# Kilo Code

Open-source AI coding agent for VS Code, JetBrains, and CLI with 500+ models, specialized modes, and cloud agent deployment.

## Agent Decision Summary
- Risk level: elevated
- Source confidence: high
- Recommended workflows: Coding agent workflow, Connector or protocol layer
- Permission surface: shell/files, external services
- Agent JSON: https://www.openagent.bot/agents/kilo-code.agent.json

## Summary
Kilo Code is an open-source AI coding agent that works across VS Code, JetBrains, CLI, and Slack with 500+ models via the Kilo Gateway. It features specialized agent modes (Code, Architect, Debug, Ask), cloud-based agent deployment (KiloClaw), AI-powered code review, and a marketplace of MCP servers and modes.


## Guide
Kilo Code is the most ambitious all-in-one open-source coding agent platform. With $8M in seed funding from GitLab's co-founder, support for 500+ models, and a vision that spans VS Code, JetBrains, CLI, Slack, and cloud agents, Kilo Code is building the broadest platform in the open-source coding agent space.

### What it is
Kilo Code is an open-source AI coding agent that works across VS Code, JetBrains, CLI, Slack, and Cloud. It features 500+ models with zero markup, specialized agent modes, AI code review, and one-click cloud agent deployment.

### Why it matters
Kilo Code's all-in-one approach addresses a fragmentation problem in the coding agent space — developers currently need different tools for terminal, IDE, code review, and cloud automation. Kilo Code aims to be the single platform for all of these workflows.

### How it works
Start with one safe workflow for Kilo Code. Inspect official setup instructions, required credentials, execution logs, approval points, and failure recovery before expanding from a sandbox task into production automation.


## Use Cases
- Enterprise-scale model selection: Use Kilo Code's model gateway to run different models for different tasks — cheap models for boilerplate, frontier models for complex reasoning.
- 24/7 background automation: Deploy KiloClaw agents that monitor repositories, triage issues, and run scheduled tasks while your team is offline.
- Team-wide AI adoption: Standardize on Kilo Code across your team to get consistent AI coding capabilities regardless of individual editor preferences.

## Alternatives
- Use Cline for a more established ecosystem vs Cline: Kilo Code offers broader platform coverage and more models. Cline has a larger community, more extensions, and longer track record.
- Use OpenCode for simpler multi-provider workflows vs OpenCode: Kilo Code is more feature-rich across more surfaces. OpenCode offers a simpler, more focused experience with 75+ providers.

### Getting Started
- Read the documentation: https://kilo.ai/docs
- Inspect the repository: https://github.com/Kilo-Org/kilocode

### FAQ
- What should I check before using Kilo Code?
  - Start with one safe workflow for Kilo Code. Inspect official setup instructions, required credentials, execution logs, approval points, and failure recovery before expanding from a sandbox task into production automation.
- Is Kilo Code open source?
  - Kilo Code is listed with Apache-2.0 based on the official source links in this profile. The core VS Code extension is open source.
- What models does Kilo Code support?
  - Kilo Code supports 500+ models through the Kilo Gateway, including Claude, GPT, Gemini, DeepSeek, local Ollama models, and more.
## What It Does
Kilo Code is an open-source AI coding agent that works across VS Code, JetBrains, CLI, Slack, and Cloud. It features 500+ models with zero markup, specialized agent modes, AI code review, and one-click cloud agent deployment.

## How To Evaluate
Start with one safe workflow for Kilo Code. Inspect official setup instructions, required credentials, execution logs, approval points, and failure recovery before expanding from a sandbox task into production automation.

## Why It Matters
Kilo Code is backed by $8M in seed funding from GitLab's co-founder and combines the best features of Cline and Roo Code into an all-in-one platform. Its zero-markup pricing on 500+ models and cloud agent deployment make it a unique offering in the open-source coding agent space.


