awesome-repositories.com
Blog
MCP
awesome-repositories.com

Descoperă cele mai bune repository-uri open source cu căutare AI.

ExploreazăCăutări recomandateAlternative open-sourceSoftware self-hostedBlogHartă site
ProiectDespreCum realizăm clasamentulPresăServer MCP
LegalConfidențialitateTermeni
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
cft0808 avatar

cft0808/edict

0
View on GitHub↗
16,123 stele·1,698 fork-uri·Python·MIT·3 vizualizăriopenclaw.ai↗

Edict

Edict is a multi-agent orchestration system and framework designed to coordinate specialized large language model agents. It functions as a workflow designer and orchestrator that decomposes complex objectives into structured plans, using directed acyclic graphs and role-based hierarchies to execute sub-tasks.

The system is distinguished by its event-driven architecture, utilizing a publish-subscribe event bus and transactional outbox to manage agent communications and task transitions. It features a dedicated skill management system that allows for the importation, updating, and sandboxed execution of specialized capabilities from remote repositories or URL-based hubs.

Operational governance is provided through state-machine workflow validation, role-based permission matrices, and an agentic audit log that records all state changes for full traceability. Monitoring is handled via a real-time dashboard that tracks agent reasoning, token consumption, and task progress.

The framework includes capabilities for automated data collection, scheduled briefing generation, and integration with third-party messaging platforms and project management tools.

