# LiteLLM-Labs/litellm-agent-control-plane

1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents.

Repository: https://github.com/LiteLLM-Labs/litellm-agent-control-plane
Canonical: https://ross.abutalabs.com/products/litellm-agent-control-plane
Homepage: https://docs.litellm-agent-platform.ai
Language: Rust
License: MIT
License Family: permissive
Topics: agent-platform, agent-vault, claude-code, codex, codex-cli, litellm, litellm-ai-gateway, sandbox, ai-gateway, agent-builder, agent-builder-tools
Last push: 2026-06-20T20:58:35+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 88, release rhythm 35, longevity 8
- inputs: {"age_days": 118, "days_push": 74, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1235, forks 137 (observed 2026-08-28T04:04:04.523606+00:00)

## What it is
LiteLLM Agent Control Plane is a self-hosted platform that provides one unified API and UI for creating and running AI agents across multiple runtimes such as OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, and Deep Agents. It handles access control, persistent sessions, CRON scheduling, and memory so teams can manage all their agents from a single place.

## Use cases
- run all my ai agents through one unified api
- manage claude, cursor, and opencode agents from a single dashboard
- schedule agents to run on a cron
- give my team agent access without sharing anthropic or bedrock console credentials
- persist agent sessions and memory across runs
- self-host an agent gateway with docker
- talk to agents via slack or teams

## When to choose
- you use multiple agent runtimes and want one API and UI over all of them
- you need centralized access control, scheduling, and session/memory management for agents
- you want a self-hosted, Docker-based agent platform

## When to avoid
- you only use a single agent runtime and its native tooling
- you need a lightweight library to embed in your own app rather than a hosted service
- you are not working with LLM-based agents

## Facets
- artifact type: service
- maturity: active
- function: agent-framework, api-framework, auth, scheduling, chatbot, llm-inference, self-hosted
- domain: large-language-models, artificial-intelligence, developer-tools, self-hosted, apis
- platform: self-hosted, cross-platform
- tags: ai-gateway, agent-platform, agent-runtimes, unified-api, agent-orchestration, session-management, rust, ai-agents, docker, web-server

## Member repositories
- LiteLLM-Labs/litellm-agent-control-plane (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:04.523606+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:22:02.827511+00:00, confidence not recorded.
  - readme: https://github.com/LiteLLM-Labs/litellm-agent-control-plane (fetched 2026-08-28T04:04:04.523606+00:00, sha e8d484214f63)
  - homepage: https://docs.litellm-agent-platform.ai (fetched 2026-08-29T12:21:22.115175+00:00, sha ed5069267866)
  - site_page: https://docs.litellm-agent-platform.ai/quickstart (fetched 2026-08-29T12:21:22.124228+00:00, sha 4f483ddcf57a)
- Data as of 2026-08-30T08:39:29.467469+00:00.