DM-Code-Agent — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 hwfengcs · MCP Server · ★ 151

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is DM-Code-Agent safe to install? View the security audit →

About DM-Code-Agent

DM-Code-Agent 本地优先、可审计、有算法骨架的 Python Code Agent 中文 Français 一句话:DM-Code-Agent 是一个把 ReAct + Planner + Replan + Trace 写在 1500 行可读 Python 里的代码维护 Agent;v2 已落地默认关闭的 Reflexion / Critic / Self-Consistency / Adaptive Replan 模块,并接入 SWE-bench Lite Tier-1 评测链路。 它不是要做又一个聊天黑盒,而是要做一个开发者能看懂、能复现、能扩展、能拿来对比研究的 Code Agent baseline。 Why this project 可审计 (Auditable):每一步的计划、工具调用、观察结果都写入 JSONL trace,trace 自带 dry replay、显式 tool replay 和离线 diff,调试不靠"再问一次模型"。 可对标 (Benchmarked):项目自带 coding 与 maintenance 两套 hidden-test benchmark,并已发布 SWE-bench Lite DeepSeek Tier-1 baseline:0.0% resolved / 72.0% patch-applied on the fixed 50-instance subset。这个 Tier-1 数字受 host verifier 环境噪声影响,不能和官方 l

agentagent-evaluationagent-skillscode-agentllmllm-agentmcpragreact-agentreflexion-agent

Quick Facts

Stars151
Forks15
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score63.2665042616416/100
Open Issues2
Last Updated2026-08-27
Created2025-09-30
Platformsmcp, python
Est. Tokens~16k

Compatible Skills

These tools work well together with DM-Code-Agent for enhanced workflows:

  • DeepEye — semantic(0.18)+complementary+shared_fw(react)+same_lang+similar_pop+shared_platform (64%)
  • RepoMaster — semantic(0.33)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
  • Micro-Agent — semantic(0.34)+shared_fw(react)+rare_topics+same_lang+similar_pop+shared_platform (59%)
  • tau2-bench — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (58%)

DM-Code-Agent alternative? Top 6 similar tools

Looking for a DM-Code-Agent alternative? If you're comparing DM-Code-Agent 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.

  • Xenon by xianyu-sheng · ⭐ 53

    🚀 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

  • wcgw by rusiaaman · ⭐ 674

    Shell and coding agent on mcp clients

  • aser by AmeNetwork · ⭐ 472

    Aser is a lightweight, self-assembling AI Agent frame.

  • zypher-agent by corespeed-io · ⭐ 331

    A minimal yet powerful framework for creating AI agents with full control over tools, providers, and execution

  • coder_eval by UiPath · ⭐ 141

    Playwright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses th

  • Micro-Agent by fdueblab · ⭐ 101

    A lightweight AI agent framework for vertical domain applications | 面向垂域应用的轻量级 AI Agent 框架

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is DM-Code-Agent?

DM-Code-Agent is Local-first, auditable Python code agent. Ships its own 30-task hidden-test benchmark plus SWE-bench Verified scored by the official harness -- every number reproducible, negative results included.. It is categorized as a MCP Server with 151 GitHub stars.

What programming language is DM-Code-Agent written in?

DM-Code-Agent is primarily written in Python. It covers topics such as agent, agent-evaluation, agent-skills.

How do I install or use DM-Code-Agent?

You can find installation instructions and usage details in the DM-Code-Agent GitHub repository at github.com/hwfengcs/DM-Code-Agent. The project has 151 stars and 15 forks, indicating an active community.

What license does DM-Code-Agent use?

DM-Code-Agent is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to DM-Code-Agent?

The top alternatives to DM-Code-Agent on Agent Skills Hub include Xenon, wcgw, aser. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse MCP Server tools