## Best For
- Developers who want maximum model choice with zero-markup pricing
- Teams that need VS Code, JetBrains, and CLI support from one tool
- Engineers who want cloud-hosted agent deployment alongside IDE integration

## Not For
- Users who prefer lightweight, single-purpose terminal agents
- Teams that are satisfied with simpler, more established coding agents

## What It Actually Does
- 500+ models at zero markup: Access over 500 models through the Kilo Gateway at exact provider rates with no markup.
  - Why it matters: Model choice without price inflation means developers can use the best model for each task without paying a premium.
- Multi-surface coverage: Works in VS Code, JetBrains, CLI, Slack, and Cloud — with session sync across all surfaces.
  - Why it matters: Start a task on your phone, refine in the CLI, and finish in your IDE — all from the same agent session.
- Specialized agent modes: Code, Architect, Debug, and Ask modes — each with tailored instructions and tool permissions.
  - Why it matters: Different tasks need different agent behaviors. Mode switching keeps the agent focused and efficient.
- Cloud agent deployment: KiloClaw lets you deploy OpenClaw-compatible agents to the cloud with one click — no SSH, Docker, or YAML required.
  - Why it matters: Teams can run 24/7 agents without managing infrastructure, with auto-restart, monitoring, and security updates included.

## Typical Use Cases
- Multi-model experimentation: Switch between 500+ models to find the best performer for your specific codebase and tasks.
- Cross-platform development: Use Kilo Code in VS Code for frontend work, JetBrains for backend, and CLI for DevOps tasks — all with consistent behavior.
- Automated code review in CI: Set up AI-powered code reviews that run automatically on pull requests, with configurable rules and model selection.

## How It Compares
- Choose Kilo Code for model breadth and platform coverage vs Cline: Kilo Code offers 500+ models, JetBrains support, and cloud agent deployment. Cline has a larger community and more mature ecosystem.

## Fit Matrix
- Coding agent workflow: strong. Kilo Code has multiple signals for coding agent workflow, including matching tags, capabilities, category, or positioning. Required check: Run a small repository change and inspect the diff, tests, and rollback path.
- Connector or protocol layer: strong. Kilo Code has multiple signals for connector or protocol layer, including matching tags, capabilities, category, or positioning. Required check: Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.
- Reusable skill workflow: partial. Kilo Code has at least one signal for reusable skill workflow, but should be checked against a real task before adoption. Required check: Run one skill end to end and check whether it produces evidence or structured output.
- Browser automation: weak. Kilo Code is not primarily positioned for browser automation in the current metadata. Required check: Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
- Evaluation and observability: weak. Kilo Code is not primarily positioned for evaluation and observability in the current metadata. Required check: Add one repeatable test case and confirm results can run again in review or CI.
- Local or private AI stack: weak. Kilo Code is not primarily positioned for local or private ai stack in the current metadata. Required check: Verify hardware requirements, data path, storage, and whether all calls stay in your environment.

## Evidence
- verified: Kilo Code is listed as open source. Source: License metadata: Apache-2.0
- verified: Kilo Code has a recorded GitHub repository: Kilo-Org/kilocode. Source: Resource facts and GitHub source link.
- inferred: Kilo Code supports these recorded deployment modes: cloud. Source: OpenAgent decision signal metadata.
- inferred: Kilo Code is tagged with mcp, workflow orchestration capabilities. Source: OpenAgent capability taxonomy.

## Missing Checks
- Repository freshness has not been recorded.

## Next Actions
- Inspect repository: https://github.com/Kilo-Org/kilocode
- Open Homepage: https://kilo.ai
- Read setup docs: https://kilo.ai/docs
- Install Kilo Code CLI: brew install kilo-org/tap/kilo

## Command Line
### Install Kilo Code CLI
Install via Homebrew, then run 'kilo' in any project directory. Also available as a VS Code and JetBrains extension.

```bash
brew install kilo-org/tap/kilo
```

## Facts
- Category: agents
- Resource type: agent
- Open source: yes
- License: Apache-2.0
- Last verified: 2026-06-04
- GitHub repo: Kilo-Org/kilocode
- GitHub stars: 19800

## Capabilities
- mcp
- workflow-orchestration

## Structured Use Case Tags
- developer-workflow

## Getting Started
- Open the GitHub repository: https://github.com/Kilo-Org/kilocode
- Read the documentation: https://kilo.ai/docs
- Visit the project website: https://kilo.ai

## Links
- GitHub: https://github.com/Kilo-Org/kilocode
- Homepage: https://kilo.ai
- Docs: https://kilo.ai/docs

## Structured Outputs
- JSON: https://www.openagent.bot/agents/kilo-code.json
- Markdown: https://www.openagent.bot/agents/kilo-code.md
- Agent JSON: https://www.openagent.bot/agents/kilo-code.agent.json
- Canonical: https://www.openagent.bot/agents/kilo-code