AI & Agents MCP servers

Local memory, a work tracker and a shell-command guard shared by coding agents on one machine.

Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.

Local knowledge graph memory for agents. SHACL rules refuse bad facts; SPARQL and time travel.

LLM benchmark rankings, drift status, incidents and Smart Router previews from AI Stupid Level.

Long-term memory for Claude: Markdown in a git repo you own. Survives context compaction.

Runs non-urgent LLM tasks at the cleanest grid hour before a deadline, via Batch APIs when allowed.

AI API gateway MCP: Claude, GPT, Gemini, Grok & Kimi with one Zerouter API key, plus API pricing.

Session continuity for AI assistants: resume any work lane where the last session stopped.

Self-hosted catalogue of your skills, agents and MCP servers, searchable by meaning over MCP

Local hybrid-search memory for AI agents over plain Markdown. Multi-tenant, offline, no LLM.

Windows x64/Python 3.12 MCPB preview: governed local tools and persistent profiles.

Alibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account.

Agora agent economy over MCP: browse the board, register, claim on-chain work, and post bounties.

Ask any website's AI concierge a grounded question, and generate the embed to add one to a site.

Verifiable, portable AI memory. Optional vault: encrypted on your machine, 12 words only you hold.

Persistent, structured project memory for AI coding agents, stored locally in SQLite.

Local visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding.

Content contract layer: read-only retrieval over protocol, modules, pipelines, assets, library.

Persistent 3D/2D spatial world model for AI agents with dynamic velocity and entity tracking.

Persistent workflow graph server tracking tasks, decisions, spatial entities, and blockers.

Multiplayer for AI coding agents: collision detection before the edit, messaging, delegation.

Run WhatsApp AI agents: manage agents, conversations, CRM contacts, orders and RAG docs.

Identity, trust, and A2A orchestration for autonomous AI agents. Official A2A partner.

Developer memory CLI and MCP server. Remember decisions, preferences, and lessons locally.

THE LINE Protocol (the1ine.com): send tasks to verified AI agents, paid on Tempo testnet.

A marketplace where AI agents find complementary agents, form teams, and complete real work.

Pay-per-call AI + web + on-chain tools over x402 (USDC on Base): LLM, SEO, extract, token safety.

Trust OS for AI agents: governed memory, payments, reputation, approvals, and audit evidence.