agentica-infrastructure
starsforks
How to install agentica-infrastructure?
vibeeval/vibecosystem/agentica-infrastructure
$npx -y skills add vibeeval/vibecosystem --skill agentica-infrastructure--- name: agentica-infrastructure description: Reference guide for Agentica multi-agent infrastructure APIs allowed-tools: [Read] user-invocable: false ---
SKILL.md
| 1 | # Agentica Infrastructure Reference |
| 2 | |
| 3 | Complete API specification for Agentica multi-agent coordination infrastructure. |
| 4 | |
| 5 | ## When to Use |
| 6 | |
| 7 | - Building multi-agent workflows with Agentica patterns |
| 8 | - Need exact constructor signatures for pattern classes |
| 9 | - Want to understand coordination database schema |
| 10 | - Implementing custom patterns using primitives |
| 11 | - Debugging agent tracking or orphan detection |
| 12 | |
| 13 | ## Quick Reference |
| 14 | |
| 15 | ### 11 Pattern Classes |
| 16 | |
| 17 | | Pattern | Purpose | Key Method | |
| 18 | |---------|---------|------------| |
| 19 | | `Swarm` | Parallel perspectives | `.execute(query)` | |
| 20 | | `Pipeline` | Sequential stages | `.run(initial_state)` | |
| 21 | | `Hierarchical` | Coordinator + specialists | `.execute(task)` | |
| 22 | | `Jury` | Voting consensus | `.decide(return_type, question)` | |
| 23 | | `GeneratorCritic` | Iterative refinement | `.run(task)` | |
| 24 | | `CircuitBreaker` | Failure fallback | `.execute(query)` | |
| 25 | | `Adversarial` | Debate + judge | `.resolve(question)` | |
| 26 | | `ChainOfResponsibility` | Route to handler | `.process(query)` | |
| 27 | | `MapReduce` | Fan out + reduce | `.execute(query, chunks)` | |
| 28 | | `Blackboard` | Shared state | `.solve(query)` | |
| 29 | | `EventDriven` | Event bus | `.publish(event)` | |
| 30 | |
| 31 | ### Core Infrastructure |
| 32 | |
| 33 | | Component | File | Purpose | |
| 34 | |-----------|------|---------| |
| 35 | | `CoordinationDB` | `coordination.py` | SQLite tracking | |
| 36 | | `tracked_spawn` | `tracked_agent.py` | Agent with tracking | |
| 37 | | `HandoffAtom` | `handoff_atom.py` | Universal handoff format | |
| 38 | | `BlackboardCache` | `blackboard.py` | Hot tier communication | |
| 39 | | `MemoryService` | `memory_service.py` | Core + Archival memory | |
| 40 | | `create_claude_scope` | `claude_scope.py` | Scope with file ops | |
| 41 | |
| 42 | ### Primitives |
| 43 | |
| 44 | | Primitive | Purpose | |
| 45 | |-----------|---------| |
| 46 | | `Consensus` | Voting (MAJORITY, UNANIMOUS, THRESHOLD) | |
| 47 | | `Aggregator` | Combine results (MERGE, CONCAT, BEST) | |
| 48 | | `HandoffState` | Structured agent handoff | |
| 49 | | `build_premise` | Structured premise builder | |
| 50 | | `gather_fail_fast` | TaskGroup-based parallel execution | |
| 51 | |
| 52 | ## Full API Spec |
| 53 | |
| 54 | See: `API_SPEC.md` in this skill directory |
| 55 | |
| 56 | ## Usage Example |
| 57 | |
| 58 | ```python |
| 59 | from scripts.agentica_patterns.patterns import Swarm, Jury |
| 60 | from scripts.agentica_patterns.primitives import ConsensusMode |
| 61 | from scripts.agentica_patterns.coordination import CoordinationDB |
| 62 | from scripts.agentica_patterns.tracked_agent import tracked_spawn |
| 63 | |
| 64 | # Create tracking database |
| 65 | db = CoordinationDB(session_id="my-session") |
| 66 | |
| 67 | # Swarm with tracking |
| 68 | swarm = Swarm( |
| 69 | perspectives=["Security expert", "Performance expert"], |
| 70 | db=db |
| 71 | ) |
| 72 | result = await swarm.execute("Review this code") |
| 73 | |
| 74 | # Jury with consensus |
| 75 | jury = Jury( |
| 76 | num_jurors=3, |
| 77 | consensus_mode=ConsensusMode.MAJORITY, |
| 78 | premise="You evaluate code quality", |
| 79 | db=db |
| 80 | ) |
| 81 | verdict = await jury.decide(bool, "Is this code production ready?") |
| 82 | ``` |
| 83 | |
| 84 | ## Location |
| 85 | |
| 86 | API spec: `.claude/skills/agentica-infrastructure/API_SPEC.md` |
| 87 | Source: `scripts/agentica_patterns/` |
People who liked this also viewed
6 picksType
- microsoft-foundryDeploy, evaluate, fine-tune, and manage Foundry agents end-to-end with azd: hosted agent scaffold/run/deploy, prompt agent create, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffoSkillsJul 2026
- azure-deployExecute Azure deployments for ALREADY-PREPARED applications that have existing .azure/deployment-plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application SkillsJul 2026
- azure-preparePrepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wSkillsJul 2026
- azure-validate--- name: azure-validate description: "Pre-deployment validation for Azure readiness. Run deep checks on configuration, infrastructure (Bicep or Terraform), RBAC role assignments, managed identity pSkillsJul 2026
- azure-aigatewayConfigure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbSkillsJul 2026
- azure-hosted-copilot-sdkOfficial agent plugin providing skills and MCP server configurations for Azure scenarios.SkillsJul 2026
