platform

workflow
Security Audit
Warn
Health Warn
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Execution context manager for AI coding agents. Sandbox isolation, model provider routing, terminal session management, Kubernetes orchestration, and plan-driven development workflows.

README.md

Xonovex Platform Monorepo

License
Node
Go

Monorepo for Xonovex AI agent tools, workflows, and skills

AI coding agents handle prompts, tools, and code changes. What they don't manage is the environment around them: sandbox isolation, model provider routing, terminal sessions, reproducible toolchains, and orchestration at scale.

Xonovex fills this gap. It currently supports Claude Code and OpenCode as agents, with sandboxing via bubblewrap and Docker, VM-level isolation via gVisor and Kata Containers, confidential computing via Confidential Containers (CoCo) with AMD SEV-SNP and Intel TDX, model routing through providers like Gemini, GLM, and GPT, workspace management with Git and Jujutsu, reproducible toolchains via Nix, and Kubernetes orchestration for running agents at scale.

The included skills are token-efficient, harness-neutral, and based on current research and best practices (Agent Skills spec, agentskills.io, agents.md).

  • agent-cli-go configures sandboxes, providers, and terminal sessions, then launches the agent
  • agent-operator-go orchestrates agents as Kubernetes Jobs with managed workspaces, provider secrets, shared multi-agent workspaces, namespace-level policy enforcement, network isolation, and Nix toolchain provisioning
  • moon-nix-toolchain wraps every Moon task in the repository's Nix flake dev shell, giving reproducible flake-pinned toolchains in local runs, pre-commit hooks, and CI
  • Skills give agents coding guidelines they follow automatically; plan-driven development with worktrees, project-instruction management, insight extraction, and skill authoring all live here as consolidated skill packages

Quick Start

Agent CLI

npm install -g @xonovex/agent-cli-go
agent-cli run --agent claude --isolation bwrap --provider gemini

The sandbox is selected by three orthogonal axes — --isolation {none,bwrap,docker} ×
--provision {none,nix,command} × --network {host,none,proxy} — see
packages/agent/AGENTS.md.

Agent Kubernetes Operator

# Install CRDs and deploy the operator
kubectl apply -k https://github.com/xonovex/platform//packages/agent/agent-operator-go/config/crd
kubectl apply -k https://github.com/xonovex/platform//packages/agent/agent-operator-go/config/default

# Create a provider and run an agent
kubectl create secret generic gemini-credentials --from-literal=api-key='your-key'
kubectl apply -f - <<EOF
apiVersion: agent.xonovex.com/v1alpha1
kind: AgentProvider
metadata:
  name: gemini-provider
spec:
  displayName: Google Gemini
  authTokenSecretRef:
    name: gemini-credentials
    key: api-key
---
apiVersion: agent.xonovex.com/v1alpha1
kind: AgentRun
metadata:
  name: review-code
spec:
  harness:
    type: claude
  providerRef: gemini-provider
  workspace:
    type: git
    repository:
      url: https://github.com/org/repo.git
      branch: main
  prompt: "Review the codebase and suggest improvements"
EOF

Agent Plugins

Each skill is a separate plugin. Skills are applied automatically when the agent detects a relevant task — no explicit slash-command invocation needed. Skills also work cross-harness (Claude Code, OpenCode, etc.) since they follow the Agent Skills spec.

Claude Code

# Add the Xonovex plugin marketplace
claude plugin marketplace add xonovex/platform

# Install workflow skills — each covers a full operation lifecycle via consolidated references
claude plugin install xonovex-skill-plan@xonovex-marketplace          # research, decide, plan, revise, critique, accept/reject, subplans, continue, update, validate, code-align/harden/simplify
claude plugin install xonovex-skill-git@xonovex-marketplace           # commit, merge-resolve, feature-worktree create/merge/abandon/cleanup
claude plugin install xonovex-skill-instruction@xonovex-marketplace   # AGENTS.md init / sync / simplify / consolidate / merge
claude plugin install xonovex-skill-reflect@xonovex-marketplace       # session reflection: extract lessons, fold into AGENTS.md or a skill
claude plugin install xonovex-skill-code-review@xonovex-marketplace   # Conventional Comments feedback: blocking vs non-blocking, summary + inline
claude plugin install xonovex-skill-pull-request@xonovex-marketplace  # PR authoring: description, size/atomicity, testing evidence, tradeoffs, self-review
claude plugin install xonovex-skill-command@xonovex-marketplace        # author / merge / simplify reusable prompt files (cross-harness format reference)
claude plugin install xonovex-skill-skill@xonovex-marketplace         # author / extract / merge / simplify / validate Agent Skills
claude plugin install xonovex-skill-content@xonovex-marketplace       # multilingual articles, news, travel guides, prose humanization
claude plugin install xonovex-skill-llmstxt@xonovex-marketplace       # /llms.txt files and per-page markdown mirrors

# Install language / framework guides (apply automatically when editing those files)
claude plugin install xonovex-skill-typescript@xonovex-marketplace
claude plugin install xonovex-skill-react@xonovex-marketplace
claude plugin install xonovex-skill-hono@xonovex-marketplace
claude plugin install xonovex-skill-zod@xonovex-marketplace
claude plugin install xonovex-skill-vitest@xonovex-marketplace
# … see .claude-plugin/marketplace.json for the full list

Codex

# Add the Xonovex plugin marketplace
codex plugin marketplace add xonovex/platform

# Install workflow skills — each covers a full operation lifecycle via consolidated references
codex plugin add xonovex-skill-plan@xonovex-marketplace          # research, decide, plan, revise, critique, accept/reject, subplans, continue, update, validate, code-align/harden/simplify
codex plugin add xonovex-skill-git@xonovex-marketplace           # commit, merge-resolve, feature-worktree create/merge/abandon/cleanup
codex plugin add xonovex-skill-instruction@xonovex-marketplace   # AGENTS.md init / sync / simplify / consolidate / merge
codex plugin add xonovex-skill-reflect@xonovex-marketplace       # session reflection: extract lessons, fold into AGENTS.md or a skill
codex plugin add xonovex-skill-code-review@xonovex-marketplace   # Conventional Comments feedback: blocking vs non-blocking, summary + inline
codex plugin add xonovex-skill-pull-request@xonovex-marketplace  # PR authoring: description, size/atomicity, testing evidence, tradeoffs, self-review
codex plugin add xonovex-skill-command@xonovex-marketplace        # author / merge / simplify reusable prompt files (cross-harness format reference)
codex plugin add xonovex-skill-skill@xonovex-marketplace         # author / extract / merge / simplify / validate Agent Skills
codex plugin add xonovex-skill-content@xonovex-marketplace       # multilingual articles, news, travel guides, prose humanization
codex plugin add xonovex-skill-llmstxt@xonovex-marketplace       # /llms.txt files and per-page markdown mirrors

# Install language / framework guides (apply automatically when editing those files)
codex plugin add xonovex-skill-typescript@xonovex-marketplace
codex plugin add xonovex-skill-react@xonovex-marketplace
codex plugin add xonovex-skill-hono@xonovex-marketplace
codex plugin add xonovex-skill-zod@xonovex-marketplace
codex plugin add xonovex-skill-vitest@xonovex-marketplace
# … see .agents/plugins/marketplace.json for the full list

Development

git clone https://github.com/xonovex/platform.git
cd platform && npm install

Tasks are managed with Moon:

npx moon run <project>:<task>    # run a specific task
npx moon run :<task>             # run task across all projects
moon query projects              # list all projects

License

MIT


See CONTRIBUTING.md for development setup and guidelines.

Reviews (0)

No results found