"Project Manager Agent positions" matching MCP connectors:

Diagnose AI agent failures & translate ambiguous human input into clear intent using RPCS-1.

The agent-native cloud: database, functions, AI, storage, auth and more. 50 tools, one API key.

AI-agent image generation: cohesive sets & illustrations. PNG/WebP (optional transparency) or JPEG.

Live AI agent contest platform on Solana mainnet. Compete in skill tournaments (ART, STORY, JOKE) for real USDC payouts via on-chain Anchor smart contract. Confidential-rubric LLM judging on four dimensions: originality, theme_alignment, execution, surprise. Engine never holds private keys — entries use a two-call co-sign handshake.

Pay-per-use tool API for AI agents. Free tier, x402 USDC micropayments, or API key.

AI agent infrastructure: dedup, cost prediction, validation, governance, failure intelligence.

MCP server exposing 8 tools for trust scoring, sybil detection, reviewer wallet analysis, and counterparty risk across 150,000+ AI agents on ERC-8004, Olas, and Virtuals. Streamable HTTP, JSON-RPC 2.0, no API key required.

MiCA compliance evidence, stablecoin risk scoring (105+ tokens), macroeconomic regime detection (86 FRED series), and AI agent governance. 79 tools across 5 MCP servers. Every response ECDSA-signed, blockchain-anchored, audit-ready. Free tier, no API key needed. Works with Claude Managed Agents.

Verifiable cognition: any agent file to a deterministic content-addressed brain_id.

Developmental agents + Wu Wei compute routing: evolve from outcomes, route to cheapest reliable.

Carbon-accounted agent compute: free footprints; certificates backed by real offset retirement.

Video generation cost estimates across providers, with provenance, freshness, and confidence.

Preflight, approve, and prove consequential agent actions with signed evidence and x402 tools.

Authenticated async GPT-5.6-luna Agent agent with status polling and artifact results.

Authenticated async GPT-5.6-sol Agent agent with status polling and artifact results.

X feedback discovery, noise-reduced query planning, signal filtering, and AI handoffs.

The directory AI agents call when a buyer asks an LLM for a B2B software recommendation. Same listings G2 has — but capability-structured, continuously verified, and agent-callable. One listing visible to both audiences.

Play chess live against your own personal AI agent — OpenClaw, Hermes, and similar.

Signed verification attestations for agent decisions: business, price, freshness, claim checks.

Independent AI-agent reviews: trust checks, evidence scorecards, incident registry, recommendations.