Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
GLM-5
GLM-5: From Vibe Coding to Agentic Engineering
3.3kstars
361forks
agentic-aicodingglmllm
Quality signals
StaleNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
Large language models designed for long-horizon coding and agentic tasks with 1M-token context and strong reasoning capabilities.
Use this when
- Debugging multi-file codebases with long dependencies
- Automating multi-step deployment workflows
- Planning and executing long-term software projects
- Generating entire repositories from high-level requirements
- Running agentic workflows that require sustained reasoning
Don't use when
- Quick one-off code snippets under 100 lines
- Simple API integrations or CRUD operations
- Tasks requiring real-time sub-second responses
Capabilities
- 1M-token context window for sustained long-horizon work
- Multi-level reasoning effort (max/high) for balancing speed and depth
- State-of-the-art performance on SWE-bench Pro and Terminal-Bench
- Improved architecture with IndexShare for 2.9× FLOPs reduction at 1M context
- Supports FP8 quantization for cost-efficient deployment
- Built-in tool integration for terminal and repository operations
Install
Universal installANY TOOL
$ npx skillcity@latest zai-org/GLM-5Auto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Prefer to set it up by hand? Clone the repository:
git clone https://github.com/zai-org/GLM-5.git
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
glm-5 — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt