by xianyu-sheng · MCP Server · ★ 53
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🚀 Xenon — Agent Harness for AI coding agents. 证据导向架构 + 7种推理范式 + 执行隔离边界 + SWE-bench 40% 通过率（+6.7pp）。可信、可验证、可评测的 AI Agent 运行时。
| Stars | 53 |
| Forks | 1 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 49.9761720052511/100 |
| Open Issues | 10 |
| Last Updated | 2026-08-30 |
| Created | 2026-06-03 |
| Platforms | cli, mcp, python |
| Est. Tokens | ~13k |
Looking for a Xenon alternative? If you're comparing Xenon with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A coding agent whose claims about its own work resolve to machine-captured evidence: an append-only hash-chain
Open Python agent harness for production AI apps: tools, MCP, memory, workspace, telemetry, subagents, backgro
Local-first, auditable Python code agent. Ships its own 30-task hidden-test benchmark plus SWE-bench Verified
Evidence-gated runner for Codex, Claude Code, OpenCode, and local coding agents. Routes tasks into scoped DAG
Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolat
A memory-first AI agent that remembers why decisions were made — not just the last message. Runs local (Ollama
Explore other popular mcp server tools:
Xenon is 🚀 Xenon — Agent Harness for AI coding agents. 证据导向架构 + 7种推理范式 + 执行隔离边界 + SWE-bench 40% 通过率（+6.7pp）。可信、可验证、可评测的 AI Agent 运行时。. It is categorized as a MCP Server with 53 GitHub stars.
Xenon is primarily written in Python. It covers topics such as agent, agent-framework, agent-harness.
You can find installation instructions and usage details in the Xenon GitHub repository at github.com/xianyu-sheng/Xenon. The project has 53 stars and 1 forks, indicating an active community.
Xenon is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to Xenon on Agent Skills Hub include swarm-orchestrator, omnicoreagent, DM-Code-Agent. 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: