Continue
Open-source AI code agent for IDE and CI
Description
Continue is an Apache 2.0 licensed AI coding tool built by Continue Dev, Inc., a Y Combinator-backed company founded in 2023 by Ty Dunn and Nate Sesti. The project began as a vendor-neutral IDE extension and now extends into source-controlled AI checks that run as GitHub status checks during pull request review. Continue ships no proprietary models and works as an orchestration layer over external providers and local LLMs.
Key Capabilities:
VS Code and JetBrains extensions with Chat, Plan, and Agent modes for in-editor workflows
Continue CLI for running AI checks in CI pipelines through markdown-defined rules in .continue/checks/
Universal model support covering OpenAI, Anthropic, Google Gemini, Mistral, Together, and others
Local model execution through Ollama, LM Studio, and Msty for offline and air-gapped use
Workspace-wide context gathering across open files, related code, and git diffs
Side-by-side diff view with per-change accept and reject controls
Team standards enforcement through .continue/rules/ directory configuration
Cloud Agents and Mission Control for managing remote agent runs
Continue Hub marketplace for sharing custom assistants, rules, and skills
YAML and TypeScript configuration files for project-specific customization
Open source under Apache 2.0 license with self-hostable deployment
Alternative tools
- Claude Code
Agentic coding tool that runs in your terminal
- OpenAI Codex CLI
Terminal coding agent built on OpenAI reasoning models
- Aider
AI pair programming in your terminal
- Cline
Open-source AI coding agent for any editor
- Braintrust Evals
Trace every step your LLM agent takes, from prompt to response
- Giskard
Scan AI agents for vulnerabilities before and after deployment
