AI Agents
octomind
An MCP-native AI coding agent and runtime in a single binary.
★ 151 starsApache-2.0
View guide →// agents · nextlevelbuilder/goclaw
goclaw
goclaw is an open-source ai agents project by nextlevelbuilder (nextlevelbuilder/goclaw on GitHub). It has 3,643 GitHub stars and 1,069 forks, is released under the CC BY-NC 4.0 license, and was last updated on GitHub on 4 October 2026.
OpenClaw rebuilt in Go — multi-tenant AI agent teams with 5-layer security in a single binary.
★ 3.6k stars⑂ 1.1k forksCC BY-NC 4.0updated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- nextlevelbuilder/goclaw
- GitHub stars
- 3,643
- Forks
- 1,069
- License
- CC BY-NC 4.0
- Last updated on GitHub
- 4 October 2026
- Category
- AI Agents
- Listing
- Full install guide
- Official site
- Official site
// how it works
How it works
- Clarify your goal
Decide the first concrete outcome you want from it, so you can pick the right example, template or mode instead of exploring everything at once.
- Get the project
Clone the repository (or install the published package) and skim its README quick start for the requirements for your platform.
- Install and configure
Run the documented install step and set any required configuration — such as provider keys, data sources or local services — before the first run.
- Run your first task
Execute the smallest documented example end to end, confirm the output is what you expected, then adapt it to your real data or workflow.
// features
Why people love it
8-stage agent pipeline
Context → history → prompt → think → act → observe → memory → summarize, with pluggable stages.
3-tier memory and Knowledge Vault
Working, episodic and semantic memory, plus a document registry with wikilinks and hybrid FTS + pgvector search.
Agent teams
Shared task boards, inter-agent delegation (sync/async) and auto/explicit/manual orchestration modes.
20+ LLM providers
Anthropic, OpenAI, OpenRouter, Groq, DeepSeek, Gemini, Mistral, xAI and any OpenAI-compatible endpoint, plus Claude CLI/Codex/ACP.
Channels and security
Telegram, Discord, Slack, Zalo, Feishu/Lark and WhatsApp channels; 5-layer permissions, injection detection, SSRF protection and AES-256-GCM key encryption.
Self-evolution with guardrails
Metrics feed suggestions that auto-adapt agent behaviour within guardrails, with full LLM call tracing.
Advertisement
// run it
Run it yourself
- Clone the repository
Get the source so you can inspect, configure and run it locally.
git clone https://github.com/nextlevelbuilder/goclaw.git cd goclaw - Install the lite binary
Use the official install script, or pull the Docker stack as the README describes.
curl -fsSL https://raw.githubusercontent.com/nextlevelbuilder/goclaw/main/scripts/install-lite.sh | bash - Or run with Docker
Generate the .env, add at least one provider key, and start the stack; the dashboard listens on port 18790.
make up # after adding a GOCLAW_*_API_KEY to .env — see README # Web Dashboard at http://localhost:18790
// use cases
What you can build
- Run a multi-tenant agent team for a whole company on one VPS
- Operate Telegram and Discord agent bots from one deployment
- Give each user an isolated workspace with its own memory and keys
- Automate office workflows with agent teams and a knowledge vault
Advertisement
// faq
Questions, answered
Who maintains goclaw?
It is maintained by nextlevelbuilder on GitHub (nextlevelbuilder/goclaw), where the source, issues and releases live.
Is it free to use?
The code is free for non-commercial use under CC BY-NC 4.0 (attribution required); commercial use is not covered by that licence.
Does it need a paid API key?
Yes — you add at least one LLM provider key (GOCLAW_*_API_KEY) for the providers you enable; the software itself is free for non-commercial use under CC BY-NC 4.0.
How does it compare to the original OpenClaw (Node.js) implementation?
Compared with the original OpenClaw (Node.js) implementation, goclaw's distinguishing focus is: openClaw rebuilt in Go — multi-tenant AI agent teams with 5-layer security in a single binary. Pick it when that focus matches your need; the alternative may suit you better if its broader or different scope is the priority.
How do I get started?
Clone https://github.com/nextlevelbuilder/goclaw (or install its published package), follow the README quick start to install and configure it, then run the smallest documented example — the Run section on this page mirrors those steps.
// keep exploring
Similar tools
AI Agents
moltis
Secure persistent personal agent server in one Rust binary — sandboxed, multi-provider, on your hardware
★ 2.9k starsMIT
View guide →AI Agents
OpenYabby
A voice-driven multi-agent assistant that orchestrates in realtime.
★ 130 starsMIT
View guide →Agents
danghuangshang
Multi-agent court inspired by ancient China: specialized agents debate and decide.
★ 2.7k starsMIT
View guide →AI Agents
agentic_coding_flywheel_setup
Turn a fresh Ubuntu VPS into a multi-agent dev environment.
★ 1.7k starsNOASSERTION
View guide →AI Agents
SkillSpector
NVIDIA's security scanner for AI agent skills - check before you install
★ 19.7k starsApache-2.0
View guide →// alternatives
Alternatives in AI Agents
The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if goclaw is not the right fit.
- openclaw★ 391.6k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294.9k
An agentic skills framework & software development methodology that works.
- ECC★ 275.2k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252.0k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245.5k
DeepSeek's plugin-based agent harness where everything is a plugin.
// more in agents
More in AI Agents
Nearby AI Agents projects in the catalogue, closest in stars to goclaw — keep exploring the shelf either side of it.
- antigravity-sdk-python★ 3.7k
Google's Python SDK for building AI agents on the Antigravity platform and Gemini models.
- dbhub★ 3.6k
A token-conscious MCP server that connects AI tools to Postgres, MySQL, SQLite and more.
- morphik-core★ 3.7k
An open-source multimodal retrieval engine for agent pipelines.
- TradingAgents-astock★ 3.6k
A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等)，7位分析师基于A股规则的辩论决策，基于TradingAgents深度改造，适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear deb…
- AgentBench★ 3.8k
A rigorous benchmark for LLMs acting as agents.
- onecli★ 3.6k
An open-source sandboxed agent harness for teams — a secured personal agent for every employee.
Get goclaw
Free and open — grab the source, star the repo, and start creating.