goclaw

MCP开发工具

提供方 nextlevelbuilder · 包名 goclaw

开发工具 stdio · 本地进程 未标注 社区 / 第三方 Claude DesktopCursorClineClaude Code
查看接入方式

GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deploy AI agent teams at scale with

一句话选型结论

按资料字段整理

goclaw 属于开发工具类 MCP 服务器,stdio · 本地进程,鉴权方式未标注,可直接接入 Claude Desktop、Cursor、Cline 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类开发工具 传输方式stdio · 本地进程 鉴权未标注 部署方式本地部署
GitHub 星标 2,591 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

开发工具
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

goclaw agent-orchestration ai-agent ai-gateway anthropic

支持客户端

适用场景

goclawagent-orchestrationai-agent

安装与配置

stdio · 本地进程 未标注
客户端在本机拉起子进程,数据不出本机
go install nextlevelbuilder/goclaw@latest

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Cross-platform,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
代码与仓库操作

在对话里直接查代码、提 issue、走 PR,省掉来回切工具。

本地命令与脚本

把构建、测试、格式化这类重复命令交给模型执行。

接口联调与测试

让模型调你的接口、跑一遍用例,快速定位问题。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Cursor、Cline,换客户端不用重新研究配置。
  • 仓库有一定关注度(星标 2,591),遇到问题更容易搜到资料。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在开发工具场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
goclaw当前 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Git 838e2ec1 12 stdio · 本地进程 本地部署 有 2026-05-17
Markitdown MCP 2c653a5f 1 stdio · 本地进程 本地部署 有 2026-05-17
JavaGuide 未标注 stdio · 本地进程 本地部署 有 2026-04-11
awesome-claude-skills 未标注 stdio · 本地进程 本地部署 有 2026-04-26
Context7 831acf40 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

开发工具
字段来自项目仓库与公开索引,中文说明由本站标注
提供方nextlevelbuilder上游标注的维护方 nextlevelbuilder
分类开发工具本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式未标注远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时goclaw · Cross-platform本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-04-11上游最后核验时间

详细介绍

12.7 KB
来自项目仓库与上游目录的原文,未做删改

Multi-Tenant AI Agent Platform

Multi-agent AI gateway built in Go. 20+ LLM providers. 7 channels. Multi-tenant PostgreSQL.

Single binary. Production-tested. Agents that orchestrate for you.

Documentation •
Quick Start •
Twitter / X

🌐 Languages:
🇻🇳 Tiếng Việt ·
🇨🇳 简体中文 ·
🇯🇵 日本語 ·
🇰🇷 한국어 ·
🇵🇭 Tagalog ·
🇪🇸 Español ·
🇧🇷 Português ·
🇮🇹 Italiano ·
🇩🇪 Deutsch ·
🇫🇷 Français ·
🇸🇦 العربية ·
🇮🇳 हिन्दी ·
🇷🇺 Русский ·
🇧🇩 বাংলা ·
🇮🇱 עברית ·
🇵🇱 Polski ·
🇨🇿 Čeština ·
🇳🇱 Nederlands ·
🇹🇷 Türkçe ·
🇺🇦 Українська ·
🇮🇩 Bahasa Indonesia ·
🇹🇭 ไทย ·
🇵🇰 اردو ·
🇷🇴 Română ·
🇸🇪 Svenska ·
🇬🇷 Ελληνικά ·
🇭🇺 Magyar ·
🇫🇮 Suomi ·
🇩🇰 Dansk ·
🇳🇴 Norsk

