Kilo Code
The open-source coding agent that mass-uninstalled Copilot across 1.5 million developers
Video Review
About
Kilo Code started as a fork of Cline and Roo Code. Nine months and $8 million in seed funding later, it processes over 25 trillion tokens and sits on 1.5 million desktops. That trajectory alone should make you pause. Here's what makes it different: Orchestrator mode. You describe a task — 'refactor the auth module to use OAuth2' — and Kilo splits it into coordinated subtasks across a planner agent, a coding agent, and a debugger agent. Each subtask runs in parallel. The planner maps architecture, the coder writes implementation, the debugger catches issues before you even see the diff. It's not autocomplete pretending to be agentic. It's actual multi-agent orchestration inside your IDE. You get access to 500+ AI models at provider rates. No markup. Claude Sonnet 4.6, GPT-5, Gemini, Llama — all at the same price you'd pay the API directly. New users get $20 in free credits without setting up any API keys. Memory Bank stores your architectural decisions, coding patterns, and team conventions. Open a new session weeks later and the agent remembers your project structure, your preferred patterns, your naming conventions. It onboards new team members automatically. The extension runs on VS Code, JetBrains, and CLI. Inline autocomplete, browser automation for testing, automated PR reviews, and a visual app builder that generates production code from descriptions. The GitLab co-founder built this because existing tools felt like smart autocomplete rather than actual engineering partners. The weakness: Orchestrator mode burns through tokens fast on complex tasks. A heavy refactoring session can run $15-25 in API costs. And because it forked from Cline, some UI patterns still feel borrowed rather than native.
Key Features
- Orchestrator mode splits complex tasks across planner, coder, and debugger agents running in parallel
- Access to 500+ AI models at zero markup on provider API rates
- Memory Bank persists architectural decisions, patterns, and conventions across sessions
- Inline autocomplete with context-aware code suggestions
- Browser automation for testing and visual app building
- Automated code review agents that analyze pull requests and catch bugs
- Works on VS Code, JetBrains IDEs, and command-line interface
- Custom modes for planning, coding, and debugging workflows
Use Cases
- 1Refactoring entire codebases with multi-agent orchestration that plans, codes, and debugs in parallel
- 2Onboarding new developers by letting Memory Bank explain project architecture and conventions automatically
- 3Running automated code reviews on pull requests before human reviewers touch them
- 4Building MVPs from natural language descriptions using the visual app builder
- 5Switching between AI models mid-task to balance cost and quality
Pros
- 500+ AI models at zero markup — Claude Sonnet 4.6 costs roughly $3-8/hour of heavy usage at direct API rates
- Orchestrator mode is genuine multi-agent coordination, not just sequential prompting
- Memory Bank remembers project context across sessions — no re-explaining your codebase every time
- JetBrains support sets it apart from most competitors locked to VS Code only
- $20 in free credits for new users with no API key setup required
Cons
- Orchestrator mode burns through tokens fast — complex refactoring sessions can cost $15-25 in API fees
- Forked from Cline and Roo Code, so some UI elements feel derivative rather than purpose-built
- Memory Bank can get stale if project architecture changes significantly without explicit updates
- 500+ model options create decision paralysis — no clear guidance on which model fits which task
Details
- Category
- code
- Pricing
- freemium