Continue.dev Review: Open-Source Coding Assistant
TL;DR: Continue.dev is one of the strongest free AI coding assistants going around. It runs in most IDEs, hooks up to almost any model, and because it's open source you're not tied to one vendor. It's rougher around the edges than Copilot or Cursor, but the price and the flexibility are hard to argue with. One caveat worth knowing up front: the original open-source project has since been archived, so check the current state before you commit a team to it.
There's a particular kind of frustration that comes from paying a monthly fee for a coding tool, then discovering it only behaves the way you want inside one editor, with one company's model, on that company's terms. Continue.dev was built for the developers who got tired of that arrangement.
It's an open-source AI coding assistant that drops into your editor and lets you choose the engine yourself. Want OpenAI's latest? Fine. Want a model running entirely on your own laptop so no code ever leaves the building? Also fine. That openness is the whole pitch, and for a lot of teams it's the difference between adopting an AI tool and quietly avoiding one because the data rules say no.
For an Australian business weighing up coding tools, the appeal is practical rather than ideological. Free to run, no lock-in, and a privacy story you can actually explain to a compliance officer. The trade-off is that you do some of the setup work yourself, and you don't get every polished trick the paid tools throw in.
One thing the original review didn't flag, and you should know: the continuedev/continue repository that powered the open-source project is now read-only and archived, with v2.0.0 listed as its final release. Anything below about the tool's behaviour still describes how it worked, but treat the "actively maintained" assumption with caution and confirm the current situation before betting a team on it.
What Is Continue.dev?
Continue.dev is an open-source AI coding assistant, released under the Apache 2.0 licence. The core pieces:
- IDE extension, VS Code, JetBrains, Vim, Neovim
- Any LLM, OpenAI, Anthropic, Google, Ollama, LM Studio
- Autocomplete, inline suggestions
- Chat, sidebar conversation
- Edit, targeted code modifications
- Context awareness, understands your codebase
Price: Free (open source)
Works Everywhere
Continue's main selling point is that it isn't fussy about which editor you use:
| IDE | Support Level | Features |
|---|---|---|
| VS Code | Full | All features |
| JetBrains | Full | All features |
| Vim/Neovim | Full | All features |
| Jupyter | Partial | Chat only |
One thing to keep in mind: the official project ships first-party clients for VS Code, JetBrains, and a CLI. The Vim and Neovim "Full" rating in the table above overstates things, there's no official Vim/Neovim extension, and Neovim support reportedly runs through community wrappers like continue.nvim that proxy the Continue CLI rather than first-party parity. The Jupyter chat-only support is also unconfirmed; it isn't listed among the official clients. We tested in Neovim and VS Code, and the experience felt consistent across both.
Bring Your Own LLM
Continue is model-agnostic, point it at whatever you like:
- Cloud: GPT-5.5, Claude Opus 4.8, Gemini 2.0
- Local: Ollama, LM Studio, vLLM
- API: Any OpenAI-compatible endpoint
A note on the cloud list: GPT-5.5 (released April 2026) and Claude Opus 4.8 (released May 2026) are both current. Gemini 2.0, though, is dated, Google's line as of mid-2026 is the Gemini 3 family, so read that entry as a stale example rather than today's pick.
We ran Continue against a local model through Ollama to see how the zero-cost, fully-private setup holds up in practice. The headline finding from the original draft, that it ran on a "Llama 4 8B" at roughly 70% the quality of GPT-5.5, doesn't hold up: no Llama 4 8B model exists. The smallest released Llama 4 model is Scout (109B total, 17B active), so both the specific model claim and the 70% figure are unsubstantiated and should be treated as such. The broader point still stands: a capable local model gives you coding help with no API bill and no code leaving your machine, and for plenty of everyday tasks that's good enough.
Pros and Cons
| Pros | Cons |
|---|---|
| Completely free | Less polished than paid alternatives |
| Works in any IDE | Autocomplete not as fast as Copilot |
| Any LLM, including local | Requires configuration |
| Open source, no lock-in | Community support only |
| Privacy-friendly | Fewer "magic" features |
The "autocomplete not as fast as Copilot" line is our impression from using both, not a benchmarked result, worth taking as opinion.
Verdict
Score: 8.3/10 (our subjective editorial rating, not a measured one)
If you care about freedom and privacy, Continue.dev earns its place: free, open source, and happy to run wherever you work. Pair it with a local model via Ollama and you've got coding help that never phones home. If raw productivity matters more than control, you may still want Copilot or Cursor alongside it. The honest caveat, again, is that the open-source project is now archived, so confirm where things stand before you make it a fixture of your team's workflow.
*Published June 21, 2026 | Continue.dev v0.9 tested in VS Code and Neovim*
*Editor's note: the version under test was listed as v0.9, but as of mid-June 2026 the project's final release is v2.0.0 and the repository is archived, so that version label appears inconsistent with the public release history.*