Core Features

  • 8-Stage Agent Pipeline — context → history → prompt → think → act → observe → memory → summarize. Pluggable stages, always-on execution
  • 4-Mode Prompt System — Full / Task / Minimal / None with section gating, cache boundary optimization, and per-session mode resolution
  • 3-Tier Memory — Working (conversation) → Episodic (session summaries) → Semantic (knowledge graph). Progressive loading L0/L1/L2
  • Knowledge Vault — Document registry with [[wikilinks]], hybrid search (FTS + pgvector), filesystem sync
  • Agent Teams & Orchestration — Shared task boards, inter-agent delegation (sync/async), 3 orchestration modes (auto/explicit/manual)
  • Self-Evolution — Metrics → suggestions → auto-adapt with guardrails. Agents refine their own communication style
  • Multi-Tenant PostgreSQL — Per-user workspaces, per-user context files, encrypted API keys (AES-256-GCM), RBAC, isolated sessions
  • 20+ LLM Providers — Anthropic (native HTTP+SSE with prompt caching), OpenAI, OpenRouter, Requesty, Groq, DeepSeek, Gemini, Mistral, xAI, MiniMax, DashScope, Claude CLI, Codex, ACP, and any OpenAI-compatible endpoint
  • 7 Messaging Channels — Telegram, Discord, Slack, Zalo OA, Zalo Personal, Feishu/Lark, WhatsApp
  • Production Security — 5-layer permission system, rate limiting, prompt injection detection, SSRF protection, AES-256-GCM encryption
  • Single Binary — ~25 MB static Go binary, no Node.js runtime, <1s startup, runs on a $5 VPS
  • Observability — Built-in LLM call tracing with spans and prompt cache metrics, optional OpenTelemetry OTLP export

Desktop Edition (GoClaw Lite)

A native desktop app for local AI agents — no Docker, no PostgreSQL, no infrastructure.

macOS:```bash
curl -fsSL https://raw.githubusercontent.com/nextlevelbuilder/goclaw/main/scripts/install-lite.sh | bash


**Windows (PowerShell):**```powershell
irm https://raw.githubusercontent.com/nextlevelbuilder/goclaw/main/scripts/install-lite.ps1 | iex

What's Included

  • Single native app (Wails v2 + React), ~30 MB
  • SQLite database (zero setup)
  • Chat with agents (streaming, tools, media, file attachments)
  • Agent management (max 5), provider config, MCP servers, skills, cron
  • Team tasks with Kanban board and real-time updates
  • Auto-update from GitHub Releases

Lite vs Standard

Feature Lite (Desktop) Standard (Server)
Agents Max 5 Unlimited
Teams Max 1 (5 members) Unlimited
Database SQLite (local) PostgreSQL
Memory FTS5 text search pgvector semantic
Channels — Telegram, Discord, Slack, Zalo, Feishu, WhatsApp
Knowledge Graph — Full
RBAC / Multi-tenant — Full
Auto-update GitHub Releases Docker / binary

Building from Source```bash

Prerequisites: Go 1.26+, pnpm, Wails CLI (go install github.com/wailsapp/wails/v2/cmd/wails@latest)

make desktop-build # Build .app (macOS) or .exe (Windows)
make desktop-dmg VERSION=0.1.0 # Create .dmg installer (macOS only)
make desktop-dev # Dev mode with hot reload


### Desktop Releases
Desktop uses independent versioning with `lite-v*` tags:```bash
git tag lite-v0.1.0 &amp;&amp; git push origin lite-v0.1.0
# → GitHub Actions builds macOS (.dmg + .tar.gz) + Windows (.zip)
# → Creates GitHub Release with all assets

Architecture

Quick Start

Prerequisites: Go 1.26+, PostgreSQL 18 with pgvector, Docker (optional)

From Source```bash

git clone -b main https://github.com/nextlevelbuilder/goclaw.git && cd goclaw
make build
./goclaw onboard # Interactive setup wizard
source .env.local && ./goclaw


&gt; **Note:** The default branch is `dev` (active development). Use `-b main` to clone the stable release branch.

### With Docker```bash
# Generate .env with auto-generated secrets
chmod +x prepare-env.sh &amp;&amp; ./prepare-env.sh

# Add at least one GOCLAW_*_API_KEY to .env, then:
make up

# If Postgres fails to start (&quot;port 5432 already allocated&quot;), set another host
# port in .env, e.g. POSTGRES_PORT=5433 (see .env.example).

# Web Dashboard at http://localhost:18790 (built-in)
# Health check: curl http://localhost:18790/health

# Optional: separate nginx for custom SSL/reverse proxy
# make up WITH_WEB_NGINX=1  → Dashboard at http://localhost:3000

make up creates a Docker network, embeds the correct version from git tags, builds and starts all services, and runs database migrations automatically.

