Skip to content

ardaglobal/hca

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

59 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Holonic Compound Architecture (HCA)

A protocol standard for autonomous, composable, and continuously-improving agentic systems.

Version Status


What is HCA?

HCA combines two powerful ideas:

  1. Holonic Architecture: Agents that are both autonomous wholes AND cooperative parts of a larger system
  2. Compound Engineering: Mandatory iteration loops where each task improves future tasks

The result: agent systems that are governable without being rigid, autonomous without being chaotic, and get better over time.


Quick Start

I want to... Start here
Understand HCA in 3 minutes QUICK-REFERENCE
Read the full specification SPEC
See the architecture visually ARCHITECTURE-DIAGRAM
Implement HCA HCA-EXTENSIONSSTATE-MACHINES
Certify compliance CONFORMANCE-CRITERIA

The Problem

Current agent architectures have fundamental limitations:

Approach What Happens
Hub-and-spoke Central orchestrator becomes a bottleneck. Agents have fake autonomy.
Pure swarm Emergent chaos. Unreproducible results. Ungovernable.
One-shot agents No iteration. No learning. Same mistakes repeated forever.

HCA solves this by combining structured hierarchy (holons) with mandatory improvement loops (compound engineering).


Core Concepts

Holons: Whole AND Part

A holon is an agent that is:

  • Autonomous: Makes its own decisions within constraints
  • Embedded: Operates as part of a larger goal structure
Root Holon (Mission Control)
    │
    ├── Domain Holon (Engineering)
    │       ├── Leaf Holon (Dev Agent)
    │       └── Leaf Holon (Refactor Agent)
    │
    ├── Domain Holon (QA)
    │       ├── Leaf Holon (Test Agent)
    │       └── Leaf Holon (Verifier Agent)
    │
    └── Domain Holon (Data)
            └── Leaf Holon (Research Agent)

Authority flows down (constraints, goals, budgets). Results flow up (artifacts, verdicts, status).

The Compound Loop

Every task follows this pattern:

┌────────┐     ┌────────┐     ┌────────┐     ┌─────────────┐
│  PLAN  │ ──► │  WORK  │ ──► │ REVIEW │ ──► │REVISE/ACCEPT│
└────────┘     └────────┘     └────────┘     └─────────────┘
     ▲                                              │
     └──────────────── (on failure) ◄───────────────┘

Plus an outer loop that extracts lessons:

COMPOUND: What worked? What failed? → Knowledge Base → Future PLANs

This is the compound principle: each task makes the next task easier.

Protocol Boundaries

HCA uses standard protocols at each boundary:

Boundary What It's For Protocol
Northbound Human/IDE ↔ System ACP
Coordination Holon ↔ Holon A2A
Tools Holon → External tools MCP
Runtime Holon → Sandbox OpenHands/Docker

Key Principles

1. Constraint-Based Authority

Parents don't command; they constrain.

Parent provides:           Child decides:
├── Goals                  ├── How to achieve goals
├── Acceptance criteria    ├── When to delegate
├── Budgets (time/tokens)  ├── Implementation approach
└── Policies               └── Whether to accept/negotiate

2. Negotiation is Normal

Agents can:

  • Accept tasks as specified
  • Reject tasks (with reason)
  • Counter with modified constraints

This isn't insubordination—it's the protocol.

3. Separate Producer and Reviewer

The agent that writes code cannot be the agent that reviews it.

This prevents self-approval and forces genuine evaluation.

4. Learning Compounds

Every completed task (success or failure) produces lessons that go into a shared knowledge base. Future PLAN phases query this knowledge.


Documentation

Folder Structure

hca/
├── README.md                 ← You are here
├── DOCUMENT-INDEX.md         ← Navigation & reading paths
│
├── spec/                     ← Normative specification (THE RULES)
│   ├── SPEC.md               Core specification
│   ├── GLOSSARY.md           Term definitions
│   ├── HCA-EXTENSIONS.md     JSON-RPC schemas
│   └── STATE-MACHINES.md     Formal state diagrams
│
├── reference/                ← Reference materials (Informative)
│   ├── QUICK-REFERENCE.md    1-page cheat sheet
│   ├── ARCHITECTURE-DIAGRAM.md  Visual architecture
│   ├── BUILDING-BLOCKS.md    Protocol rationale
│   └── CONFORMANCE-CRITERIA.md  Certification requirements
│
├── guidance/                 ← Implementation guidance
│   └── SECURITY-CONSIDERATIONS.md  Security patterns
│
└── working/                  ← Working documents (not part of spec)
    ├── ANALYSIS-SUMMARY.md   Validation executive summary
    ├── PROTOCOL-GAP-ANALYSIS.md  Detailed gap analysis
    └── CRITICAL-FIXES-REQUIRED.md  Action items

By Classification

Type Folder Description
Normative spec/ The rules (MUST implement)
Reference reference/ Explains & guides
Guidance guidance/ Implementation patterns
Working working/ Project management (not part of spec)

See DOCUMENT-INDEX.md for complete navigation and reading paths.


Conformance Levels

Adopt HCA incrementally:

Level What You Need Use Case
1 - Minimal Holons + delegation + artifacts + review Proof of concept
2 - Standard + Full compound loop + iteration + negotiation Production pilot
3 - Full + Knowledge base + cross-task learning Production system

See CONFORMANCE-CRITERIA for detailed certification requirements.


Building Blocks

HCA builds on proven foundations:

Component Purpose Source
LSP Pattern JSON-RPC + capabilities Microsoft
A2A Agent-to-agent coordination Google/Linux Foundation
MCP Tool invocation Anthropic
ACP Client interface Community
OpenHands Runtime substrate OpenHands
ADK Agent framework Google

HCA references these; it doesn't require specific implementations.

See BUILDING-BLOCKS for detailed rationale.


Why "Compound"?

The term comes from Compound Engineering by Dan Shipper (Every, 2025):

"Compound engineering creates a learning loop for your agents and team, so that each bug, failed test, or problem-solving insight gets documented and used by future agents."

Without compound loops, agent systems don't improve. Each task is isolated. The same mistakes repeat.

With compound loops, each task makes the next task easier.


Status

Version: 0.1.0 (Draft)

This is an initial specification. Future versions will add:

  • v0.2: Security model, extension mechanisms
  • v0.3: Conformance test suite
  • v1.0: Stable specification

Contributing

This specification is open for feedback. Please open issues for:

  • Clarifications needed
  • Inconsistencies found
  • Use cases not covered
  • Implementation experience

References

  • A2A Protocol - Agent-to-Agent communication
  • MCP - Model Context Protocol
  • ACP - Agent Client Protocol
  • OpenHands - Agent runtime
  • ADK - Agent Development Kit
  • Compound Engineering - Every/Dan Shipper
  • Arthur Koestler, The Ghost in the Machine (1967) - Holon concept origin

HCA: Autonomous agents that learn. Governed systems that flex. Architecture that compounds.


This document is part of the Holonic Compound Architecture (HCA) Specification v0.1

About

Holonic Compound Architecture (HCA)

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published