# BillHuang2001/evogit

Repository: https://github.com/BillHuang2001/evogit
Canonical: https://ross.abutalabs.com/products/evogit
Language: Python
License: AGPL-3.0
License Family: copyleft
Last push: 2026-08-10T10:05:37+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 35, longevity 59
- inputs: {"age_days": 834, "days_push": 23, "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 1357, forks 183 (observed 2026-08-28T04:04:29.545904+00:00)

## What it is
EvoGit is a decentralized multi-agent framework that treats software development as an evolutionary process, deploying a population of independent coding agents that evolve a shared codebase asynchronously. Coordination emerges implicitly through a Git-based phylogenetic graph tracking the complete version lineage, with no central coordinator, message passing, or shared memory.

## Use cases
- coordinate multiple coding agents without a central orchestrator
- evolve a codebase automatically using a population of AI agents
- run decentralized multi-agent software development experiments
- use git history as the coordination mechanism for agent collaboration
- research asynchronous multi-agent collaboration on shared code
- scale autonomous code generation across many independent agents

## When to choose
- you want decentralized multi-agent coding without explicit message passing or shared memory
- you want agents to coordinate implicitly through git version lineage
- you are researching evolutionary or population-based approaches to code generation
- you want an award-winning, paper-backed framework for multi-agent software evolution

## When to avoid
- you need a single-agent coding assistant for everyday autocomplete or refactoring
- you require fine-grained, deterministic control over agent communication
- your project needs centralized orchestration with strict task assignment
- you need a production-ready commercial tool rather than a research framework

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, version-control, llm-inference, developer-tools
- domain: large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: multi-agent, git-based, decentralized, code-evolution, asynchronous-collaboration, ai-agents, automation

## Member repositories
- BillHuang2001/evogit (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:29.545904+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 2026-08-30T04:41:47.925481+00:00, confidence not recorded.
  - readme: https://github.com/BillHuang2001/evogit (fetched 2026-08-28T04:04:29.545904+00:00, sha f6de5d7b0247)
- Data as of 2026-08-30T08:39:29.467469+00:00.