agent-control-plane

A control plane with a durable state kernel for long-horizon agents and teams. Keep work moving and improving across sessions, with less human attention.

ACP is the Agent Control Plane - a distributed agent scheduler optimized for simplicity, clarity, and control. It is designed for outer-loop agents that run without supervision, and make asynchronous tool calls like requesting human feedback on key operations. Full MCP support.

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

The open-source Agent Gallery and Gateway for Codex, Claude Agent SDK, and OpenCode. Developers publish an Agent once behind one HTTP API; users run it in an isolated cloud sandbox—no local harness setup, compute, or runtime infrastructure.

One place to build, run and govern your company's AI agents — skills, context files, MCP at registry scale, automations, budgets and an audit trail. Self-hosted and open source, on your own Postgres and Docker.

Discord control plane for project-bound ACP agents (Kiro CLI/OMP) with MCP policy, cron/audit, and A2A over NATS/JetStream.

Run reviewable, resumable coding-agent workflows across Claude Code, Codex, Gemini, GitHub Copilot CLI, or any CLI. You define the stages in Markdown; Crewplane runs the workflow, agents do the work, and every handoff stays on disk.

Marblo — the live orchestrator for AI-native teams

Agent control plane and runtime access platform for enterprise systems — govern business APIs as Tools, compose Agents and Workflows, expose runtimes through AAP, and trace executions end to end. https://act-weave.grok.me

AI agent CLI and coding-agent Skill for mosoo. Configure, publish, run, and inspect agents through the Agent API on cloud, local, or self-hosted targets.

Utu - Multi-agent, multi-provider, multi-model dashboard & control

Production-oriented governance control plane for autonomous AI agents. Policy engine, approval gates, budget tracking, kill switches, and auditable event sourcing.

A curated list of tools, frameworks, and resources for building and securing the AI agent control plane: identity, policy enforcement, gateways, sandboxing, and governance.

🛠️ Log and trace your AI's decisions securely with DecisionTrace, ensuring transparency and integrity in every choice it makes.

Mobile control surface for Hermes Agent, built with KMP and Compose Multiplatform

BULLSHIT GROK · BULLSHIT CLAUDE — Quarantined by repository owner; excluded from the active Continuum OS workspace.

AI-first operating system for running a one-person company: Markdown source of truth, agent prompts, and an agent control plane with deny-by-default permissions, runtime governance, policy-as-code, telemetry, and a safe-delegation feedback loop

Guild.ai — independent third-party profile of a public API surface, by API Evangelist. Guild.ai is a control plane for AI agents that lets engineering teams build, deploy, govern, and share agents in production. Agents are authored in TypeScript with the @guildai/agents-sdk (alongside Guild Native and Goose recipe agent types) and run in a governed

Installable, runtime-dependency-free Python reference for fail-closed agent execution, deterministic revalidation, effect readback, replay prevention, and hash-bound receipts.

Experimental control-plane kernel for bounded agent execution, policy checks, provenance, authority envelopes, and fail-closed workflow supervision.