Practical overview
When it fits
Use Edict when a task benefits from multiple specialized agents, explicit workflow stages, review before execution or an auditable record of agent activity.
Who it is for
- Developers building multi-agent orchestration workflows
- Teams exploring approval-gated agent pipelines
- Users who need task status and execution history for AI workflows
- People testing different models across specialized orchestration roles
Documented uses
- Route complex tasks through separate planning, review, dispatch and execution stages.
- Divide work among parallel specialist agents.
- Review or reject plans before agent execution.
- Configure models for different orchestration roles.
- Inspect workflow status and audit execution history.
Requirements & limits
The repository is public and uses an MIT license. Linux, Docker, server and self-hosted contexts are listed. Docker documentation exposes port 7891 for a dashboard demo with preloaded simulated data; this does not establish production deployment behavior.
- Its value depends on whether your workflow needs multiple coordinated agent roles rather than a single-agent flow.
- The staged structure is relevant when planning, review, dispatch and execution should remain distinct.
- Audit trails and dashboard monitoring matter when workflow visibility and execution history are required.
- Python is the primary implementation language, with OpenClaw, Claude and OpenAI listed in the project ecosystem context.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Run the Edict dashboard demo with Docker
Launch the dashboard demo with its preloaded simulated data.
Before you start
- Docker
- A host capable of exposing port 7891
Steps
Run the command below.
docker run -p 7891:7891 cft0808/sansheng-demoOpen
http://localhost:7891to access the dashboard.If an
exec format erroroccurs on an x86/amd64 machine, run the command below instead.docker run --platform linux/amd64 -p 7891:7891 cft0808/sansheng-demoAlternatively, use the command below, which includes the documented
linux/amd64platform setting.docker compose up
Expected outcome
The Edict dashboard demo is accessible locally and displays preloaded simulated data.
Guide limitations
- The documented Docker path demonstrates a dashboard demo with simulated data, not production deployment.
- The README also shows a different image name in one demo note; this recipe follows the explicit quick-start command and its documented image.
- The evidence does not document connecting the demo to live agents or external services.
Install Edict and initialize its OpenClaw agent workspaces
Install the documented Edict project and let its installer configure the agent structure and dashboard prerequisites.
Before you start
- OpenClaw installed
- Python 3.10 or newer
- macOS or Linux
- Node.js 18 or newer for React frontend construction
Steps
Clone the repository with the command below.
git clone https://github.com/cft0808/edict.gitEnter the project directory with
cd edict.Make the installer executable and run it with
chmod +x install.sh && ./install.sh.Allow the installer to create workspaces, write agent rules, register agents and permissions, link shared data and scripts, configure communication visibility, synchronize API keys, and initialize the data directory.
Expected outcome
The documented installer configures the Edict/OpenClaw agent workspaces and related project initialization; the frontend is built when Node.js 18 or newer is available.
Guide limitations
- The evidence documents installation and initialization, but not a subsequent execution or deployment procedure.
- The frontend build is skipped if Node.js is not installed.
- The installer synchronizes an API key from an already configured agent; the evidence does not specify provider setup or key-management details.
- The documented prerequisites list macOS and Linux, not other operating systems.
Compare options for Agent orchestration
These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.
| Project | Documented purpose | Platform | Access and requirements |
|---|---|---|---|
| Edict | Route complex tasks through separate planning, review, dispatch and execution stages. | Docker, Linux, Self-hosted, Server | The repository is public and uses an MIT license. Linux, Docker, server and self-hosted contexts are listed. Docker documentation exposes port 7891 for a dashboard demo with preloaded simulated data; this does not establish production deployment behavior. |
| Massgen | Run multiple AI agents against the same user task. | CLI | The repository documents installation through pip or uv and requires Python 3.11 or later. Setup can configure API keys for OpenAI, Anthropic, Google and xAI; credentials are needed for the selected model backends. |
| Langchain Multi Agents Boilerplate | Route incoming football questions to model and agent workflows according to task complexity. | Web | The repository is public and specifies an MIT license. Running the application requires OpenAI and Groq API keys and a Redis server. |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 30 September 2026
- Original website title
- cft0808/edict · Official homepage title · retained in its source language