Agentica Infrastructure

by parcadeid07ff4b06b62No license3.9K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 8 months ago

Reference guide for Agentica multi-agent infrastructure APIs

Instructions onlyAI & Agents

AI-generated overview

Reference guide documenting Agentica multi-agent infrastructure APIs, pattern classes, primitives and coordination components.

What it does: Provides a reference specification for Agentica multi-agent coordination infrastructure, listing eleven pattern classes such as Swarm, Pipeline and Jury with their key methods. It also documents core infrastructure components like CoordinationDB, tracked_spawn and HandoffAtom, plus primitives such as Consensus and Aggregator. The full API specification is contained in the bundled API_SPEC.md file, and the skill includes a Python usage example.
When to use it: Use when building multi-agent workflows with Agentica patterns or when exact constructor signatures for pattern classes are needed. It is also intended for understanding the coordination database schema, implementing custom patterns from primitives, or debugging agent tracking and orphan detection.
Requirements: Instructions only; no scripts are run. It references API_SPEC.md in the skill directory and source files under scripts/agentica_patterns/, and the usage example imports Python modules from that path.

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`	`blackboard.py`	Hot tier communication
`MemoryService`	`memory_service.py`	Core + Archival memory
`create_claude_scope`	`claude_scope.py`	Scope with file ops

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

python

from scripts.agentica_patterns.patterns import Swarm, Juryfrom scripts.agentica_patterns.primitives import ConsensusModefrom scripts.agentica_patterns.coordination import CoordinationDBfrom scripts.agentica_patterns.tracked_agent import tracked_spawn
# Create tracking databasedb = CoordinationDB(session_id="my-session")
# Swarm with trackingswarm = Swarm(    perspectives=["Security expert", "Performance expert"],    db=db)result = await swarm.execute("Review this code")
# Jury with consensusjury = 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?")

from scripts.agentica_patterns.patterns import Swarm, Juryfrom scripts.agentica_patterns.primitives import ConsensusModefrom scripts.agentica_patterns.coordination import CoordinationDBfrom scripts.agentica_patterns.tracked_agent import tracked_spawn
# Create tracking databasedb = CoordinationDB(session_id="my-session")
# Swarm with trackingswarm = Swarm(    perspectives=["Security expert", "Performance expert"],    db=db)result = await swarm.execute("Review this code")
# Jury with consensusjury = 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/

Source and attribution

Source:parcadei/continuous-claude-v3in.claude/skills/agentica-infrastructureat commitd07ff4b

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

Agentica Infrastructure

Agentica Infrastructure Reference

When to Use

Quick Reference

11 Pattern Classes

Core Infrastructure

Primitives

Full API Spec

Usage Example

Location

Source and attribution

More from parcadei/continuous-claude-v3

Tldr Stats

Wiring

Workflow Router

Validate Agent

Tour

Tldr Overview

More in AI & Agents

Ppt Template Creator

Skill Development

Plugin Structure

Command Development

Claude Md Improver

Find Skills