Free & Open Source
$0
Apache 2.0, BYOK, pay only LLM API costs
Continue
Open-source AI coding platform — IDE, CLI, and source-controlled AI checks in CI.
Continue is the leading open-source AI coding platform for VS Code and JetBrains, with 33K+ GitHub stars under Apache 2.0. It provides chat, inline edit, autocomplete, and agent mode in the IDE, a CLI for headless and scripted work, and a Continuous AI surface that runs source-controlled AI checks on pull requests in CI. Model-agnostic, self-hostable, and extensible via custom context providers and the Continue Hub marketplace.
+ Pros
- Open source (Apache 2.0) with 33.4k+ GitHub stars, 4.6k forks, and 822 releases — one of the most popular and actively maintained AI coding tools with strong community trust.
- Dual-product powerhouse: an AI coding IDE extension (agent mode, chat, autocomplete, edit) AND a CI-focused AI checks system that enforces engineering standards as GitHub status checks on every PR.
- Multi-IDE support across VS Code and all JetBrains IDEs (IntelliJ, PyCharm, WebStorm, GoLand, etc.), plus a standalone CLI with npm/curl install.
- Supports an extensive range of LLM providers: OpenAI, Anthropic, Ollama, Groq, Gemini, OpenRouter, xAI/Grok, DeepSeek, vLLM, Moonshot, Llama.cpp, plus cost-optimized routing via ClawRouter.
- Full MCP (Model Context Protocol) integration with SSE, Streamable HTTP, OAuth support, JSON config files, and resource templates — enabling deep tool ecosystem connectivity.
- Agent mode with autonomous file read/write, terminal commands, AST-based fast apply (avoiding full-file rewrites), ripgrep search, internet search, and shareable agent workflows.
- hub.continue.dev marketplace for custom assistants, rules, MCP servers, and models — plus tabs, pause/resume, the 'notch' control panel, LLM logs UI, and enterprise license support.
− Cons
- Dual-product identity (IDE assistant vs CI checks) creates confusion about what Continue actually is — the GitHub README recently pivoted to emphasize CI checks, while the changelog and version tags still predominantly focus on the IDE extension.
- Heavily reliant on external LLM API providers — most advanced features (agent mode, CI checks, fast apply) require paid API keys to OpenAI, Anthropic, or similar services; local-only setups via Ollama have limited tool-calling capability.
- JetBrains integration has persistent stability issues — recent changelogs document fixes for IDE freezes, JCEF sidebar freezes, memory leaks, remote config sync crashes, and disposed browser exceptions.
- Versioning is confusing with parallel tracks (v1.2.x stable, v1.3.x pre-release, v1.0.x JetBrains, v1.5.x standalone) making it hard to track which version to use and what's the canonical latest release.
Pricing
Continue Hub Free
$0
Team configs, shared assistants
Enterprise
Custom
Self-hosted, SSO, audit logs
Continue is the leading open-source AI coding platform with full parity between VS Code and JetBrains — the only OSS option that serves both ecosystems equally well. Distributed under the Apache 2.0 license with 33K+ GitHub stars, it provides four core in-IDE capabilities (chat, inline edit, autocomplete, and agent mode) plus a CLI and a Continuous AI surface that runs source-controlled AI checks on pull requests in CI.
Continue's extensibility is its key differentiator: a rich context provider system lets teams connect any data source — internal documentation, databases, GitHub repositories, Jira tickets, Confluence pages, or custom APIs — directly into the assistant's context window. Configuration is YAML-based and fully version-controllable, making it easy to enforce consistent setups across teams. The Continue Hub provides a marketplace for sharing team configurations, assistants, prompts, rules, and skills, enabling organizations to distribute standardized AI setups to all developers in seconds.
Continue is model-agnostic: Anthropic, OpenAI, Google Gemini, Mistral, Azure OpenAI, AWS Bedrock, Together AI, Groq, ClawRouter for cost-optimized routing, and any local model via Ollama, LM Studio, or llama.cpp. Self-hosted deployments keep all code and queries on-premise, making Continue the preferred choice for regulated industries, air-gapped environments, and privacy-conscious teams. The Continuous AI direction — markdown-defined Checks that run as full AI agents on every PR, plus Mission Control for observability — turns Continue from "AI in the editor" into a programmable engineering system.
Key Features
• VS Code + JetBrains parity: full feature support in both ecosystems — the only major OSS assistant with this
• Four in-IDE modes: chat, inline edit, autocomplete, and agent mode
• Continue CLI: same engine on the terminal, scriptable for headless workflows
• Continuous AI: source-controlled markdown Checks run as full AI agents on pull requests
• Model-agnostic: Anthropic, OpenAI, Gemini, Mistral, Azure, Bedrock, Groq, ClawRouter, or local (Ollama, LM Studio, llama.cpp)
• Custom context providers: docs, databases, GitHub, Jira, Confluence, or any API
• Continue Hub: marketplace for team configurations, assistants, prompts, rules, and skills
• YAML config: version-controllable setup files for consistent team deployments
• Self-hostable: all data stays on-premise — ideal for regulated and air-gapped environments
• MCP support: connect Model Context Protocol tools for extended capabilities
• 33K+ GitHub stars · Apache 2.0 open source
• Team/Company plans: SSO, audit logs, shared private agents, BYOK, enterprise support
Version History
Latest stable VS Code release. Fixes config.yaml access issues, adds session history filtering by workspace directory, and introduces .continue/configs support for multi-config workflows.
Introduces shareable agent links, Code Review Inbox for PR workflow management, and the ability to add just-in-time additional instructions when starting an agent.
Major release with full GPT-5 Codex support via OpenAI Responses API, Grok Code Fast 1 integration from xAI, and Instant Edit mode with synchronous diff application for find/replace operations.
Enables file access beyond the workspace directory with permission controls, improves agent error handling with fetch error feedback, and adds CLI stability fixes including loading animations and proper exit handling.
Major UI overhaul with notch cleanup and settings revamp, git-aware CLI showing current branch, enhanced /info diagnostics screen, smart diff visual UI, pause/resume, and ctrl+C safety improvements.
Signature Snippet
A team at a regulated company self-hosts Continue with a local Ollama instance running CodeLlama. Developers in both VS Code and IntelliJ get chat, inline edit, and autocomplete with zero data leaving the network. A shared team config in Continue Hub enforces the company's coding standards and connects to the internal docs context provider for all queries.More in this Space
Paca
Paca is a free, open-source, self-hosted Scrum board where AI agents work as equal teammates — assigned to sprints, picking up tasks, and collaborating on BDD specs alongside humans. Built as an alternative to Jira and Linear, it treats AI agents as first-class Scrum members.
Nanobot
Nanobot is an ultra-lightweight, open-source (MIT) personal AI agent that ships with WebUI, multi-channel chat (Telegram, Discord, WeChat, Slack, Feishu, email), MCP support, memory, model routing with fallbacks, cron automation, and a plugin skill system — all pip-installable in seconds. Built on a deliberately small and readable Python core, it lets you truly own your AI agent stack.
AionUi
AionUi is a free, open-source Cowork desktop app that runs Claude Code, Codex, Gemini CLI, OpenClaw, Hermes Agent, and 20+ more coding agents side-by-side within a unified Electron interface. It auto-detects installed CLI agents, provides a built-in AI engine with 30+ provider support, and adds Team Mode for multi-agent orchestration — all from one desktop workspace.