#5151st of 102 in Agent platforms
goclaw
Multi-tenant agent gateway in Go with team delegation, memory and chat channels
- Stars
- 3.7k
- License
- custom license
- Last commit
- Nov 2026
- Last release
- Jun 2026
- Language
- Go
2,817 on 25 Apr 20263,721 on 14 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Before you pick it
- Known advisory in latest version. 2 known advisories: github.com/nextlevelbuilder/goclaw v1.76.1, the latest version. Source (opens in a new tab), checked .
Overview
GoClaw is a Go gateway that runs multiple agents, each with its own identity, tools and LLM provider, and connects them to Telegram, Discord, Slack, Zalo, Feishu/Lark and WhatsApp. It stores per-user workspaces, sessions and encrypted API keys in PostgreSQL with pgvector, and includes agent teams with task boards, a three-tier memory and a web dashboard. A lighter desktop edition uses SQLite with a smaller feature set.
Who it is for: Self-hosters running multi-user agent teams on chat channels, non-commercially
Strengths
- Per-user workspaces, RBAC and AES-256-GCM encrypted API keys for multi-tenant hosting
- 20+ providers including Anthropic, OpenAI, Gemini, DeepSeek and any OpenAI-compatible endpoint
- Static ~25 MB Go binary; built-in tracing with optional OpenTelemetry export
- Webhook API with bearer or HMAC auth to trigger agents from external systems
Weaknesses
- CC BY-NC 4.0 license forbids commercial use
- Server edition requires PostgreSQL 18 with pgvector
- Desktop Lite edition caps at 5 agents and has no channels or RBAC
- Default branch is dev; stable code is on main, so cloning needs -b main
What it needs
- no GPU
- Docker + Compose
- Needs PostgreSQL 18 with pgvector, Docker (optional), Headless Chrome (optional), Redis (optional)
- Models: Anthropic, OpenAI, OpenRouter, Groq, DeepSeek
- port 18790
Also in Agent platforms
See all 102| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 95 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 95 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, served as API or MCP server | 94 out of 100 |
| #4 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 93 out of 100 |
| #5 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |