Build New Features from Approved Issues
Have the architect and coding agents collaborate to generate and implement feature code directly from a GitHub issue
Best for：VS Code users
Coding / Developer
Zoo Code
Zoo Code is an open-source code editor extension that can run multiple AI agents inside the editor as a development team.
Product type: Model Gateway / Routing ToolPricing: UnknownAPIMaster integration: Unknown
OpenRouter token usage rank
#27
Source: OpenRouter
Overview
Zoo Code is positioned as an AI agent system integrated into code editors, primarily running through environments such as VS Code. Users launch agents with different roles under local or remote models to complete code-related workflows. Its core is providing a way for multiple agents to work collaboratively, rather than acting as a single AI assistant. It is suitable for developers already using local models or multi-agent workflows. Compared with traditional single-agent tools, the difference lies in its built-in team structure and open-source implementation.
One-line summary
Zoo Code is an open-source code editor extension that can run multiple AI agents inside the editor as a development team.
What people use it for
After installing it in VS Code, users launch agents such as orchestrator, architect, and debugger to handle project tasks.
Best for
Developers, engineering teams, and technical leads
How it works
It usually starts by reading context in the IDE, terminal, or project environment, then the Agent plans steps, executes commands, or modifies files, and the user reviews the results.
Quick facts
Product type
Model Gateway / Routing Tool
Pricing
Unknown
The current enhanced batch dataset does not maintain real-time pricing for this product. Please refer to the official website or official documentation.
APIMaster integration
Unknown
Pending Verification
Data confidence
Medium
Last verified: 2026-08-30
Supported models / APIs
Third-Party Provider
Core features and differentiators
Multi-AI Agent Team
Run multiple specialized AI agents such as orchestrator, architect, debugger, and coding simultaneously inside the VS Code editor
Codebase Knowledge Graph
Automatically builds and displays call graphs and dependency graphs for the codebase
Semantic Code Search
Supports semantic codebase search instead of only keyword matching
Safe Simulated Editing
Executes code changes in a simulated environment first, then applies them for real after confirmation
Persistent Codebase Memory
Retains codebase context and change history across sessions
External Tool Integration
Built-in tools for web search, web browser, GitHub operations, and compliance checks
What is Zoo Code best for?
Analyze CI Failure Logs
Use the debugger agent to read CI logs, identify the cause of failure, and propose fixes
Best for：VS Code users
Review Open PRs
Have the agent team go through open PRs, inspect code changes, and generate review feedback
Best for：VS Code users
Sync Documentation with Code Changes
Automatically update related documentation after merging a PR
Best for：VS Code users
Third-party key setup for Zoo Code (APIMaster integration)
We do not yet have reliable evidence that this product supports third-party keys, proxies, custom providers, or a custom base URL, so we do not show speculative setup steps or config values.
Community discussion
Discussion summary
Users usually understand Zoo Code as an open-source VS Code AI agent extension (a fork of Roo Code) that provides a multi-mode AI agent team for architecting, coding, debugging, and more inside the editor. Discussion mainly focuses on how to use Zoo Code with local LLMs such as Ollama, Qwen, and DeepSeek, as well as hardware configuration and performance optimization. Users also often share experience with agent modes, tool integrations such as web search and Qdrant context indexing, and overall workflow setup.
Most discussed topics
- 1
How to Build a Local LLM Coding Environment with Zoo Code
Users discuss integrating local models such as Gemma and Qwen2.5-Coder with Zoo Code, focusing on VRAM requirements, Ollama/llama.cpp configuration, and feasibility on lower-spec hardware.
- 2
Zoo Code Agent Modes and Skills Configuration
Users share how to combine VSCode + Zoo Code + Skills (orchestrator, architect, debugger, coding), as well as how to add Tools such as web search and compliance and Qdrant indexing to improve agent capabilities.
- 3
API Integration Between Zoo Code and Different Models
Users discuss how to connect OpenAI-compatible interfaces or specific models such as DeepSeek v4 pro and Kimi K3 in Zoo Code, including base URL setup, token speed optimization, and context management.
- 4
Using Zoo Code in Real Coding Projects
Users discuss using Zoo Code for vibe coding, game tool development, or Next.js tasks, emphasizing switching between Architect mode for planning and Code mode for execution, as well as integration with daily VS Code workflows.
FAQ
What type of product is Zoo Code?
We currently classify it under the "Programming / Developer" category, and the page description is based on public materials from the official website and OpenRouter.
What is Zoo Code suitable for?
The enhanced Zoo Code page prioritizes the core tasks and use cases that have been collected, helping you quickly judge whether it matches your current needs.
Can Zoo Code connect directly to APIMaster right now?
There are currently no reliable sources confirming that the product supports third-party keys or custom compatible endpoints, so the page status is shown as pending verification.
Similar agents
Claude Code
It is also in the Programming / Developer category and can be used to compare different task entry points and product formats side by side.
Cline
It is also in the Programming / Developer category and can be used to compare different task entry points and product formats side by side.
Kilo Code
It is also in the Programming / Developer category and can be used to compare different task entry points and product formats side by side.
Sources：Official websiteOfficial docsGitHub
Last verified: 2026-08-30 · Report a correction