AI & Agents MCP servers

List the models each AI provider's API serves and see which are new since the last check.

Free, account-free agent messaging with signed sessions, AEAD, and replay protection.

Self-hosted MCP gateway and LLM proxy: OAuth 2.1, model aliases, Grok subscription as an API.

Memory the human governs, on their own machine, plus what other coding agents here wrote.

Agent memory: working, episodic, semantic, procedural and core layers. Local SQLite, no account.

Keep Claude Code and Codex off each other's files: hook-enforced path leases, presence, messages.

Let coding agents on one machine message and wake each other. Run `harness-summit install` first.

Local practice gym for AI agents on real apps: practice Excalidraw tasks, get a reproducible score.

Deterministic pre-execution verification tools for AI agents with x402 USDC pay-per-call on Base

One memory for every AI: Claude, ChatGPT and more share a memory that lives on your computer.

Autonomous M2M marketplace for AI agents: semantic discovery, CNP bidding, and task escrow.

Guardrails for LLM answers: exact checks against sources, PASS/REVIEW/FAIL, signed records.

Local persistent memory and Markdown wiki for AI coding agents: 24 MCP tools, no gateway required.

Local MCP runtime for policy-governed, verified agent actions with durable receipts.

SigRank SignalAF on-device scanner — four-token cascade, leaderboard, 25 local tools.

Encrypted local ledger of structured user state, shared across every MCP-aware AI tool.

AI agent memory & knowledge graph, hosted in Germany (GDPR). Recall, relations, store via MCP.

Persistent decision memory for AI agents: rationale, rejected approaches, and entity history.

CPU task-specific context preparation and explicitly saved local project notes through MCP.

A personal work twin for every AI agent: your confirmed guidance and explicit grants, enforced.

Repository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.

A host-agnostic MCP worker runtime for supervising local Pi coding-agent processes.

Your AI agents in an Epeaky den: end-to-end encrypted rooms. Only their owner's orders count.

Expose an OpenAPI document to agents as a search-first tool catalog over your existing API.

Read-only MCP server for markdown and agent steering files: read, outline, lint, context budget.

Shared session bus for Claude, Codex, Copilot, Cursor, Gemini, AGY, Grok, and OpenCode.

Langfuse public API (Cloud and self-hosted): traces, prompts, datasets and gated writes.

Persistent knowledge graph and MCP server for AI workflows with git-tracked project context.