Edict vs NanoClaw
Which should you use? A side-by-side look at what each one does, who it suits, what it costs, how hard it is to set up, and where each falls short.
Open source · MIT
Multi-agent AI system modeled on China's Tang-era governance, with a live task dashboard, requires OpenClaw.
Open source · MIT
A small, container-isolated AI assistant that connects to chat apps and runs on Anthropic's Agent SDK.
The short answer
Choose Edict if you need…
- Developers already running OpenClaw who want a multi-agent workflow with visible task history
- People who want a review step before agent output is executed, as the README describes
- Teams who want to watch and pause agent tasks from a dashboard
- Users who want to switch the LLM model used by each agent from a UI
Choose NanoClaw if you need…
- Developers who want a small codebase they can read and change
- People who want an assistant on chat apps with container-level isolation
- Users comfortable working with Claude Code to customize their fork
- Anyone who wants separate agents with separate memory per channel
Side-by-side
| Edict | NanoClaw | |
|---|---|---|
| Type | AI model / agent | AI model / agent |
| Price | Free and open source | Free and open source |
| Licence | MIT | MIT |
| GitHub stars | 17k | 31.1k |
| Setup difficulty | Advanced | Intermediate |
| How you get it | Clone and build from source | Clone and build from source |
| Main language | Python | TypeScript |
| Last code update | 39 days ago | 4 days ago |
What each one is
Edict
Edict is a set of about 12 AI agents arranged in roles borrowed from an ancient Chinese imperial administration: one sorts incoming requests, others plan, review, and dispatch work, and six execution departments carry it out. A web dashboard shows tasks on a kanban board, agent health, token usage, and an audit trail of each task's path. It is built to run on top of OpenClaw, which the README lists as a requirement.
NanoClaw
NanoClaw is an open-source AI assistant you run on your own machine. It connects to messaging apps such as WhatsApp, Telegram, Slack, Discord and others, and each agent runs in its own Linux container so it can only see files you explicitly mount. The README describes it as a smaller alternative to OpenClaw, designed to be read and modified as code rather than configured through many settings.
Best for
Edict
- Developers already running OpenClaw who want a multi-agent workflow with visible task history
- People who want a review step before agent output is executed, as the README describes
- Teams who want to watch and pause agent tasks from a dashboard
- Users who want to switch the LLM model used by each agent from a UI
NanoClaw
- Developers who want a small codebase they can read and change
- People who want an assistant on chat apps with container-level isolation
- Users comfortable working with Claude Code to customize their fork
- Anyone who wants separate agents with separate memory per channel
Strengths
Edict
- Dashboard shows task status, heartbeats, and full task history in one place
- README describes a review stage that can send work back for rework before execution
- Configuration is set up by an install script and can run as a systemd service
NanoClaw
- Agents run in containers and only see explicitly mounted files, per the README
- The codebase is described as small, with one process and a handful of files
- Supports many channels and can use Claude, Codex, OpenCode, Cursor or local Ollama models
Not ideal for
Edict
- People without OpenClaw installed, since the README lists it as required and the dashboard depends on it for live data
- Non-technical users, because setup involves shell scripts, API keys, and an agent configuration
- Anyone needing Windows support, since the README lists macOS and Linux as the prerequisites
NanoClaw
- Non-technical users who want a finished app with no setup, since install runs shell scripts and may require Docker and Node
- Users on native Windows, since the README lists macOS, Linux and WSL2 for containers
- People who expect a monitoring dashboard or debugging UI, which the README says is intentionally absent
Trade-offs
Edict
- Depends on OpenClaw, so it is not useful on its own without that separate system
- README is written mainly in Chinese, and the English README is a separate file the excerpt did not include
- No formal release is listed, and some claims in the README (such as comparisons with other frameworks) are the author's own
NanoClaw
- Relies on Claude Code and Anthropic's Agent SDK for its default workflow, so it assumes that stack
- Setup and customization depend on Claude Code, and the README says there is no monitoring UI
- Some features, such as the credential gateway and prebuilt image, involve a third-party gateway or optional account
Getting started
Edict
Clone the repository
git clone https://github.com/cft0808/edict.gitEnter the project folder
cd edictNanoClaw
Clone the repository
git clone https://github.com/nanocoai/nanoclaw.git nanoclaw-v2Enter the directory
cd nanoclaw-v2Frequently asked questions
What is the difference between Edict and NanoClaw?
Edict: Multi-agent AI system modeled on China's Tang-era governance, with a live task dashboard, requires OpenClaw. NanoClaw: A small, container-isolated AI assistant that connects to chat apps and runs on Anthropic's Agent SDK. Edict suits developers already running openclaw who want a multi-agent workflow with visible task history, while NanoClaw suits developers who want a small codebase they can read and change.
Are Edict and NanoClaw free?
Edict: Free and open source. NanoClaw: Free and open source.
Which is easier to set up, Edict or NanoClaw?
NanoClaw is easier to get started with (rated intermediate); Edict is rated advanced and usually needs more setup.
Is Edict or NanoClaw more popular?
NanoClaw has more GitHub stars (31.1k) than Edict (17k). Popularity isn't the same as fit — check which one matches your use case above.
What are other alternatives to Edict and NanoClaw?
Other options people compare them with include CrewAI, MetaGPT, SuperAGI, DeerFlow, Ponytail.
Keep comparing
Built from our catalogue entries for both products: open-source details come from each project's README (AI-assisted, refreshed weekly) and GitHub data; AI-tool details are editorial. Spotted something wrong? Let us know from either product's page.