{"id":"cft0808-edict","name":"edict","homepage":"https://openclaw.ai","repo_url":"https://github.com/cft0808/edict","category":"ai-ml","subcategories":[],"tags":["ai-agents","ai-orchestration","multi-agent","dashboard","kanban","audit-trails","python","react","openclaw","skills-management"],"what_it_does":"Edict is an OpenClaw-based multi-agent orchestration system that routes tasks through a structured approval/dispatch workflow (modeled as “three provinces and six ministries”) and provides a real-time dashboard/kanban with sessions, memorials (archive), model configuration, skills management (including remote skills), and controls to pause/cancel/resume tasks.","use_cases":["Building auditable, multi-step AI agent workflows with approval gates","Task orchestration with real-time operational visibility (kanban, timeline, session monitoring)","Agent-to-agent governance patterns (permissions matrix, protected state transitions)","Programmatic or semi-automated skill/tool injection for specialized agents","Prototype and demonstrate multi-agent systems with UI + operator controls"],"not_for":["High-assurance security environments without additional review and hardening","Production deployments that require formal SLAs, strong backwards-compatibility guarantees, and explicit API contracts","Use cases needing managed cloud-native reliability features (managed queues, retries, idempotency guarantees) out of the box","Teams that cannot run/operate an LLM gateway and dashboard server"],"best_when":"You want a structured, observable multi-agent workflow with human/operator controls and an approval stage before execution, and you can run the local dashboard + OpenClaw gateway.","avoid_when":"You need standardized enterprise APIs (OpenAPI/SDKs) or strong, explicitly documented security boundaries and SLAs; or you plan to integrate primarily via MCP/SDK rather than the provided HTTP endpoints and scripts.","alternatives":["OpenAI Assistants + custom orchestration","LangGraph (graph-based agent workflows with state management)","CrewAI/AutoGen (simpler multi-agent coordination, usually less governance/audit-focused)","Orchestration frameworks with explicit workflow engines (Temporal, Cadence) paired with LLM agents","Custom OpenClaw agent setups without the Edict dashboard/governance layer"],"af_score":43.5,"security_score":48.8,"reliability_score":30.0,"package_type":"skill","discovery_source":["openclaw"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-29T13:20:45.771395+00:00","interface":{"has_rest_api":true,"has_graphql":false,"has_grpc":false,"has_mcp_server":false,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["API key (described as OpenClaw agent API key synchronized to agents)"],"oauth":false,"scopes":false,"notes":"README indicates an API key must be configured (e.g., `openclaw agents add taizi`) and then synchronized to agents. The Edict REST endpoints are shown via curl examples but explicit details about auth requirements per endpoint, header names, and scope granularity are not provided in the provided content."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Licensing is MIT and usage appears self-hosted; README does not describe any hosted pricing or credit-based billing."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":43.5,"security_score":48.8,"reliability_score":30.0,"mcp_server_quality":0.0,"documentation_accuracy":60.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":70.0,"rate_limit_clarity":0.0,"tls_enforcement":50.0,"auth_strength":45.0,"scope_granularity":30.0,"dependency_hygiene":50.0,"secret_handling":70.0,"security_notes":"TLS enforcement and security headers are not specified in the provided README content; authentication details for the Edict REST endpoints are not fully described beyond an OpenClaw API key that is synchronized across agents. There is mention of a state transition validator and permission matrix, which can reduce workflow bypass risk, but the provided material does not include threat-modeling, rate limiting, input sanitization details, or secure defaults for remote skill loading.","uptime_documented":0.0,"version_stability":40.0,"breaking_changes_history":30.0,"error_recovery":50.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["First installation requires configuring an API key and re-running install to sync it to all agents.","Docker image may fail with 'exec format error' on mismatched architecture; platform override may be needed."]}}