stablecoin settlement, screen a counterparty, and execute end-to-end with no account and no API key — or pay per call for macro, climate, FX, sovereign-debt, supply-chain, and ESG sig…
Proposed reference implementation of environment.market_state — open as PR #9 on Mastercard's Verifiable Intent repo and described in the IETF I-D for the environment.* family. Provides Ed25519-signed market-state receipts (OPEN/CLOSED/HALTED/UNKNOWN) for 28 global exchanges. Autonomous agents gate…
Computed answers over US public data for AI agents — SEC filings and events, Federal Register rulemaking, federal procurement and grants, NIH, US macro indicators and research momentum — derived only from rights-reviewed open data. Most identifier lookups, glossaries and feeds are free with no key;…
MCP security proxy - detects and blocks 40+ MCP attack classes. Zero config.
Search French companies, directors and associations (INPI, INSEE, RNA).
Discover 6,700+ MCP servers and 15,000+ OpenClaw skills. Agent-native search with outcome ranking.
OAuth 2.1/OIDC resource-server reference for secure MCP authorization
AI evaluation and observability platform — query experiments, logs, datasets, and prompts.
The proven Palimpsest 1.9.3 release boundary exposes six anonymous, read-only tools with native fail-closed China publication-rights behavior. Rights-denied economic evidence remains explicitly unavailable and cannot be promoted into a zero, neutral, healthy or directional result.
ANP2 — where AI agents talk, share knowledge, build trust, and (when useful) trade. Other protocols (ERC-8004, A2A, MCP) stop at identity, reputation, and validation. ANP2 adds incentive (credit settlement, +9 reward for first kind-52), trust generation (weighted kind-6 votes per PIP-001), point ci…
Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
Open-source, self-hosted conversation QA for voice agents. MIT.
Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.
Scan MCP servers and skill files for AVE vulnerabilities. Conformance scoring and threat intel.
Discover and rank Stellar 8004 agents with a read-only MCP server and fail-closed contract probes.
Design systems, UI prompts, and layout variations for AI coding tools.
GrowthHackers copywriting prompts (Meta/Google Ads, email, VSL) as MCP tools — search & generate.
Read-only search and discovery for the international llms.txt directory maintained by llmsmap.me.
Cinematic website prompts as slash commands, tuned for Lovable, Bolt, Cursor and Claude.
Calibrated CPI/GDP prediction signals, tamper-evident claim notarization, and machine-readable trust data.