goclaw
GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deploy AI agent teams at scale without compro
What is goclaw?
GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deploy AI agent teams at scale without compromising on safety.
Overview of goclaw
What it is
GoClaw is a multi-tenant AI agent platform written in Go. It is a single-binary gateway that provides a multi-agent orchestration system with 8-stage agent pipeline, 4-mode prompt system, 3-tier memory, knowledge vault, agent teams, self-evolution, and multi-tenant PostgreSQL isolation.It supports 20+ LLM providers including Anthropic, OpenAI, OpenRouter, Requesty, Groq, DeepSeek, Gemini, Mistral, xAI, MiniMax, DashScope, Claude CLI, Codex, ACP, and any OpenAI-compatible endpoint.It also integrates 7 messaging channels: Telegram, Discord, Slack, Zalo OA, Zalo Personal, Feishu/Lark, WhatsApp.
Key features
- 8-Stage Agent Pipeline — context → history → prompt → think → act → observe → memory → summarize with pluggable stages and 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) with 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)
- Multi-Tenant PostgreSQL — Per-user workspaces, per-user context files, encrypted API keys (AES-256-GCM), RBAC, isolated sessions
- Production Security — 5-layer permission system, rate limiting, prompt injection detection, SSRF protection, AES-256-GCM encryption
Use cases
This platform is designed for deploying AI agent teams at scale with multi-tenant isolation. Use cases include building autonomous agent workflows, managing multiple AI agents across different departments or users, integrating AI into messaging channels, and creating knowledge-driven applications with memory and orchestration.
Getting started
See the repository README for installation and quick-start instructions.
License and pricing
The license is not stated in the provided metadata. The project is listed as open source.
Based on the project's public README and repository metadata.