Kilo Code
Open-source (MIT) VS Code and JetBrains agentic coding extension - the community successor to Roo Code - with 500+ models, BYOK, five agent modes, MCP support and model routing.
Work at Kilo Code? Manage this listing
Our take
Kilo Code is the actively maintained community fork that picked up where Roo Code left off after it was archived. It's an open-source VS Code/JetBrains agent with BYOK across 500+ models, five agent modes, MCP support and routing to keep spend in check. You only pay for the model calls. A strong fit if you want agentic coding without lock-in.
Best for
Developers who want flexible, open-source agentic coding in their existing IDE without vendor lock-in.
Pros
- Open source (MIT); no platform fee, BYOK across 500+ models
- VS Code and JetBrains, five agent modes, MCP support
- Model routing helps control agentic spend
- Active community fork continuing Roo Code
Cons
- Quality depends on the models you bring
- Fork governance is younger than commercial rivals
- Setup/BYOK asks more of you than a turnkey tool
How it compares
Versus Cursor or Copilot, Kilo Code trades a polished managed experience for openness and control - bring your own keys and models, and pay only for what you call.
Full review
Kilo Code is an open-source, agentic coding extension for VS Code and JetBrains, and the community's continuation of Roo Code after that project was archived in May 2026. It is MIT-licensed, brings your own keys across 500+ models, and ships five agent modes plus MCP support, so it can plan and edit across files rather than just autocomplete a line.
The economics are the draw: there is no platform fee - you pay only for the model calls you make - and built-in model routing helps control agentic spend by sending work to the right model. The trade-offs are real: output quality tracks the models you bring, BYOK setup asks more of you than a turnkey product, and a young community fork has less governance behind it than a commercial vendor. For developers who value openness and control, that is usually an acceptable deal.
Cloudkart Trust Graph
4.0/5- Actual Utility4/5
Source: Initial LLM-authored rubric (backfill)
- Ease of Use4/5
Source: Initial LLM-authored rubric (backfill)
- Pricing Fairness5/5
Source: Initial LLM-authored rubric (backfill)
- Reliability3/5
Source: Initial LLM-authored rubric (backfill)
- Differentiation4/5
Source: Initial LLM-authored rubric (backfill)
Scored as of . Each score is versioned and auditable; vendors cannot buy it.
How this score is set
- Editorial rubric
- Primary signal — five dimensions, 4.0/5 average.
- Community reviews
- None yet.
- Pricing verified
- Not yet verified
- Independence
- Score set by our editorial team before any affiliate relationship is considered. No vendor can buy it.
Frequently asked questions
- Is Kilo Code free, and how much does it cost?
- Kilo Code is open source and free to self-host.
- Who is Kilo Code best for?
- Developers who want flexible, open-source agentic coding in their existing IDE without vendor lock-in.
- How is Kilo Code rated on Cloudkart.ai?
- Kilo Code scores 4.0 out of 5 on the Cloudkart.ai rubric, which weighs actual utility, ease of use, pricing fairness, reliability and differentiation. Scores are set editorially and can never be bought.
Community reviews
No community reviews yet. Be the first to share how Kilo Code works for you.
Relevant tools
More tools in AI Coding Assistants.
Composio
Composio provides the execution infrastructure that connects AI agents to real software. It sits at the tooling and connectivity layer of the agent stack, giving developers one framework - SDKs, a CLI and 850+ pre-built connectors - to let agents act across apps such as GitHub, Slack and Salesforce. It handles the hard parts: complex authentication and OAuth, plus remote sandboxed environments for safe execution, exposed over the Model Context Protocol so agents can reason and then reliably take action. The platform is built for production, with SOC 2 and ISO 27001:2022 certifications and deployment across public cloud, VPC and on-premises. Composio operates from San Francisco and Bangalore and raised a $25M Series A led by Lightspeed, with angels including Vercel's Guillermo Rauch and HubSpot's Dharmesh Shah.
LiteLLM
LiteLLM, from BerriAI, is an open-source AI gateway that gives you a single OpenAI-compatible interface to 140+ providers and 2,500+ models, including OpenAI, Anthropic, Gemini, Bedrock, Azure, Mistral, Ollama and vLLM. You can use it as a lightweight Python SDK for direct calls, or deploy the proxy server as a centralized gateway for a team, with virtual keys, budgets, load balancing, rate limiting, request logging and LLM guardrails. It has become a default building block in the AI stack, with 45,000+ GitHub stars, 240M+ Docker pulls and over a billion requests served, and is used by companies including Netflix, Adobe and Stripe. The core is free; an enterprise tier adds JWT auth, SSO/SAML, audit logs, SLAs and dedicated support.
Claude Code
Terminal-based agentic coding tool from Anthropic for autonomous multi-step coding tasks.
Kiro
AWS agentic IDE built around spec-driven development: it writes a spec, then builds matching code, tests and docs across IDE, CLI and web.
Compare Kilo Code head-to-head: vs Composio · vs LiteLLM · vs Claude Code · vs Kiro