Skip to content

Repository files navigation

⚡ AgentBoost

Make your coding agent plan better, remember more, verify its own work, and stay safe — in under 5 minutes.

A thin, pluggable enhancement layer for the agents you already use.
One MCP server · a clean CLI · a local dashboard.

CI License: MIT Node TypeScript MCP PRs welcome

Quick Start · Features · How it works · Tools · Full Guide · 中文


Why AgentBoost?

Coding agents are powerful but unreliable in predictable ways: they go off-track, over-engineer, lose context between sessions, plan weakly, and occasionally run something dangerous. Most fixes mean adopting a heavy new platform.

AgentBoost takes the opposite bet. It's a thin layer that plugs into your existing agent and does five things well:

The agent keeps thinking. AgentBoost gives it structure, memory, guardrails, and feedback — all stored in a plain .agentboost/ folder you can read, diff, and edit.

  • 🔌 No lock-in — works with Claude Code, Cursor, OpenCode, Codex, and any MCP client
  • 🔑 No API keys, no cloud — your agent does the reasoning; data never leaves your machine
  • ⏱️ Useful in 5 minutes — one command to init, one to connect, one to open the dashboard

✨ Features

Feature What it does
🧭 Structured Planning Turn a natural-language goal into a clean Spec + small, individually verifiable steps. Refine iteratively; track per-step status.
🧠 Context & Memory Persistent project memory — decisions, architecture, preferences, and hard-won learnings. Keyword search, importance-aware pruning, one-call context injection.
Automatic Verification Auto-detects your test / typecheck / lint / build commands (npm, tsc, pytest, go, cargo, make), runs them, and returns clear pass/fail to drive fix loops.
🛡️ Safety & Permissions Three permission levels + dangerous-op detection (rm -rf, git push --force, DROP TABLE, DELETE without WHERE…) with human-confirmation gates and an audit log.
🧩 Parallel Sub-agents A bounded, concurrency-capped task runner with simple result aggregation for fan-out work.
📊 Local Web Dashboard See the current phase, plan progress, memory, verification results, and a live activity log — edit memory and permissions right from the browser.

📸 Dashboard

agentboost gui opens a clean, localhost-only dashboard that shows everything at a glance:

┌────────────────────────────────────────────────────────────────┐
│ ⚡ AgentBoost   my-project          [ executing ]  Permission ▾  ↻│
├────────────────────────────────┬───────────────────────────────┤
│ Current Plan                   │ Verification        [Run checks]│
│  Ship search feature           │  ✅ test    npm run test        │
│  ▓▓▓▓▓▓▓░░░  3/5 done           │  ✅ lint    npm run lint        │
│  [x] Add DB index              │  ❌ build   npm run build       │
│  [~] Wire /search API          ├───────────────────────────────┤
│  [ ] Add integration tests     │ Project Memory          [+ Add]│
├────────────────────────────────┤  [decision]     Use SQLite     │
│ Safety Check                   │  [architecture] REST, not gRPC  │
│  > rm -rf build/   ⛔ critical   │  [preference]   2-space indent  │
└────────────────────────────────┴───────────────────────────────┘

💡 Real screenshots/GIFs belong in docs/screenshots/ — run the dashboard against examples/demo-project to capture them.

🚀 Quick Start

# 1 · Initialize AgentBoost in your project (creates .agentboost/)
npx agentboost init

# 2 · Open the dashboard
npx agentboost gui

# 3 · Print the MCP config for your agent
npx agentboost adapters

Connect Claude Code — drop this into .mcp.json at your project root and restart:

{
  "mcpServers": {
    "agentboost": {
      "command": "npx",
      "args": ["-y", "agentboost", "mcp"],
      "env": { "AGENTBOOST_ROOT": "." }
    }
  }
}

Then just tell your agent: "Plan this with AgentBoost first." It calls plan_startplan_create, records decisions with memory_add, runs verify_run after changes, and checks risky commands with safety_check — all visible live in the dashboard.

