# aiwaves-cn/agents

An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents

Repository: https://github.com/aiwaves-cn/agents
Canonical: https://ross.abutalabs.com/products/aiwaves-cn-agents
Language: Python
License: Apache-2.0
License Family: permissive
Topics: autonomous-agents, language-model, llm
Last push: 2024-09-26T03:12:53+00:00

## Health v2 (maintenance only)
Score: 28/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 81
- inputs: {"age_days": 1143, "days_push": 706, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5957, forks 480 (observed 2026-08-28T04:09:33.704535+00:00)

## What it is
Agents 2.0 is a Python framework for data-centric, self-evolving autonomous language agents based on symbolic learning. It adapts neural-network-style training—forward passes, language-based loss, backpropagation, and weight updates—to optimize prompts, tools, and agent pipelines, including multi-agent systems.

## Use cases
- train and optimize llm agents with symbolic learning
- build self-evolving autonomous language agents
- optimize prompts and tools via language gradients
- train multi-agent systems
- evaluate agent pipelines with language-based loss

## When to choose
- you want agents that improve themselves from training data
- you need prompt optimization inspired by backpropagation
- you are researching agent training and evaluation methods

## When to avoid
- you need a simple production agent runtime without training
- you want a framework with active ongoing development
- you need non-Python or lightweight agent orchestration

## Facets
- artifact type: framework
- maturity: maintenance
- function: agent-framework, llm-training, prompt-engineering, machine-learning
- domain: artificial-intelligence, large-language-models, machine-learning
- platform: python, cross-platform
- tags: symbolic-learning, self-evolving-agents, language-agents, backpropagation, multi-agent-systems, research, ai-agents

## Member repositories
- aiwaves-cn/agents (main) score 28

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:33.704535+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 2026-08-29T17:50:41.886226+00:00, confidence not recorded.
  - readme: https://github.com/aiwaves-cn/agents (fetched 2026-08-28T04:09:33.704535+00:00, sha c96bf29e8c05)
- Data as of 2026-08-30T08:39:29.467469+00:00.