Features

  • Automation Workflows - Designs automated sequences of LLM tasks using directed acyclic graphs and state machine transitions.
  • Event-Driven Agent Communications - Employs messaging protocols and an event-driven framework to coordinate interactions and transitions between specialized agents.
  • Skill Lifecycle Management - Provides a complete lifecycle for agent capabilities, including installation, versioning, and updates from remote sources.
  • Agent Task Lifecycles - Tracks agent tasks through a complete pipeline from creation and planning to execution and final archiving.
  • Agentic Planning - Provides architectures that decouple high-level strategic reasoning and planning from low-level task execution.
  • Reasoning Traceability - Persists all events and state changes to a database to audit the reasoning and logic of agents.
  • Skill Importation - Downloads and assigns specialized capabilities to agents from repositories, URLs, or local file paths.
  • Event-Driven Agent Runtimes - Implements an execution environment that manages asynchronous message passing and state transitions via an event bus.
  • Request Routing - Implements a recommendation-based routing system to assign tasks to the most appropriate specialized agent.
  • Agentic Workflow Graphs - Decomposes complex objectives into directed acyclic graphs to assign tasks to specialized agents.
  • AI Agent Skills - Enables the dynamic importation and updating of specialized capabilities for agents from remote skill hubs.
  • Agent Governance - Enforces communication hierarchies and permission matrices to govern the behavior of autonomous agents.
  • Hierarchical Agent Orchestration - Organizes agents into a structured manager-worker hierarchy with defined roles to ensure quality control.
  • Model Routing Layers - Provides a configuration layer to dynamically map individual agents to different LLMs to optimize specific personas.
  • Multi-Agent Orchestration - Framework for decomposing and delegating complex goals across a team of specialized autonomous agents.
  • Persona Configurations - Defines agent roles, personas, and output specifications through markdown-based configuration files.
  • Remote Skill Imports - Dynamically imports specialized agent capabilities and skills from remote repositories or URL-based hubs.
  • Skill Management Platforms - Provides a dedicated platform for importing, updating, and assigning specialized capabilities to agents from remote repositories.
  • State Machine Transitions - Controls task progression through a linear sequence of states to prevent unauthorized skips.
  • DAG-Based Orchestration - Utilizes directed acyclic graphs to decompose high-level commands into sub-tasks and resolve execution dependencies.
  • Execution Audit Trails - Maintains full traceability of AI execution paths by recording every state change and event in a persistent trail.
  • Agent Communication Restrictions - Restricts communication and task flow between different agent roles using a permission matrix.
  • Event-Driven Coordination - Implements an event-driven architecture using a publish-subscribe bus to coordinate task transitions between agents.
  • Agent Skill Extenders - Loads isolated tools and specialized skills dynamically at runtime via URLs or file paths.
  • Automation State Machines - Prevents illegal workflow jumps using a state machine that rejects unauthorized status changes.
  • Real-Time Monitoring Dashboards - Visualizes task progress, agent health, and token consumption through a real-time operational dashboard.
  • AI Agent Activity Monitors - Provides a real-time dashboard for tracking agent reasoning, token consumption, and task progress.
  • Agent Reasoning Reporters - Captures and displays the incremental thought processes and todo list changes of agents in real-time.
  • Agent Interaction Dashboards - Offers a web-based interface for monitoring and visualizing the progress of autonomous agent collaboration.
  • Skill Updates - Automatically checks for and applies new versions of remote agent skills on a recurring schedule.
  • Automated Skill Loading Systems - Implements automated loading of pre-defined skill sets from a centralized hub to expand agent capabilities.
  • Multi-Agent Debate Frameworks - Coordinates multiple agents to discuss topics from different professional perspectives to reach a summarized conclusion.
  • Result Consolidation - Combines outputs from multiple specialized agents into a single consolidated report and summary.
  • Bidirectional Agent Streams - Uses WebSocket subscriptions to stream real-time updates of agent reasoning and task progress to clients.
  • Manual Task Management - Offers dashboard controls to stop, cancel, resume, or advance tasks through human intervention.
  • Workflow State Tracking - Tracks the movement of tasks through a visual board to observe state transitions and agent workloads.
  • Unified Activity Streams - Aggregates status transfers, progress reports, and tool results into a single unified activity stream.
  • Data Aggregators - Collects and summarizes information from multiple third-party platforms into consolidated datasets for agent processing.
  • Asynchronous Agent Task Triggers - Triggers immediate agent execution via notifications when tasks enter an assigned state.
  • LLM Component Assignments - Assigns different large language models to each agent and applies changes without system downtime.
  • Task Auditing - Provides detailed auditing of the execution history and state transitions for automated agent workflows.
  • Running Task Terminations - Provides a management dashboard to interrupt or terminate running agent processes in real-time.
  • Reliable Event Delivery Systems - Ensures at-least-once delivery of agent communications via a transactional outbox and publish-subscribe event bus.
  • Execution Interventions - Allows users to pause tasks or inject manual commands to steer agent behavior during real-time execution.
  • Agent Communication Permissions - Enforces a strict communication hierarchy using a permission matrix to restrict agent-to-agent service requests.
  • Skill Sandboxing - Runs imported agent skills within a sandbox to restrict access to sensitive system files.
  • Centralized Configuration Systems - Provides a centralized interface to switch language models and update skill sets for individual agents.
  • Parallel Task Execution - Executes multiple agent tasks simultaneously using resource locking and automated retry logic.
  • State Transition Validation - Validates task progression using a state machine to prevent illegal transitions and unauthorized skips.
  • Task Creation Templates - Generates complex agent instructions using pre-set templates and parameter forms to standardize jobs.
  • Task Progress Monitors - Detects tasks that have stalled within a set timeframe and triggers automated retries or human escalations.
  • Audit-Ready Execution Logs - Maintains a persistent audit log of every state change and event for full traceability and execution replay.
  • Token Consumption Trackers - Records token usage and monetary costs for every progress report to enable operational accounting.
  • Feasibility Reviews - Requires an approval step by a reviewer agent to validate feasibility before executing a task.
  • WebSocket Dashboards - Pushes real-time agent reasoning and task updates to a monitoring dashboard using persistent WebSocket connections.
  • Intent Routing - Identifies whether a user request is conversational or an instruction to direct it to the appropriate processing layer.
  • AI Agent Frameworks - Multi-agent orchestration system with real-time dashboards.

Istoric stele

Graficul istoricului de stele pentru cft0808/edictGraficul istoricului de stele pentru cft0808/edict

Căutare AI

Explorează mai multe repository-uri excelente

Descrie ce ai nevoie în limbaj simplu — AI-ul sortează mii de proiecte open source selectate în funcție de relevanță.

Start searching with AI

Întrebări frecvente

Ce face cft0808/edict?