Common commands:```bash
make up # Start all services (build + migrate)
make down # Stop all services
make logs # Tail logs (goclaw service)
make reset # Wipe volumes and rebuild from scratch


**Operator CLI:**

The main `goclaw` binary can also inspect local or remote gateways:```bash
goclaw traces list --status error
goclaw traces get &lt;trace-id&gt; -o json
goclaw --server https://goclaw.example.com --token &quot;$GOCLAW_GATEWAY_TOKEN&quot; traces follow --session &lt;session-key&gt;

Optional services — enable with WITH_* flags:

Flag Service What it does
WITH_BROWSER=1 Headless Chrome Enables browser tool for web scraping, screenshots, automation
WITH_OTEL=1 Jaeger OpenTelemetry tracing UI for debugging LLM calls and latency
WITH_SANDBOX=1 Docker sandbox Isolated container for running untrusted code from agents
WITH_TAILSCALE=1 Tailscale Expose gateway over Tailscale private network
WITH_REDIS=1 Redis Redis-backed caching layer

Flags can be combined and work with all commands:```bash

Start with browser automation and tracing

make up WITH_BROWSER=1 WITH_OTEL=1

Stop everything including optional services

make down WITH_BROWSER=1 WITH_OTEL=1


When `GOCLAW_*_API_KEY` environment variables are set, the gateway auto-onboards without interactive prompts — detects provider, runs migrations, and seeds default data.

&gt; **Docker image variants:**
&gt; · Image · Description
&gt;
&gt; · `latest` · Backend + embedded web UI + Python (**recommended**)
&gt; · `latest-base` · Backend API-only, no web UI, no runtimes, no media probes (`read_video` and `read_audio` refuse without `ffprobe`; `read_document` falls back to the 1000-page ceiling without `pdfinfo`)
&gt; · `latest-full` · All runtimes + skill dependencies pre-installed
&gt; · `latest-otel` · Latest + OpenTelemetry tracing
&gt; · `goclaw-web` · Standalone nginx + React SPA (for custom reverse proxy)
&gt;
&gt; For custom builds (Tailscale, Redis): `docker build --build-arg ENABLE_TSNET=true ...`
&gt; See the Deployment Guide for details.

## Easypanel

Easypanel is a self-hosted Docker deployment platform, and GoClaw has a one-click deployment template there: https://easypanel.io/templates/goclaw. It deploys the full stack (Postgres with pgvector, the GoClaw backend, headless Chrome for browser automation, and the web UI) - you&#x27;ll still need to set your `GOCLAW_*_API_KEY` after deploying.

## Updating

### Docker```bash
docker compose pull &amp;&amp; docker compose up -d

Binary (with embedded web UI)```bash

goclaw update --apply # Downloads, verifies SHA256, swaps binary, restarts


### Web Dashboard
Open **About** dialog → click **Update Now** (admin only). The update includes both backend and web dashboard when using the default `latest` image.

## Multi-Agent Orchestration

Each agent runs with its own identity, tools, LLM provider, and context files.
Agent Links define outbound, inbound, or bidirectional permission edges.
Delegation can run synchronously or asynchronously and exchanges files through
an isolated delegation workspace; validated outputs are published back under
the caller&#x27;s `.delegations//` directory.

&gt; Details: Agent Teams docs

## Knowledge Vault

Document registry with `[[wikilinks]]` for bidirectional linking. Hybrid search combines full-text (BM25) and semantic (pgvector) for precise retrieval. Filesystem sync keeps vault in sync with on-disk files.

## Self-Evolution

Agents improve themselves through a 3-stage guardrailed pipeline: metrics collection → suggestion analysis → auto-adaptation. Can refine communication style and domain expertise (CAPABILITIES.md) — but never change identity, name, or core purpose.

## Provider Adapters

20+ LLM providers unified through a single adapter interface. Capability-based routing, encrypted API keys (AES-256-GCM), extended thinking support per-provider, and prompt caching for Anthropic + OpenAI.

## Event-Driven Architecture

Typed domain events power the consolidation pipeline — session summaries, knowledge graph extraction, and dreaming promotion all run asynchronously via worker pools with dedup and retry.

