The AI Coding Tool Built on Trust and Transparency
Open IDE and CLI clients. Provider-rate inference. 500+ hosted models, plus supported BYOK and local options. Choose the workflow and provider that fit your project.
Use the Kilo agent in a desktop workspace, or keep your existing VS Code, JetBrains, CLI, and Cloud workflows. Desktop runs the Kilo CLI engine and supports 500+ hosted models through Kilo Gateway, your provider keys, and local inference.
Available for macOS Apple Silicon, Windows, and Linux. The built-in local model server, notebooks, and conda environments require a Kilo account. Local inference is not a guarantee of an entirely offline or air-gapped application. See requirements.
Compare the whole cost, not just the seat
- Platform
- Free for individuals. Teams is $15/user/month; Enterprise is custom. SSO, SCIM, and audit logs are Enterprise features, not included in Teams.
- Inference
- Use available free models, local inference, or BYOK. Kilo Gateway charges provider rates with no inference markup. Kilo Pass is an optional credit subscription.
- Cloud compute
- Cloud Agents and hosted Code Reviews have separately priced compute in addition to model inference. Check current pricing and any applicable beta offer. BYOK does not remove compute charges.
Credit purchase processing fee: 5%. Applies to card purchases that add credits, including top-ups and Kilo Pass. Excludes seat subscriptions and non-card payments. See full pricing.
Open-source scope: VS Code, JetBrains, and CLI clients are MIT-licensed; Gateway and Cloud backend code are source-available under a separate license. These licenses do not establish the license of every Desktop component. See component licenses.
Kilo details reviewed . Competitor review dates are listed separately.
Four reasons developers choose Kilo Code
Not just another AI coding tool. A fundamentally different approach.
Open IDE and CLI Clients
Inspect and customize MIT-licensed VS Code, JetBrains, and CLI clients. Gateway and Cloud backend code are source-available under separate terms; Desktop licensing is not established by those licenses.
Transparent Inference Pricing
Individual platform access is free. Gateway inference uses provider rates. Cloud compute, paid team seats, and optional Kilo Pass are separate parts of the cost.
500+ Models — Including Free
Access supported frontier models (Claude Sonnet 5, GPT-5.5, Gemini), any available free models, and compatible local inference through Ollama or LM Studio.
Ships Fast, Listens Faster
15k+ developers in our Discord shaping the roadmap. Weekly releases. Features ship in days, not quarters. Community-driven development where your feedback becomes reality.
Trusted by developers at the world's most innovative companies
Pricing should be simple and transparent
Separate platform access, inference, cloud compute, and credit purchase fees when comparing total cost. Optional subscriptions and team plans serve different needs.
Kilo Code
What you see is what you pay
Individual platform access is free. Teams costs $15/user/month; Enterprise is custom. Paid inference and cloud compute are separate. Kilo Gateway charges provider rates with no inference markup; a 5% processing fee applies to card purchases of credits, including optional Kilo Pass. Seat subscriptions and non-card payments are excluded from that processing fee. BYOK covers inference through your provider, not Kilo cloud compute.
Already paying for OpenAI, Anthropic, or Google?
Bring supported API keys to compatible Kilo workflows. Provider subscriptions are not automatically interchangeable with API access. Model and autocomplete compatibility vary, and cloud compute remains separately billable even when inference uses your own key.
Why developers are switching to Kilo
500+ models. Use the right one for the job.
Choose from Kilo's hosted catalog or configure a compatible provider or local model. Other tools also offer model choice; compare tool support and feature coverage.
Frontier Models
Choose supported models including Claude Sonnet 5, GPT-5.5, Gemini, and Grok. Availability and feature support vary.
Free & Budget Models
Explore budget models and any currently available free models. Free availability can change; check the model listing before starting a task.
Local Models
Run compatible Ollama or LM Studio models for local inference. Connected tools, account services, and hosted features have separate data flows.
Supported BYOK Workflows
Use supported provider keys and compatible endpoints. Not every model supports tools or autocomplete; hosted compute is separate from inference billing.
Specialized agents for every part of your workflow
Purpose-built agents that go beyond basic chat. Each agent is optimized for a specific development task.
Code Agent
Autonomous multi-file coding agent. Writes, edits, and refactors code across your project with full context awareness.
Native Sub-Agent Delegation
Breaks complex projects into subtasks and delegates to specialized sub-agents. Manages the full lifecycle from planning to deployment.
Plan Agent
Researches your codebase and creates detailed implementation plans before writing a single line of code. Plan with confidence.
Debug Agent
Systematic troubleshooting with automatic error detection, test execution, and intelligent recovery. Finds bugs so you don't have to.
Ask Agent
Ask questions about your codebase, get explanations, learn patterns. A knowledgeable pair programmer that understands your project.
Custom Agents
Create custom agents for your workflow and share team configurations. Compare tool permissions and delegation behavior with the other agent platforms you use.
