Categories
Self-Hosted Developer Tools AI Agents Automation MCP Agent Orchestration LLM Gateway Agent ManagementStars
Forks
Watchers
Developer links
LiteLLM Agent Control Plane
Agents scattered across vendor consoles become one tidy workspace in LiteLLM Agent Control Plane, which puts Claude Managed Agents, Cursor, OpenCode, OpenClaw, Deep Agents, and Hermes behind a single login, one API, and one dashboard. Describe an agent in plain language or start from a template for a deep researcher, an inbox triager, or a security reviewer, then tick the tools, skills, and MCP integrations it may use and pick the runtime that executes it. Chat happens inline with streamed output, sessions persist across runs, and a memory layer carries context from one session to the next. Routines launch agents on a cron schedule, and each scheduled run lands in the history as its own session. An MCP proxy injects upstream credentials at the wire, so agents never hold real secrets, and provider keys sit encrypted in a vault. Colleagues can reach the same agents from Slack, Microsoft Teams, Google Chat, or a webhook, and developers can drive everything through a REST API with a live try-it reference. Administrators issue per-user virtual keys with budgets, model limits, and expiry dates, and an inbox gathers anything that needs a human decision. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Benefits
- One Dashboard For Every Runtime
- Claude Managed Agents, Cursor, OpenCode, OpenClaw, Deep Agents, and Hermes register as runtimes, so teams create and run agents in one place instead of juggling vendor consoles.
- Secrets Stay Out Of Agents
- The MCP proxy injects upstream credentials into tool calls, and provider keys sit encrypted in a vault, so agents and their users never handle the real secrets.
- Agents Work Where Teams Chat
- Connect any agent to Slack, Microsoft Teams, or Google Chat, or call it through the REST API and webhooks, so colleagues reach it from tools they already use.
- Spend And Access Under Control
- Issue per-user virtual keys with budgets, model restrictions, and expiry dates, so developers get access to agents without sharing the master key or console logins.
Features
- Agent Builder And Templates
- Describe an agent in plain language or start from a template, then choose its tools, skills, and attached MCP integrations before running it.
- Persistent Sessions And Memory
- Sessions persist across runs and can be resumed, and agents remember context from earlier sessions instead of starting fresh each time.
- Cron Scheduled Routines
- Schedule agents on a cron expression, and each scheduled run creates its own session that appears in the history for review.
- MCP Proxy And Vault
- Declare MCP servers once, route tool calls through the proxy, and keep provider credentials encrypted in a vault that agents never read.
- Per-User Virtual Keys
- Create keys with budget limits, model restrictions, and expiry dates for each team member from the Settings screen of the dashboard.
- Skills Rules And Inbox
- Attach reusable skills and rules to agents, and review anything awaiting attention in a shared inbox inside the same dashboard.