# jd-opensource/OxyGent

[ACL 2026] OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction https://arxiv.org/abs/2604.25602

Repository: https://github.com/jd-opensource/OxyGent
Canonical: https://ross.abutalabs.com/products/oxygent
Homepage: https://oxygent.jd.com
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-07-21T08:34:07+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 35, longevity 29
- inputs: {"age_days": 411, "days_push": 43, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2067, forks 274 (observed 2026-08-28T04:06:10.160946+00:00)

## What it is
OxyGent is an open-source Python framework that unifies tools, models, and agents into modular 'Oxy' components for building multi-agent systems. It emphasizes modularity, observability, and evolvability, supporting agent topologies from simple ReAct to complex hybrid architectures.

## Use cases
- build a multi-agent AI system in python
- orchestrate llm agents with tools and models
- create production-ready agent pipelines
- decompose tasks across collaborating ai agents
- hot-swap and reuse agent components across scenarios
- build a ReAct agent with full decision auditability

## When to choose
- you need a modular, extensible multi-agent framework in Python
- you want transparent, auditable agent decision pipelines
- you need flexible agent topologies beyond rigid workflows
- you want rapid assembly of agents from standardized components

## When to avoid
- you need a single-agent chatbot with minimal overhead
- you require a framework in a language other than Python or Java
- you need a fully managed cloud agent service rather than a self-hosted framework

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, workflow-automation, sdk
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform
- tags: multi-agent-systems, oxy-abstraction, modular-agents, production-ready, acl-2026, ai-agents

## Member repositories
- jd-opensource/OxyGent (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:10.160946+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 2026-08-30T02:56:49.110164+00:00, confidence not recorded.
  - readme: https://github.com/jd-opensource/OxyGent (fetched 2026-08-28T04:06:10.160946+00:00, sha 5739287cee8c)
  - homepage: https://oxygent.jd.com (fetched 2026-08-29T10:37:06.665147+00:00, sha d89cc48541b9)
- Data as of 2026-08-30T08:39:29.467469+00:00.