Agentica 多智能体协调基础设施 API 规范 - 11种模式类与核心组件详解

agentica-infrastructure by parcadei/continuous-claude-v3

196 周安装量

3,600 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/parcadei/continuous-claude-v3 --skill agentica-infrastructure

AI/机器学习自动化系统架构

🇨🇳中文介绍

Agentica 基础设施参考

Agentica 多智能体协调基础设施的完整 API 规范。

使用时机

使用 Agentica 模式构建多智能体工作流时
需要模式类的确切构造函数签名时
想要理解协调数据库模式时
使用原语实现自定义模式时
调试智能体跟踪或孤儿检测时

快速参考

11 种模式类

模式	用途	关键方法
`Swarm`	并行视角	`.execute(query)`
`Pipeline`	顺序阶段	`.run(initial_state)`

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

相关 Skills

FlyClaw：零登录航班聚合查询工具，Python实现多源航班信息与价格搜索

4,000,000 周安装

find-skills 技能搜索工具 - Vercel Labs 开源智能体技能包管理器

827,200 周安装

Azure RBAC 权限管理工具：查找最小角色、创建自定义角色与自动化分配

117,000 周安装

React 组合模式指南：Vercel 组件架构最佳实践，提升代码可维护性

111,800 周安装

组件	文件	用途
`CoordinationDB`	`coordination.py`	SQLite 跟踪
`tracked_spawn`	`tracked_agent.py`	带跟踪的智能体
`HandoffAtom`	`handoff_atom.py`	通用交接格式
`BlackboardCache`	`blackboard.py`	热层通信
`MemoryService`	`memory_service.py`	核心 + 归档记忆
`create_claude_scope`	`claude_scope.py`	带文件操作的 Scope

原语	用途
`Consensus`	投票 (MAJORITY, UNANIMOUS, THRESHOLD)
`Aggregator`	合并结果 (MERGE, CONCAT, BEST)
`HandoffState`	结构化的智能体交接
`build_premise`	结构化的前提构建器
`gather_fail_fast`	基于 TaskGroup 的并行执行

from scripts.agentica_patterns.patterns import Swarm, Jury
from scripts.agentica_patterns.primitives import ConsensusMode
from scripts.agentica_patterns.coordination import CoordinationDB
from scripts.agentica_patterns.tracked_agent import tracked_spawn

# 创建跟踪数据库
db = CoordinationDB(session_id="my-session")

# 带跟踪的 Swarm
swarm = Swarm(
    perspectives=["Security expert", "Performance expert"],
    db=db
)
result = await swarm.execute("Review this code")

# 带共识的 Jury
jury = Jury(
    num_jurors=3,
    consensus_mode=ConsensusMode.MAJORITY,
    premise="You evaluate code quality",
    db=db
)
verdict = await jury.decide(bool, "Is this code production ready?")

🇺🇸English

Agentica Infrastructure Reference

Complete API specification for Agentica multi-agent coordination infrastructure.

When to Use

Building multi-agent workflows with Agentica patterns
Need exact constructor signatures for pattern classes
Want to understand coordination database schema
Implementing custom patterns using primitives
Debugging agent tracking or orphan detection

Quick Reference

11 Pattern Classes

Pattern	Purpose	Key Method
`Swarm`	Parallel perspectives	`.execute(query)`
`Pipeline`	Sequential stages	`.run(initial_state)`
`Hierarchical`	Coordinator + specialists	`.execute(task)`
`Jury`	Voting consensus	`.decide(return_type, question)`
`GeneratorCritic`	Iterative refinement	`.run(task)`
`CircuitBreaker`	Failure fallback	`.execute(query)`
`Adversarial`	Debate + judge	`.resolve(question)`
`ChainOfResponsibility`	Route to handler	`.process(query)`
`MapReduce`	Fan out + reduce	`.execute(query, chunks)`
`Blackboard`	Shared state	`.solve(query)`
`EventDriven`	Event bus	`.publish(event)`

Core Infrastructure

Component	File	Purpose
`CoordinationDB`	`coordination.py`	SQLite tracking
`tracked_spawn`	`tracked_agent.py`	Agent with tracking
`HandoffAtom`	`handoff_atom.py`	Universal handoff format
`BlackboardCache`

Primitives

Primitive	Purpose
`Consensus`	Voting (MAJORITY, UNANIMOUS, THRESHOLD)
`Aggregator`	Combine results (MERGE, CONCAT, BEST)
`HandoffState`	Structured agent handoff
`build_premise`	Structured premise builder
`gather_fail_fast`	TaskGroup-based parallel execution

Full API Spec

See: API_SPEC.md in this skill directory

Usage Example

from scripts.agentica_patterns.patterns import Swarm, Jury
from scripts.agentica_patterns.primitives import ConsensusMode
from scripts.agentica_patterns.coordination import CoordinationDB
from scripts.agentica_patterns.tracked_agent import tracked_spawn

# Create tracking database
db = CoordinationDB(session_id="my-session")

# Swarm with tracking
swarm = Swarm(
    perspectives=["Security expert", "Performance expert"],
    db=db
)
result = await swarm.execute("Review this code")

# Jury with consensus
jury = Jury(
    num_jurors=3,
    consensus_mode=ConsensusMode.MAJORITY,
    premise="You evaluate code quality",
    db=db
)
verdict = await jury.decide(bool, "Is this code production ready?")

Location

API spec: .claude/skills/agentica-infrastructure/API_SPEC.md Source: scripts/agentica_patterns/

Weekly Installs

196

Repository

parcadei/contin…laude-v3

GitHub Stars

3.6K

First Seen

Jan 22, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykPass

Installed on

opencode190

codex190

gemini-cli187

cursor187

github-copilot184

amp180