官方说明7 个来源MCP 服务8 天前

jayasukuv11-beep/agenthelm

Shared, versioned memory for AI coding agents — MCP server with git-style history (log/diff/blame) for Claude Code, Cursor & Claude Desktop

在 GitHub 查看 ↗直链 · 无中转页

配置模板（请按你的客户端调整）

claude mcp add agenthelm -- npx -y agenthelm

这是根据仓库名生成的可粘贴骨架，命令行参数与包名请以该项目 README 为准。

★ 数取值: 6 ★ · jayasukuv11-beep/agenthelm · 取自该仓库的 GitHub 页面 · （2026-10-16 20:00:20 核对）
来源明细: 收录自 punkpeye/awesome-mcp-servers 榜单（我们从中收集的条目之一） · 条目类型：MCP 服务
收录与活跃: 收录于 2026-10-09 · 最近见到 2026-10-16 · 共见到 32 次 · 被 7 个来源列出
评分构成: 综合分 703 · 6 ★ · 7 个来源 · mcp

常见问题（答案都来自我们的记录）

怎么安装？

我们【没有】从该仓库取到安装命令（我们的 install 覆盖率只有约 4%）。请看它的 README 或 releases 页。

它适合谁 / 用来做什么？

我们把它归在这些标签下: MCP 服务。标签来自条目自身，不是我们强加的分类。

谁维护它、还在更新吗？

仓库 jayasukuv11-beep/agenthelm；我们收录于 2026-10-09；最近见到 2026-10-16。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。

第三方质量标记

AgentHelm

以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →

The Control Plane for Autonomous AI Agent Fleets
---
> **AgentHelm** is the control plane that keeps autonomous AI agents safe in production. It wraps any agent framework (LangGraph, CrewAI, custom Python/Node fleets, Claude Code, Cursor) with human-in-the-loop approvals, audit trails, budget guardrails, fail-closed safety, and a shared, versioned **Project Brain** so agents stay accountable, on-budget, and recoverable.
---
🧠 The Project Brain Loop
1. **Get Context**: On startup, an agent fetches versioned, compiled architecture & database context.
2. **Execute Safely**: Agent operates within token budgets and Telegram HITL safety guardrails.
3. **Propose Knowledge**: As agents discover schemas or make design trade-offs, they propose knowledge entries.
4. **Compile & Evolve**: The **Brain Compiler** verifies evidence, resolves conflicts, and releases the next Project Brain version.
---
⚡ 60-Second Setup: Model Context Protocol (MCP)
Plug AgentHelm directly into **Cursor**, **Claude Code**, or **Claude Desktop**:
Add to .cursor/mcp.json or claude_desktop_config.json
Exposed MCP Tools
- **get_context**: Query versioned project architecture, database schemas, and conventions.
- **propose_knowledge**: Propose new engineering decisions and codebase discoveries.
- **get_history**: Audit version history logs, diffs, and decision trace blame.
---
🚀 Programmatic SDKs
Python SDK
Node.js SDK
---
📲 Human-in-the-Loop (HITL) Safety Gate
AgentHelm prevents autonomous catastrophic actions. Mark functions as @irreversible to trigger inline Telegram approval gates:
> **⚠️ Irreversible Action Requested**
> **Agent:** Cloud Architect
> **Action:** destroy_infrastructure
> **Payload:** {"region": "us-east-1"}
>
> [ ✅ Approve ] [ ❌ Reject ]
---
🏗️ Key Architecture Pillars
- **🧠 Brain Compiler**: Versioned knowledge engine resolving schema and architectural decision conflicts.
- **🔭 Fleet Observability**: Real-time telemetry, token cost tracking, and execution tracing.
- **🛡️ Safety Firewall**: Classification decorators (@read, @side_effect, @irreversible) with fail-closed default safety.