# wang2122/sprix-sage-router

Sprix AI at 屿智同行 — state-aware SELF/COLLABORATE/HANDOFF routing for A2A agent networks.

Repository: https://github.com/wang2122/sprix-sage-router
Canonical: https://ross.abutalabs.com/products/sprix-sage-router
Language: Python
License: MIT
License Family: permissive
Topics: a2a, agent-orchestration, agent-routing, ai-agents, multi-agent-systems, python, task-scheduling, sprix-ai
Last push: 2026-08-26T07:43:30+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 60, longevity 1
- inputs: {"age_days": 15, "days_push": 7, "days_rel": 15, "gap_med": null, "n_releases_24m": 1}
- flags: prerelease_only, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2221, forks 111 (observed 2026-08-28T04:06:27.555196+00:00)

## What it is
Sprix SAGE Router is a Python decision layer for Agent2Agent (A2A) networks that routes tasks across three modes—SELF, COLLABORATE, and HANDOFF—using a single auditable utility function. It assigns task-DAG roles, schedules dependencies, and learns from execution evidence under permission, budget, and deadline constraints.

## Use cases
- decide whether an agent should continue a task alone, recruit collaborators, or hand it off
- route tasks between agents in an A2A multi-agent network
- schedule task DAG dependencies across a team of agents
- replan mid-execution when an agent fails or progress stalls
- score candidate agent teams by complementary requirement coverage
- learn contextual trust per agent and requirement from execution evidence

## When to choose
- you run an A2A-based multi-agent system and need a routing/decision layer above discovery
- you want SELF/COLLABORATE/HANDOFF decisions in one auditable objective
- you need dependency-aware task scheduling and role assignment for agent teams

## When to avoid
- you need a full agent runtime or A2A transport implementation—SAGE only decides routing
- you want a production-hardened orchestrator; it is labeled a research preview
- your stack is not Python 3.10+

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, scheduling, workflow-automation, routing
- domain: large-language-models, microservices
- platform: python, cross-platform
- tags: a2a-protocol, multi-agent-systems, agent-routing, task-dag, tri-mode-routing, agent-orchestration, ai-agents, automation

## Member repositories
- wang2122/sprix-sage-router (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:27.555196+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:45:48.884245+00:00, confidence not recorded.
  - readme: https://github.com/wang2122/sprix-sage-router (fetched 2026-08-28T04:06:27.555196+00:00, sha ec76a6f8d1f5)
- Data as of 2026-08-30T08:39:29.467469+00:00.