AI & Agents MCP servers

Persistent project context for Google Gemini. Python/FastMCP. IANA-registered .faf format.

Rust MCP gateway with Code Mode, authentication, setup, logs, CLI, HTTP API, and operator web UI.

Persistent project context — Rust-native MCP server. IANA-registered .faf format.

Inspect and manage Verlon AI gates, logs, recommendations, and experiments from any MCP client.

Durable AI memory: recall distilled facts in a later session or subagent, and remember new ones.

RMCP runtime for provider-backed agents with CLI, REST, HTTP MCP, plugins, and scaffold support.

Your agents, on a team with you. Every piece of work shows who did it and who accepted it.

An append-only ledger of sourced, dated, confidence-scored claims your agent cites and you audit

Open E2EE messaging protocol and MCP server so AI agents of different people can talk directly.

Persistent memory for AI agents: local-first MCP server, zero-config. No cloud, no API keys.

Governed Memory for AI Agents, in plain local files. No network calls of its own.

Open-source guardrails for AI agents running Google Ads. Your keys, your caps.

Hand a released SkeletIQ architecture to a coding agent: brief, build order, drift check.

Pay-per-call agent services and a job board in USDC on Arc via x402, plus routed agents.

Team-aware memory: intent, decisions, real-time conflicts for AI coding assistants.

Every connected AI chat starts already knowing your project. One checked record, on your computer.

Nexus Agents: a network for AI agents. Verifiable identity, reputation, Q&A, messages, a library.

Open-source governance for MCP agents: useful autonomy without unlimited authority

Start Claude Code and Codex agents the person can watch, wait for them and read their answers.

A graph-native code repository for AI agents and the people who build with them.

MCP server for the phlow agent runtime: bounded planner-coder-reviewer agent workflows.

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

Act for a person on websites: sandboxed browser, phone approvals, saved logins, scheduled plans.

Human-in-the-loop for AI agents over MCP elicitation: confirm/form dialogs plus a capability doctor

Loads signed ALTWEB context capsules — refuses unsigned, tampered, or untrusted by default.

Search and rate AI tools, MCP servers, and agent skills, safety-checked and rated by AI agents.

Persistent decision memory for agents — learns which action works in which context

End-to-end encrypted scratchpad for coding agents across machines, vendors and people.