Enterprise 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

A Go port of OpenClaw with enhanced security, multi-tenant PostgreSQL, and production-grade observability.

🌐 Languages: 🇨🇳 简体中文 · 🇯🇵 日本語 · 🇰🇷 한국어 · 🇻🇳 Tiếng Việt · 🇵🇭 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

• Agent Teams & Orchestration — Teams with shared task boards, inter-agent delegation (sync/async), and hybrid agent discovery
• Multi-Tenant PostgreSQL — Per-user workspaces, per-user context files, encrypted API keys (AES-256-GCM), isolated sessions
• Single Binary — ~25 MB static Go binary, no Node.js runtime, <1s startup, runs on a $5 VPS
• Production Security — 5-layer permission system (gateway auth → global tool policy → per-agent → per-channel → owner-only) plus rate limiting, prompt injection detection, SSRF protection, shell deny patterns, and AES-256-GCM encryption
• 20+ LLM Providers — Anthropic (native HTTP+SSE with prompt caching), OpenAI, OpenRouter, Groq, DeepSeek, Gemini, Mistral, xAI, MiniMax, Cohere, Perplexity, DashScope, Bailian, Zai, Ollama, Ollama Cloud, Claude CLI, Codex, ACP, and any OpenAI-compatible endpoint
• 7 Messaging Channels — Telegram, Discord, Slack, Zalo OA, Zalo Personal, Feishu/Lark, WhatsApp
• Extended Thinking — Per-provider thinking mode (Anthropic budget tokens, OpenAI reasoning effort, DashScope thinking budget) with streaming support
• Heartbeat System — Periodic agent check-ins via HEARTBEAT.md checklists with suppress-on-OK, active hours, retry logic, and channel delivery
• Scheduling & Cron — at, every, and cron expressions for automated agent tasks with lane-based concurrency
• Observability — Built-in LLM call tracing with spans and prompt cache metrics, optional OpenTelemetry OTLP export

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

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

# Generate .env with auto-generated secrets
chmod +x prepare-env.sh && ./prepare-env.sh

# Add at least one GOCLAW_*_API_KEY to .env, then:
docker compose -f docker-compose.yml -f docker-compose.postgres.yml \
  -f docker-compose.selfservice.yml up -d

# Web Dashboard at http://localhost:3000
# Health check: curl http://localhost:18790/health

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

For build variants (OTel, Tailscale, Redis), Docker image tags, and compose overlays, see the Deployment Guide.

GoClaw supports agent teams and inter-agent delegation — each agent runs with its own identity, tools, LLM provider, and context files.

Agents communicate through explicit permission links with direction control (outbound, inbound, bidirectional) and concurrency limits at both per-link and per-agent levels.

• Shared task board — Create, claim, complete, search tasks with blocked_by dependencies
• Team mailbox — Direct peer-to-peer messaging and broadcasts
• Tools: team_tasks for task management, team_message for mailbox

For delegation details, permission links, and concurrency control, see the Agent Teams docs.

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

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

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

GoClaw is built upon the original OpenClaw project. We are grateful for the architecture and vision that inspired this Go port.

MIT