MCP
Local installTHE LINE Protocol (the1ine.com): send tasks to verified AI agents, paid on Tempo testnet.
2,157 servers in AI & Agents
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.
Delega MCP client. Public hosted access retired July 28, 2026; existing owner credentials only.
Pay-per-call AI + web + on-chain tools over x402 (USDC on Base): LLM, SEO, extract, token safety.
deja-vu: local memory over the session histories of forty-three coding agents.
A marketplace where AI agents find complementary agents, form teams, and complete real work.
The open-source governance layer for AI agents. Byte-identical run receipts, 40+ adapters, air-gap.
Plan OpenAI Codex usage from local quota, banked resets and extra-reset forecasts.
Trust metadata for AI agents — check files before building on them, stamp verified work.
async/await for LLM agents: spawn and await sub-agents scheduled on your own GPUs
Trust OS for AI agents: governed memory, payments, reputation, approvals, and audit evidence.
MCP server for DeepSeek AI with chat, reasoning, sessions, function calling, and cost tracking
minia2a.uk — x402 pay-per-call APIs for AI agents, USDC on Base, 5 free trials per wallet.
AI voices from many models talk to each other. Read free; write with a token that stays out of chat.
Compile your own business capabilities from declarative YAML and serve them as MCP tools.
One shared, durable memory for your AI coding agents — local-first, zero-dependency.
Preserve a user-authorized judgment and append later answers. No model verdict or human score.
Self-hosted memory for LLMs in TriliumNext, structured by the server and editable by you.
Private memory layer for AI assistants. Local-first: remember, recall, forget, expand.
SCDO agent wallet and chain tools: x402 USDC, Agent Ledger, SCDO chain, games, Connect.
Multiplayer mode for AI coding agents: team huddles, master prompt, task board, file claims.
Hot-reload for MCP servers + mount any community server mid-session, Docker-caged. No restarts.
Check the reputation of AI microservices and public APIs from an open trust registry.
Local, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.
Find MCP servers in the MCP Rating index and connect on demand, with env vars scoped per server.
Governed local memory for AI agents: facts are retired, not overwritten, and every call is audited.
Search, browse, and submit MCP servers to the AllMCPs.com directory.
Free public benchmark for AI agents: compliance tasks, every claim checked against signed receipts
Build an agent tool once; ship it as Agent Skills, MCP servers, Agent Plugins / Claude / Codex
Read-only, tenant-scoped access to Tracelane agent traces and guardrail verdicts