## Built-in Tools

30+ tools across 8 categories:

| Category | Tools | Description |
|----------|-------|-------------|
| **Filesystem** | `read_file`, `write_file`, `edit_file`, `list_files`, `search`, `glob` | File operations with virtual FS routing |
| **Runtime** | `exec`, `browser` | Shell commands (approval workflow) + browser automation |
| **Web** | `web_search`, `web_fetch` | Search (Brave, DuckDuckGo) + content extraction |
| **Memory** | `memory_search`, `memory_get`, `knowledge_graph_search` | 3-tier memory + KG traversal |
| **Media** | `create_image`, `create_audio`, `create_video`, `read_*`, `tts` | Generation + analysis (multi-provider) |
| **Skills** | `skill_search`, `use_skill`, `skill_manage` | BM25 + semantic hybrid search |
| **Teams** | `team_tasks`, `spawn`, `delegate`, `message` | Task board + orchestration + messaging |
| **Automation** | `cron`, `heartbeat`, `sessions_*` | Scheduling + session management |

&gt; Full tool reference at docs.goclaw.sh

## Webhook API

Trigger agents or send channel messages from external systems without the gateway token.```bash
# Bearer auth — sync LLM call
curl -X POST https://example.com/v1/webhooks/llm \
  -H &quot;Authorization: Bearer wh_...&quot; \
  -H &quot;Content-Type: application/json&quot; \
  -d &#x27;{&quot;input&quot;:&quot;Summarize today metrics&quot;,&quot;mode&quot;:&quot;sync&quot;}&#x27;

# HMAC auth — sign with hmac_signing_key from create response
TS=$(date +%s); BODY=&#x27;{&quot;input&quot;:&quot;hi&quot;,&quot;mode&quot;:&quot;sync&quot;}&#x27;
SIG=$(echo -n &quot;${TS}.${BODY}&quot; | openssl dgst -sha256 -mac HMAC \
      -macopt &quot;hexkey:${WEBHOOK_HMAC_KEY}&quot; | awk &#x27;{print $2}&#x27;)
curl -X POST https://example.com/v1/webhooks/llm \
  -H &quot;Content-Type: application/json&quot; \
  -H &quot;X-Webhook-Id: ${WEBHOOK_ID}&quot; \
  -H &quot;X-GoClaw-Signature: t=${TS},v1=${SIG}&quot; \
  -d &quot;$BODY&quot;

See docs/webhooks.md for the full reference: auth, async callbacks, retry schedule, HMAC examples, channel matrix.

Documentation

Full documentation at docs.goclaw.sh — or browse the source in goclaw-docs/

Section Topics
Getting Started Installation, Quick Start, Configuration, Web Dashboard Tour
Core Concepts Agent Loop, Sessions, Tools, Memory, Multi-Tenancy
Agents Creating Agents, Context Files, Personality, Sharing & Access
Providers Anthropic, OpenAI, OpenRouter, Gemini, DeepSeek, +15 more
Channels Telegram, Discord, Slack, Feishu, Zalo, WhatsApp, WebSocket
Agent Teams Teams, Task Board, Messaging, Delegation & Handoff
Advanced Custom Tools, MCP, Skills, Cron, Sandbox, Hooks, RBAC
Deployment Docker Compose, Database, Security, Observability, Tailscale
Reference CLI Commands, REST API, WebSocket Protocol, Environment Variables

Testing```bash

go test ./... # Unit tests
go test -v ./tests/integration/ -timeout 120s # Integration tests (requires running gateway)
```

Project Status

See CHANGELOG.md for detailed feature status including what's been tested in production and what's still in progress.

Acknowledgments

GoClaw was originally inspired by the OpenClaw project architecture.

License

CC BY-NC 4.0 — Creative Commons Attribution-NonCommercial 4.0 International

Star History

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
goclaw 怎么安装?

在客户端按下面的安装命令接入:go install nextlevelbuilder/goclaw@latest。对应的包名是 goclaw。装完在客户端配置里引用同一个包或端点。

goclaw 怎么在 Claude Desktop、Cursor、Cline 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

goclaw 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

goclaw 需要 API Key 吗?

资料没有标注鉴权方式,是否需要密钥取决于服务本身,接入前按官方文档确认。

goclaw 支持哪些客户端?

资料标注支持 Claude Desktop、Cursor、Cline、Claude Code;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

goclaw 能提供哪些能力?

资料显示能力标签包括 goclaw、agent-orchestration、ai-agent、ai-gateway、anthropic。具体工具清单以官方文档为准。

goclaw 需要什么运行环境?

运行时为 Cross-platform;属于本地进程,需要在本机装好运行环境。

goclaw 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-04-11。