# Zoo-Code-Org/Zoo-Code

Zoo Code gives you a whole dev team of AI agents in your code editor.

Repository: https://github.com/Zoo-Code-Org/Zoo-Code
Canonical: https://ross.abutalabs.com/products/zoo-code
Homepage: https://www.zoocode.dev
Language: TypeScript
License: Apache-2.0
License Family: permissive
Last push: 2026-08-26T02:53:50+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 9
- inputs: {"age_days": 132, "days_push": 7, "days_rel": 11, "gap_med": 6, "n_releases_24m": 18}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1731, forks 249 (observed 2026-08-28T04:05:28.532611+00:00)

## What it is
Zoo Code is an open-source AI coding assistant delivered as a VS Code extension (with JetBrains/Open VSX support), continuing development of Roo Code. It provides a team of specialized AI agent modes (Architect, Code, Debug) with file system access, terminal control, multi-file editing, MCP tool integration, and support for any LLM provider.

## Use cases
- generate code from natural language descriptions
- refactor and debug existing code
- plan refactors before editing with architect mode
- answer questions about my codebase
- automate repetitive coding tasks
- connect AI agent to databases and APIs via MCP
- run long autonomous coding sessions safely
- use any LLM provider without vendor lock-in

## When to choose
- you want a community-maintained continuation of Roo Code in VS Code
- you need model-agnostic AI coding with BYOK across many providers
- you want specialized agent modes and orchestrator workflows for complex multi-step tasks
- you need MCP integration to connect external tools to your coding agent

## When to avoid
- you want a lightweight, cheap AI autocomplete rather than token-heavy agentic workflows
- you prefer a fully hosted solution with no local file system or terminal access
- you need an editor other than VS Code, JetBrains, or Open VSX-compatible IDEs

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, llm-inference, mcp, developer-tools, code-review
- domain: developer-tools, artificial-intelligence, large-language-models, text-editors
- platform: editor-plugin, cross-platform
- tags: ai-coding-assistant, vscode-extension, roo-code-fork, multi-agent, byok, model-agnostic, orchestrator, semantic-code-search, ai-agents, nodejs

## Member repositories
- Zoo-Code-Org/Zoo-Code (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:28.532611+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 2026-08-30T03:31:41.869878+00:00, confidence not recorded.
  - readme: https://github.com/Zoo-Code-Org/Zoo-Code (fetched 2026-08-28T04:05:28.532611+00:00, sha 921ee499e8d4)
  - homepage: https://www.zoocode.dev (fetched 2026-08-29T11:08:43.044776+00:00, sha c6e2b8e1e12a)
  - site_page: https://docs.zoocode.dev (fetched 2026-08-29T11:08:43.053956+00:00, sha f0d7e8683906)
- Data as of 2026-08-30T08:39:29.467469+00:00.