← Back to list

sofagent

DeepSeek HarnessMCP Server Memory Low risk

sofagent is an open-source FDE Harness — on entry, write your business judgment into files (workflows, ontology, AI nodes); after departure, audit every change against them. 24 git-diff rules, tamper-evident chain, snapshots (107 tools, 11 plugins). Everything can be FDEing — turning FDE labor into FDEing capability.

FDE Harness:面向 AI 编码代理的审计优先治理——24 条规则、HMAC 链、快照回滚(80 个工具、13 个插件)。

How to install

DeepSeek Harness dsh plugin add github:KongFangXun/sofagent

About

🚀 **v1.4.4**——后训模块 · 信号与部署闭环(语料导出三件套 / 本地权重部署 / 产物→注册衔接 / 多基座对比 / 决策因果链 / CI 供应链加固 / 存量升级 / spec-first 硬禁令 / 审查收编批 / 五能力叙事)。✅ 已发版(2026-09-03)。见 CHANGELOG。 --- 这是什么 **开源 FDE Harness 层。**一人公司 / 小企业的 AI 落地工程师——不睡觉、不离职、自带审计官。**横跨成熟 Agent(执行体:DSH / OpenClaw / WorkBuddy)、纵贯模型层(智力源:通用大模型 + 专属小模型 / 后训练模型)**,嵌在两者之间做治理。以 **FDE 插件 + Skill + MCP + CLI + Dashboard** 五种形态分发:进场,把业务流梳理清楚、把本体图谱构建起来、把 AI 节点部署到位;离场,审计每一次变更,持续优化。 💬 **一句话版本**:你的 AI 员工每次改代码、动文件,都先过一道安检、留一份记录、存一个快照——出事能查、能回滚,这就是 sofagent 干的事。 sofagent 不造 Agent——执行能力交给成熟宿主(模型 + 工具 + 会话),它交付的是 **FDE Harness 层**。**FDE Harness = FDE 方法论 × Harness 工程**…

Recommendation signals

54 Tool quality · Based on stars, downloads, maintenance, security and docs
– User interest · Adjusted by in-site views, install copies and download clicks
54 Overall
0views
0unique visitors
0install copies
0download clicks
0outbound clicks

Meta

License
MIT
Language
TypeScript
GitHub stars
49
mo. downloads
–
Last push
2026-09-24
Created
2026-06-18

Links

Basic safety check

Findings
curated 收录但无 npm 包/安装命令
Sources
curated:awesome-dsh-plugin/awesome-dsh-plugin, curated:0xsline/awesome-deepseek-harness, curated:punkpeye/awesome-mcp-servers
Topics
agent-audit, agent-governance, ai-agents, ai-safety, compliance, dsh, dsh-plugin, enterprise-ai, fdeing, forward-deployed-engineer, forward-deployed-engineering, git-hooks, harness, llm-governance, mcp, ontology, openclaw, pre-commit, secret-scanning, typescript

Related plugins

DeepSeek Harness
Score98

hindsight

vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents

Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.

☆ 27.7K ↓ 124.6K Memory ↗
MCP ServerClaude Code
Score91

firecrawl-mcp-server

firecrawl/firecrawl-mcp-server

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

☆ 7.5K ↓ 126.7K Memory ↗
DeepSeek Harness
Score84

dsh-mnemon

omdsh-dev/dsh-mnemon

Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.

☆ 409 ↓ 36.1K Memory ↗
Claude Code
Score82

get-shit-done

gsd-build/get-shit-done

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.

☆ 64.5K ↓ 48.4K Memory ↗