No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by LiteLLM-Labs · Codex Skill · ★ 810
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is litellm-agent-platform safe to install? View the security audit →
LiteLLM Agent Platform LiteLLM Agent Platform lets you run a harness (Claude Code, Codex, Hermes) as a service. They select a harness, tools, and a system prompt, deploy it, and can start running and managing agents. LiteLLM Agent Platform manages: Unified interface for harnesses - swap between Claude Code, Codex, Hermes, PI AI Session management - persistent agent sessions across runs CRON schedules - run agents on a schedule Memory - agents remember context across sessions Usage: Create an Agent Make an agent in the UI Select a harness, attach your tools, set a system prompt, and deploy. [ screenshot: select a harness ] Select a harness. Claude Code, Codex, Hermes, or OpenCode. Set it up. Attach your tools and a system prompt. Your MCP servers and keys are already there from when you signed in. Deploy it. One click. Then start running and managing agents from the UI or an API. [ screenshot: set up the agent ] [ screenshot: deploy and run ] Your tools are already connected Add a key to the platform once. When you sign in, your GitHub and AWS MCPs are already there. You do not add them again. The agent just uses the keys.
| Stars | 810 |
| Forks | 78 |
| Language | Rust |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 65.8124105901652/100 |
| Open Issues | 8 |
| Last Updated | 2026-06-13 |
| Created | 2026-05-07 |
| Platforms | claude-code, cli, codex, rust |
| Est. Tokens | ~22k |
These tools work well together with litellm-agent-platform for enhanced workflows:
Looking for a litellm-agent-platform alternative? If you're comparing litellm-agent-platform with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Self-hosted platform for running coding agents (Claude Code, Codex, Hermes) in isolated sandboxes with vault p
One Hub All LLMs For You | 为个人打造的 LLM API 聚合网关
Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software
Practical productivity tools for Claude Code, Codex-CLI, and similar CLI coding agents.
A curated list of awesome LLM and AI Agent Skills, resources and tools for customising AI Agent workflows - th
Curated skills, sub-agents, and config templates that supercharge Claude Code — research, image gen, GitHub au
Explore other popular codex skill tools:
litellm-agent-platform is 1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents.. It is categorized as a Codex Skill with 810 GitHub stars.
litellm-agent-platform is primarily written in Rust. It covers topics such as agent-builder, agent-builder-tools, agent-platform.
You can find installation instructions and usage details in the litellm-agent-platform GitHub repository at github.com/LiteLLM-Labs/litellm-agent-platform. The project has 810 stars and 78 forks, indicating an active community.
litellm-agent-platform is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to litellm-agent-platform on Agent Skills Hub include litellm-agent-platform, octopus, pilot-shell. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: