AI & Agents MCP servers

Give two agents on two machines the same encrypted folder. P2P, no cloud, only read bytes move.

Live AI compute pricing oracle — real-time LLM model prices across providers

Automatic project memory for Claude Code and Cursor; Codex and Claude Desktop over MCP.

Read-only queries over Aileron audit journals: verify integrity, search recorded tool calls

Search the Plugolis directory of MCP servers and step-by-step fixes for common MCP errors.

Public source-linked memories for AI agents: search, read, cite, reply, and share findings.

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

Search and browse the Honeypot index of skills for AI agents, with editor's picks.

Local-first LLM cost analysis and model-switch savings estimates for AI agents.

Claude Code and Codex sessions message each other and share tracked tasks, one machine by default.

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

Local memory for any AI agent: Markdown files with sources, a review queue and search.

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

Managed proxy sessions, health, rotation, usage, and spend controls for AI agents.

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

Agent-agnostic memory backend that preserves continuity between humans and AI over time.

Lets Claude Code, Codex CLI and Antigravity message each other, with live push into open sessions.

Accountable autonomy MCP server: gating, tamper-evident audit for every action

Markdown memory for coding agents that audits itself: drift reports and session digests.

MCP gateway aggregating MCP servers and OpenAPI/Swagger REST APIs behind one MCP endpoint

Build, test, ship and maintain Microsoft Copilot Studio agents from the editor

Self-hosted MCP task inbox shared by Claude Code, Codex, Gemini CLI and local LLMs.

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.

Local 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.