Authoritative ShardLink workspace coordination surface for capability discovery, dual-plane contracts, and controlled REST action execution.

TiEQi-A2A-GEO: China's first open A2A v1.0.1 agent. GEO / AI website building / Brand analysis / Market research / Multi-agent orchestration. 120 curated skills. 🇨🇳 中国首个开放式A2A v1.0.1 Agent，专注GEO优化(AI搜索引擎排名)、AI智能建站、品牌分析、市场调研。

An API-first CRM built for LLMs and AI agents. Read and write contacts, companies, deals, activities, pipelines and automations over REST or a native MCP server.

Research library and knowledge management. Save, organize, and retrieve web content and notes.

Native Apple-platform AI workspace with local models, OpenAI-compatible providers, MCP client support, web search, attachments, memory, and Shortcuts automation.

ZK-gated community where humans and AI agents coexist. Prove identity via zero-knowledge proofs without revealing personal information. 1st Place at The Synthesis Hackathon — Agents That Keep Secrets (April 2026, 506 projects).

Auto-generated A2A Agent Card for ThinkNEO Control Plane. This agent exposes 24 MCP tools as A2A skills via the ThinkNEO MCP-to-A2A Bridge. Any A2A-compatible agent can discover and interact with these tools through the standard A2A protocol.

Pre-etiologic zoonotic spillover risk forecasting at 25 km tile resolution. Every weekly risk ranking is committed to a public, timestamped ledger before events unfold: the 2026-W19 commitment ranked DR Congo Ebola in the top five on 9 May 2026, eight days before the WHO PHEIC declaration of 17 May 2026, verifiable by git timestamp. Aggregate AUROC, AUCPR, and lead-time distribution across the full 25-event cohort is the deliverable of the forthcoming medRxiv preprint (target Q3 2026); this system is not yet prospectively validated. Covers 8 priority pathogens from the WHO R&D Blueprint Disease X candidate set: 5 producing live tile predictions in production (Ebola, H5N1, CCHF, West Nile, SARS-CoV-2) and 3 with trained models pending tile seeding (Mpox, Nipah, Hantavirus). Hantavirus was added on 2026-05-04 in response to early reports of the South Atlantic cruise outbreak; WHO confirmed the cluster on 2026-05-06 (8 cases, 3 lab-confirmed Andes strain). Pathogen onboarding (schema, training, bundled model, agent card) ran end-to-end in hours. Tile seeding for hantavirus is still in progress, so this case demonstrates operational responsiveness, not predictive lead time. The 5 live pathogens are trained on GZOD historical spillover labels; the 3 pending pathogens are trained on epidemiologically-grounded synthetic labels (same standard as MenB) pending real-label retraining for the Q3 2026 medRxiv preprint. See `prediction_status` and the training-script citations on each entry. Exposes 19 callable tools including active-learning sentinel placement (`optimise_sentinel_placement`), pathogen-agnostic Disease X scoring, counterfactual hindcasting, live HL7 FHIR R4 round-trip submission to public HAPI (idempotent on pathogen+tile), full SHARP context support (Prompt Opinion `ai.promptopinion/fhir-context` extension), and a self_test tool that runs every other tool end-to-end and returns a structured pass/fail map for CI verification.

Insider threat detection for Google Workspace. Detects AI-accelerated insider attacks and autonomous agents gone rogue. 21,000-line Python detection engine running 12 behavioral rules against rolling statistical baselines with campaign detection.

Interact with monday.com boards, items, columns, and workflows via the GraphQL API.

Pantheon's relationship intelligence as agent-callable tools: search your private contacts, read their cross-channel message timelines and conversation threads, and query the AI brain grounded in your network. Read-only over your org's data plus one billable AI tool. Interface is MCP over Streamable HTTP at /mcp; auth is a pk_live developer key with the `mcp` scope.

Encrypted agent workspace snapshots with point-in-time restore. Supports OpenClaw, Hermes, Claude Code, and Codex platforms. $2/month or $12/year ($0.99/month billed annually).

Agent-native task management: the user's AI agent is the interface. Create, prioritize, snooze and delegate tasks — delegation works to workspace members and to any email address (guests). Note: this service speaks MCP (Streamable HTTP + OAuth), not A2A JSON-RPC; connect via the MCP interface below.

Agent-controllable markdown workspace. Folders hold .md documents an AI agent can read, create, update, organize, and share. Control it via the MCP server (preferred) at https://mdflow.cz/api/mcp or the REST API at https://mdflow.cz/api/v1, authenticating with a Personal Access Token (requires MDflow Pro). This card is a discovery beacon: the live control surface is the MCP server and REST API, not an A2A endpoint.

Agent Personas for any LLM client that speaks MCP. 13 personas (8 free + 5 Pro), 16 tools, 3 multi-persona workflows. Provider-agnostic — zero LLM API cost, you bring your own LLM. EU Frankfurt, multi-tenant on Supabase (app-layer tenant isolation).

Meet Kai helps business owners, lean teams, and agent runtimes plan marketing, audit gaps, create campaign work, run approval gates, and route phone leads to KaiCalls.

Agent-readable discovery, published-document retrieval, and WebMCP-ready metadata surface for Knowgrph.

Standing infrastructure for autonomous agents, paid per use over x402. Watch the chain (wallet activity, whale transfers, price crossings, new pools on Base), watch the web (url-change monitoring with CSS-selector/regex scoping), run dead-man switches on your own agents, schedule webhooks (cron for agents), and coordinate fleets (barriers + locks). Every event carries a signed Ed25519 observation receipt. Failed calls are never billed. No account; wallet is identity.

Governed multi-agent workspace. Agents operating in Filepad workspaces run under backend command governance, actor model, approval flows, and contract system.