Edict is a multi-agent orchestration system and framework designed to coordinate specialized large language model agents. It functions as a workflow designer and orchestrator that decomposes complex objectives into structured plans, using directed acyclic graphs and role-based hierarchies to execute sub-tasks.

Care sunt principalele funcționalități ale cft0808/edict?

Principalele funcționalități ale cft0808/edict sunt: Automation Workflows, Event-Driven Agent Communications, Skill Lifecycle Management, Agent Task Lifecycles, Agentic Planning, Reasoning Traceability, Skill Importation, Event-Driven Agent Runtimes.

Care sunt câteva alternative open-source pentru cft0808/edict?

Alternativele open-source pentru cft0808/edict includ: kyegomez/swarms — Swarms is a multi-agent orchestration framework and autonomous agent toolkit designed to coordinate large language… microsoft/agent-framework — The agent-framework is an LLM agent orchestration framework and multi-agent workflow engine designed for building… cloudwego/eino — Eino is an AI agent development kit and LLM application framework designed for building autonomous agents and… opensquilla/opensquilla — OpenSquilla is an LLM agent orchestration framework designed to coordinate multi-step AI workflows and tool execution… memodb-io/acontext — Acontext is an LLM orchestration backend and agent memory framework designed to manage session state and knowledge for… hatchet-dev/hatchet — Hatchet is an open-source durable workflow engine and task orchestration platform. It provides a framework for…

Alternative open-source pentru Edict

Proiecte open-source similare, clasificate după numărul de funcționalități comune cu Edict.
  • kyegomez/swarmsAvatar kyegomez

    kyegomez/swarms

    6,888Vezi pe GitHub↗

    Swarms is a multi-agent orchestration framework and autonomous agent toolkit designed to coordinate large language model agents. It serves as a workflow engine for managing agent relationships, providing the infrastructure to build autonomous agents with integrated memory, tool-calling capabilities, and reasoning loops. The framework is distinguished by its multi-agent consensus systems, which utilize voting, adversarial debates, and judge agents to synthesize high-quality responses. It supports a variety of collaboration patterns, including director-worker hierarchies, expert synthesis, and

    Python
    Vezi pe GitHub↗6,888
  • microsoft/agent-frameworkAvatar microsoft

    microsoft/agent-framework

    7,277Vezi pe GitHub↗

    The agent-framework is an LLM agent orchestration framework and multi-agent workflow engine designed for building autonomous AI agents. It provides a tool integration layer for binding external functions, APIs, and sandboxed code as executable tools for language models. The framework distinguishes itself through a graph-based system for designing sequential and parallel task flows, featuring state management and checkpointing for long-running processes. It implements comprehensive conversational state management and an observability suite that uses telemetry to trace execution flows and monit

    Pythonagent-frameworkagentic-aiagents
    Vezi pe GitHub↗7,277
  • cloudwego/einoAvatar cloudwego

    cloudwego/eino

    9,675Vezi pe GitHub↗

    Eino is an AI agent development kit and LLM application framework designed for building autonomous agents and orchestrating complex language model workflows. It serves as a multi-agent orchestration engine and workflow orchestrator, providing a graph-based execution model to route data between models, tools, and retrievers. The framework distinguishes itself through a robust set of multi-agent coordination patterns, including supervisor-led management, sequential flows, and autonomous reasoning loops like ReAct. It features advanced agent execution controls such as active turn preemption, che

    Goaiai-applicationai-framework
    Vezi pe GitHub↗9,675
  • opensquilla/opensquillaAvatar opensquilla

    opensquilla/opensquilla

    4,211Vezi pe GitHub↗

    OpenSquilla is an LLM agent orchestration framework designed to coordinate multi-step AI workflows and tool execution using directed acyclic graphs. It functions as a centralized system for managing specialized skill packages and executing complex reasoning sequences. The project distinguishes itself through a routing gateway that directs tasks to different AI providers based on complexity, cost, and performance. It utilizes a multi-tier AI memory system that organizes working, episodic, and semantic knowledge using local embeddings and SQLite, alongside a secure execution sandbox that isolat

    Pythonagentaiai-agents
    Vezi pe GitHub↗4,211
  • Vezi toate cele 30 alternative pentru Edict→