Provider-neutral agent runtime for coding workflows. Verified DAG execution with evidence gates, worktree isolation, and local graph memory.
Workflow and task automation, orchestration.
Provider-neutral agent runtime for coding workflows. Verified DAG execution with evidence gates, worktree isolation, and local graph memory.
Quota-aware agent-swarm MCP server: routes concurrent agent turns across multiple AI provider accounts
MCP server that delegates coding tasks to your locally installed MiniMax Code CLI (mcode). Wraps the real mcode binary instead of bundling its own copy of the agent, so it inherits your MiniMax login, models and config.
MCP server exposing Sanity workflow tools to agents — operate running workflow instances and author new definitions.
Censorship data, Sentinel forecasts and agent relay tools. Relay messages are readable by the relay.
MCP server that converts natural language queries to orchestration cards for GAFF
Autopilot AI orchestration — auto-plan, parallelize, self-heal, and route across 6 LLMs.
Local messaging between AI sessions: role accounts, DMs, channels via MCP. Windows only.
Local-first multi-agent coordination tools for MCP clients
Engram — Persistent Memory Cortex for AI coding agents. Gives agents session continuity, change tracking, decision logging, and project intelligence across sessions.
Paperclip adapter that runs Qwen, Gemma, Hermes, and other OpenRouter models as a tool-loop agent — checkout, comment, and patch issues without a local CLI.
MCP server for the Google Tag Manager API v2: containers, workspaces, tags, triggers, publishing.
Unofficial MCP server for managing Healthchecks.io checks via the Management API
Governance for LLM agents: 7 enforced rules + read-only reference tools. Safe in any MCP client.
Multiplayer for AI coding agents: collision detection before the edit, messaging, delegation.
Delegate coding tasks to the OpenAI Codex CLI, installed separately, with explicit model and effort.
Let your coding agent delegate work to Claude Code, Codex and Grok: a local MCP server and Agent Client Protocol (ACP) gateway with persistent sessions, approvals and crash-safe recovery.
n8n community node for creating and monitoring CALL-E AI-agent phone-call tasks.
Run taskflow on OpenAI Codex: the npm tarball provides the Codex subagent runner and MCP server; the plugin is distributed through the repository marketplace.
Multi-agent YAML workflow engine — 211 AI roles, auto DAG parallelism, zero code. One sentence → multiple AI roles collaborate → complete plan in minutes. 10 LLM providers, 7 need no API key.