# Yuan-lab-LLM/ClawManager

A Kubernetes-native control plane for AI agent instance management, with governed AI access, runtime orchestration, and reusable resources across multiple agent runtimes.

Repository: https://github.com/Yuan-lab-LLM/ClawManager
Canonical: https://ross.abutalabs.com/products/clawmanager
Homepage: https://yuan-lab-llm.github.io/ClawManager/
Language: Go
License: MIT
License Family: permissive
Topics: kubernetes, openclaw, webtop, hermes
Last push: 2026-08-26T02:50:29+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 99, longevity 11
- inputs: {"age_days": 166, "days_push": 7, "days_rel": 10, "gap_med": 2, "n_releases_24m": 50}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1899, forks 153 (observed 2026-08-28T04:05:51.360591+00:00)

## What it is
ClawManager is a Kubernetes-native control plane for managing AI agent instances at cluster scale, providing governed AI access through an AI Gateway, runtime orchestration, and reusable resources across multiple agent runtimes such as OpenClaw, Hermes, and OpenCode. It includes team workspaces, skill management and scanning, and a security protection platform, built in Go with a React frontend.

## Use cases
- manage fleets of AI agent instances on Kubernetes
- govern and control AI model access across teams
- provision agent development workspaces like OpenCode or webtop
- manage and scan agent skills across multiple runtimes
- set up team workspaces with reusable agent templates
- orchestrate OpenClaw and Hermes agent runtimes at cluster scale
- secure and audit AI agent usage in an organization

## When to choose
- you run many AI agent instances on Kubernetes and need centralized control
- you need governed, policy-controlled AI access via a gateway
- you want reusable agent resources and templates shared across teams
- you manage multiple agent runtimes (OpenClaw, Hermes, OpenCode) from one place

## When to avoid
- you only need a single local agent with no cluster infrastructure
- you are not using Kubernetes or container orchestration
- you need a lightweight agent framework rather than a management control plane
- your team has no capacity to operate a self-hosted platform

## Facets
- artifact type: service
- maturity: active
- function: container-orchestration, deployment, api-gateway, agent-framework, configuration-management, security, web-framework
- domain: self-hosted, infrastructure-as-code, large-language-models
- platform: self-hosted, go, cross-platform
- tags: ai-gateway, agent-control-plane, openclaw, hermes, opencode, webtop, skill-hub, team-workspaces, instance-management, governance, ai-agents, containers, kubernetes, devops, docker, web-server

## Member repositories
- Yuan-lab-LLM/ClawManager (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:51.360591+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 2026-08-30T03:12:10.109357+00:00, confidence not recorded.
  - readme: https://github.com/Yuan-lab-LLM/ClawManager (fetched 2026-08-28T04:05:51.360591+00:00, sha 0e13f3418b2f)
  - homepage: https://yuan-lab-llm.github.io/ClawManager/ (fetched 2026-08-29T10:51:17.413697+00:00, sha a38bb6f86963)
- Data as of 2026-08-30T08:39:29.467469+00:00.