👉 Full walkthrough (install, every agent, examples, troubleshooting): docs/guide.md

🔌 Supported agents

Agent Integration Config
Claude Code MCP server adapters/claude-code.mcp.json
Cursor MCP server adapters/cursor.cursor/mcp.json
OpenCode / Codex MCP server adapters/opencode
Any MCP client stdio MCP npx -y agentboost mcp
No agent (CLI) terminal every feature works standalone

🛠️ How it works

                    ┌─────────────────────────────┐
   your agent  ────▶│     AgentBoost MCP server    │
   (Claude/…)       │  plan · memory · verify ·    │
                    │  safety · status             │
                    └──────────────┬──────────────┘
   you ──▶ CLI  ───────────────────┤   one shared core
   you ──▶ GUI  ───────────────────┘        │
                                             ▼
                              .agentboost/  (plain files)
             config.yaml · memory.json · plans/ · state.json · audit.log

The MCP server, CLI, and dashboard are three faces of one core, reading and writing a single plain-file data directory. Nothing is hidden — inspect it, diff it in git, or hand-edit it.

🧰 MCP tools

The agent-facing surface is 13 focused tools:

Category Tools
Planning plan_start · plan_create · plan_refine · plan_set_step_status · plan_get
Memory memory_add · memory_search · memory_context · memory_edit
Verification verify_run
Safety safety_check · safety_set_level
Status status

📂 Project structure

agentboost/
├── src/
│   ├── core/      planning · memory · verification · safety · audit · sub-agents · facade
│   ├── mcp/       MCP server (primary agent integration)
│   ├── gui/       local dashboard: http server + static SPA (no build step)
│   └── cli/       command-line tool
├── adapters/      Claude Code · Cursor · OpenCode config templates
├── examples/      runnable demo project
├── docs/          bilingual operation guide + screenshots
└── test/          node --test suite

📦 Install

Zero-install via npx agentboost <command>, or install globally:

npm install -g agentboost

Requirements: Node.js ≥ 18. Minimal dependencies — MCP SDK, commander, yaml, zod.

🧪 Development

npm install
npm run build          # compile TS + copy static assets to dist/
npm test               # run the test suite (node --test)
npm run dev -- status  # run the CLI from source via tsx

Contributions welcome — see CONTRIBUTING.md.

🗺️ Roadmap

  • Real dashboard screenshots & a short demo GIF
  • plan_start templates for common task types (bugfix, feature, refactor)
  • Richer verification (coverage thresholds, custom gates)
  • Optional standing-context sync with AGENTS.md / CLAUDE.md
  • Publish to npm

📄 License

MIT © AgentBoost contributors


🀄 中文简介

AgentBoost 是一个轻量、可插拔的增强层,让你现有的编码 Agent(Claude Code、Cursor、OpenCode、Codex)规划更清晰、记忆更持久、能自动验证、操作更安全

它不是又一个庞大的 Agent 平台,而是一层薄薄的增强:Agent 负责思考,AgentBoost 负责提供结构(计划)、持久化(记忆)、护栏(安全)和反馈(验证) —— 全部存放在项目里可读、可 diff、可手改的 .agentboost/ 纯文本目录。

  • 🔌 无锁定:兼容 Claude Code、Cursor、OpenCode、Codex 及任何 MCP 客户端
  • 🔑 无需 API key、无需联网:推理交给你的 Agent,数据不出本机
  • ⏱️ 五分钟见效:一条命令初始化,一条接入,一条打开面板

核心功能

功能 说明
🧭 结构化规划 把自然语言目标拆成清晰的 Spec + 可逐条验证的小步骤,支持迭代细化与进度跟踪
🧠 上下文与记忆 持久化项目记忆(决策/架构/偏好/经验),关键词搜索、按重要度智能修剪、一键上下文注入
自动验证 自动识别并运行测试 / 类型检查 / lint / 构建,给出清晰通过/失败,驱动修复循环
🛡️ 安全与权限 只读 / 有限写入 / 完全访问 三级权限 + 危险操作检测(rm -rf、强推、DROP TABLE 等)+ 人工确认 + 审计日志
🧩 并行子 Agent 有并发上限的任务执行器 + 结果聚合
📊 本地 Web 面板 实时查看阶段、计划进度、记忆、验证结果与操作日志,可在浏览器里直接编辑

三分钟上手

npx agentboost init      # 在项目里初始化(生成 .agentboost/)
npx agentboost gui       # 打开本地面板
npx agentboost adapters  # 打印你所用 Agent 的 MCP 接入配置

详细中文操作指南(中英双语)见 docs/guide.md

About

A thin, pluggable planning / memory / verification / safety layer for coding agents (Claude Code, Cursor, OpenCode, Codex).

Topics

Resources

Contributing

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages