edict

Multi-agent AI orchestration framework inspired by China's imperial administrative system, structuring 12 specialized agents into a hierarchical workflow with mandatory review gates, real-time Kanban dashboard, and full audit trails.

Evaluated Mar 08, 2026 (0d ago) vlatest
Homepage ↗ Repo ↗ AI & Machine Learning multi-agent orchestration openclaw dashboard kanban audit-trail workflow-automation agent-framework
⚙ Agent Friendliness
34
/ 100
Can an agent use this?
🔒 Security
31
/ 100
Is it safe for agents?
⚡ Reliability
22
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
60
Error Messages
50
Auth Simplicity
90
Rate Limits
5

🔒 Security

TLS Enforcement
30
Auth Strength
15
Scope Granularity
40
Dep. Hygiene
40
Secret Handling
35

No authentication on dashboard API. Internal permission matrix between agents but no external access control documented. Very new project.

⚡ Reliability

Uptime/SLA
0
Version Stability
25
Breaking Changes
20
Error Recovery
45
AF Security Reliability

Best When

You need structured multi-agent workflows with mandatory review gates, real-time visibility, and comprehensive audit trails.

Avoid When

You want simple agent orchestration, are not using OpenClaw, or need minimal infrastructure overhead.

Use Cases

  • • Complex multi-agent task orchestration with quality control gates
  • • AI workflows requiring audit trails and task intervention capabilities
  • • Teams needing visual real-time monitoring of agent activities
  • • Structured agent collaboration with strict permission boundaries

Not For

  • • Simple single-agent use cases
  • • Teams unfamiliar with OpenClaw framework
  • • Projects needing lightweight agent orchestration without ceremony

Interface

REST API
Yes
GraphQL
No
gRPC
No
MCP Server
No
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No explicit auth documented. Dashboard API endpoints appear unauthenticated. LLM provider keys configured per-agent.

Pricing

Model: open_source
Free tier: Yes
Requires CC: No

MIT license. LLM provider costs are external. Requires OpenClaw framework.

Agent Metadata

Idempotent
Unknown
Retry Guidance
Documented

Known Gotchas

  • ⚠ Depends on OpenClaw framework — additional dependency
  • ⚠ Very new project (Feb 2026) — stability unproven
  • ⚠ Dashboard API endpoints not formally documented
  • ⚠ Chinese-primary documentation may hinder English-only teams
  • ⚠ Complex 12-agent architecture may be overkill for most use cases

Alternatives

crewai autogen langraph swarm

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for edict.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo
API endpoint ↗ Agent guide ↗ Report inaccuracy

Scores are editorial opinions as of 2026-03-08.

6961
Packages Evaluated
25669
Need Evaluation
173
Need Re-evaluation
♥
Community Powered