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 Zleap-AI · Codex Skill · ★ 218
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Zleap-Agent safe to install? View the security audit →
Workspace Is All Agents Need English | 简体中文 Preview status Zleap-Agent is an early preview. The public repository is intended for source review, local development, and feedback. APIs, UI details, packaging, and release flows may change before a stable release. What Is Zleap-Agent? Zleap-Agent is a workspace-first agent harness for local and OpenAI-compatible models. It is built around one practical idea: An agent should not see every tool, memory, rule, and previous message on every step. It should first know which workspace it is in, then receive only the context needed for that workspace. Instead of treating context as one large prompt, Zleap-Agent separates the agent runtime into workspaces. Each workspace can have its own prompt, tools, skills, memory, model, and execution history. This makes the system easier to reason about when running smaller local models, enterprise-local deployments, or workflows where permissions and data boundaries matter. Highlights Workspace isolation for prompts, tools, skills, models, memory, and history. Web UI for chat, workspaces, assistants, models, tools, MCP servers, skills, memory, tasks, gateway configuration, and artifacts.
| Stars | 218 |
| Forks | 26 |
| Language | TypeScript |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 79.3250756686424/100 |
| Open Issues | 1 |
| Last Updated | 2026-08-05 |
| Created | 2026-05-31 |
| Platforms | node |
| Est. Tokens | ~15k |
These tools work well together with Zleap-Agent for enhanced workflows:
Looking for a Zleap-Agent alternative? If you're comparing Zleap-Agent 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.
Traffic light for AI Agents and TypeScript/Node multi-agent orchestrator with shared state, guardrails, and ad
🤖 MateClaw — Your second brain with Multi-Agent Orchestration, MCP Protocol, Skills & Memory, Dream, and Mult
The governed runtime for Python agents you can let act: policy on every action, durable runs, sandboxes, budge
The minimal interpretable model router that learns & adapts to your agent workflows
Battle-tested skill library for AI agents. Save 98% of API costs with ready-to-use code for crypto, PDFs, sear
Secure autonomous AI agent framework and platform. Build AI teams by describing what you want. Orchestrate age
Explore other popular codex skill tools:
Zleap-Agent is Agent Harness developed specifically for local small-parameter models.. It is categorized as a Codex Skill with 218 GitHub stars.
Zleap-Agent is primarily written in TypeScript. It covers topics such as agent, agent-harness, hermes-agent.
You can find installation instructions and usage details in the Zleap-Agent GitHub repository at github.com/Zleap-AI/Zleap-Agent. The project has 218 stars and 26 forks, indicating an active community.
Zleap-Agent is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to Zleap-Agent on Agent Skills Hub include Network-AI, mateclaw, omnicoreagent. 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: