axeon-atrest 0.2.0

Agent Task Runtime & State Transport — middleware for AI agent communication, memory, and task lifecycle

AT Rest — Agent Task Runtime & State Transport

Middleware untuk agent communication, memory, dan task lifecycle.

4 agent built-in (planner, researcher, reviewer, mentor) via Redis Streams bus. Neo4j task persistence. FastAPI REST API server. Qdrant + Neo4j knowledge retrieval.

Quick Start

pip install atrest

from atrest import Agent, generate, search

class MyAgent(Agent):
    channel = "researcher"

    def handle_request(self, msg):
        goal = msg["payload"]["goal"]
        results = search(goal, limit=3)
        summary = generate(f"Summarize: {goal}\n\nContext: {results}")
        return {"summary": summary, "sources": []}

MyAgent().run()

Available Imports

from atrest import Agent, ATRestClient, AgentBus, TaskStore, generate, embed, search

• Agent — base class for custom agents
• ATRestClient — HTTP client for AT Rest API
• AgentBus — Redis Streams pub/sub
• TaskStore — Neo4j AgentTask persistence
• generate() — Ollama LLM call
• embed() — Ollama embedding
• search() — Qdrant vector search

Optional: API Server

pip install atrest[api]
python -m api.server

Architecture

User → REST API / Agent SDK → Agent Bus (Redis Streams)
  → Planner → Researcher / Reviewer / Mentor
  → Task Store (Neo4j) → Broadcast
  → Knowledge (Qdrant + Neo4j)

License

MIT