Sources for refreshed claims
- Copilot CLI, MCP, BYOK, and local endpoints
- VS Code BYOK and local-model scope
- Cursor CLI and cloud handoff
- Windsurf / Devin local agent
- Claude Code surfaces and agents
Plan links above provide current terms. This refresh does not certify every competitor feature or a universal cost advantage.
Common Questions
Compare Kilo Code with Other Tools
See how Kilo Code stacks up against other AI coding assistants
Kilo Code vs Cursor
Compare Kilo Code with Cursor across desktop apps, IDEs, models, BYOK, agents, cloud workflows, pricing, and enterprise controls.
GitHub Copilot vs Kilo Code
Compare GitHub Copilot and Kilo across desktop apps, IDEs, agents, CLI, models, local use, pricing, review, and governance.
Kilo Code vs Cline
Compare Kilo and Cline across Desktop beta apps, IDEs, CLI, cloud sessions, models, BYOK, orchestration, teams, and pricing.
Kilo Code vs Devin Desktop
Compare Kilo with Devin Desktop, formerly Windsurf, across IDEs, local and cloud agents, models, pricing, and teams.
Kilo Code vs Roo Code
Roo Code was discontinued May 15, 2026. Compare its preserved capabilities with maintained Kilo workflows and plan a safe migration.
Kilo Code vs Continue
Continue joined Cursor and is no longer actively maintained. Compare its preserved IDE, CLI, YAML, and local-model capabilities with Kilo.
Kilo Code vs Gemini Code Assist
Compare Kilo with paid Gemini Code Assist across IDEs, models, agents, quotas, Google Cloud integration, data controls, and pricing.
Kilo Code vs OpenAI Codex
Compare Kilo and Codex across desktop apps, IDEs, CLI, cloud, hosted models, local providers, subagents, open source, pricing, and governance.
Kilo Code vs Claude Code
Compare Kilo and Claude Code across Desktop, IDEs, CLI and cloud workflows, including model choice, subscription entitlements, extensibility and usage costs.
Kilo Code vs Roomote
Compare Kilo Desktop beta, IDE and CLI workflows with Roomote, a source-available cloud coding agent offering self-hosting, BYOK and parallel tasks.
Kilo Code vs Tabnine
Compare Kilo with Tabnine across agentic coding, IDE and CLI workflows, model choice and private enterprise deployments. Pricing depends on the offered contract.
Kilo Code vs Augment Code
Compare Kilo with Augment Cosmos, Auggie CLI and IDE integrations: context, custom agents, parallel cloud work, flat-team pricing and the Harness asset-sale agreement.
Kilo Code vs Lovable
Kilo Code plugs into your real IDE and codebase — Lovable is a hosted AI app builder optimized for greenfield prototyping.
Kilo Code vs Replit
Use Kilo inside your existing editor and infrastructure vs Replit's hosted browser IDE.
The Open-Source Google Antigravity Alternative
Compare Google Antigravity with Kilo Code for agentic coding across Desktop beta, VS Code, JetBrains, CLI and cloud, with supported BYOK and local models.
Kilo Code vs Warp
Compare Kilo's IDE integrations, CLI, Desktop beta and Cloud Agents with Warp's terminal-first agent environment. Model access and billing depend on the workflow.
Kilo Code vs Amp Code
Compare Amp apps, orbs, BYOK, and teams with Kilo Desktop, IDEs, CLI, and Cloud
Kilo Code vs Grok Build
Compare terminal agents, provider choice, and automation
Kilo Code vs JetBrains AI and Junie
Compare native JetBrains workflows, model access, and pricing
Kilo Code for JetBrains IDEs
AI coding assistant for IntelliJ, PhpStorm, WebStorm, and Rider
Kilo CLI vs Claude Code
Compare Kilo CLI with Claude Code for terminal-first AI coding
Kilo CLI vs Aider
Compare model choice, workflows, and pricing for command-line agents
Kilo CLI vs Codex CLI
See how Kilo CLI compares with OpenAI Codex CLI
Kilo CLI vs Gemini CLI
Compare Google Gemini CLI with Kilo CLI and 500+ models
Kilo CLI vs OpenCode CLI
Compare Kilo CLI with the upstream OpenCode CLI and subscriptions
Kilo Code vs Google Antigravity
Compare models, pricing, agent workflows, and product surfaces
Kilo Autocomplete vs Cursor Tab
Feature-by-feature comparison for AI code completions
Kilo Autocomplete vs GitHub Copilot
Compare autocomplete quality, pricing, and IDE support
Kilo Autocomplete vs Codeium
Compare Kilo Code autocomplete with Codeium completions
Kilo Code Reviews vs Greptile
Compare AI code review workflows, model choice, and pricing
Graphite vs Kilo Code Reviews
Compare Graphite PR workflows with Kilo Code Reviews
Ready to try AI coding without the lock-in?
Join 5M+ developers. Open source. Zero markup. 500+ models.