Archon Autonomous Workflows — AI skill for Claude Code
Autonomous distributed AI agent platform — Gemma plans, Claude builds, self-corrects via retry loop with pgvector memory and Neo4j graph.
How to install Archon Autonomous Workflows
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Moiz-Ali-Moomin/archon-autonomous-workflows and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Archon Autonomous Workflows does
Autonomous distributed AI agent platform — Gemma plans, Claude builds, self-corrects via retry loop with pgvector memory and Neo4j graph.
Alternatives in AI
- WeKnora — Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, an 26.9k ★
- Sentrux — Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improveme 2.9k ★
- Ralphex — Extended Ralph loop for autonomous AI-driven plan execution 1.1k ★
README
Gemma Agent Platform Architecture
A distributed autonomous coding agent. Send it a goal over HTTP, it writes Python code to solve it, executes it, and self-corrects on failure — all asynchronously.
Architecture
HTTP Client
│
▼
┌─────────┐ enqueue ┌──────────────┐
│ FastAPI │ ─────────────▶│ Redis │
│ :8000 │ │ (broker + │
└─────────┘ │ task state)│
│ └──────┬───────┘
│ GET /status │ dequeue
▼ ▼
┌─────────┐ ┌──────────────────┐
│ Redis │◀─ status ────│ Celery Worker │
└─────────┘ │ │
│ workflow.py │
│ ┌────────────┐ │
│ │ builder() │ │──▶ Ollama (gemma:2b)
│ │ fixer() │ │──▶ Ollama (gemma:2b)
│ │ run_code() │ │
│ └────────────┘ │
└──────┬───────────┘
│
┌───────────┴───────────┐
▼ ▼
┌────────────┐ ┌────────────┐
│ PostgreSQL │ │ Neo4j │
│ (pgvector) │ │ (GraphRAG) │
│ long-term │ │ Goal→File │
│ memory │ │ Error→Fix │
└────────────┘ └────────────┘
Services
| Service | Port | Purpose |
|---|---|---|
| API | 8000 | REST interface |
| Worker | — | Celery task executor |
| Flower | 5555 | Celery task monitoring dashboard |
| Redis | 6379 | Message broker + short-term state |
| PostgreSQL | 5432 | Long-term memory (pgvector) |
| Neo4j | 7687 | Graph memory (Goal/File/Error nodes) |
| Neo |
Related Skills
Looper Rust
An autonomous AI development loop for Claude Code, Codex that plans, executes, and iterates on your tasks auto
Vox Agent
LLM agent for customer support with inline evaluation, hallucination detection, retry/fallback logic, and RAG
Knowledge Graph Based Hybrid RAG System
Knowledge Graph-RAG system using Neo4j, LangChain, LangGraph, Claude-3.5-Sonnet. Hybrid retrieval: SBERT embed
Capy Cortex
Autonomous memory and learning system for AI coding agents. LLM-powered knowledge extraction, triple fusion re
Ouro Loop
Give AI coding agents (Claude Code, Cursor, Aider, Codex) a structured autonomous loop with guardrails — bound
Mem0 MCP Selfhosted
Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j +
Related Agents
Game QA
Game QA. Runs the autonomous self-verify loop (build → launch .exe → screenshot → read PNG → verdict). Catches
Swe Dev Loop Systems Architect
Designs and audits coding-agent loops, debugging and migration workflows, CI/release loops, autonomous-science
Knuth
SPECIALIST — Data Architect. PostgreSQL, RuVector graph adapter (AD-49 default), Neo4j fallback, query optimiz