GILD verdict
Choose Cursor if your team is ready to change editors and wants a maintained product with model usage included.
Keep Continue only while you plan a move if completion must run on local models, and pilot Cursor on accepted, reviewed changes before you switch.
Cursor acquired Continue in June 2026, and Continue stopped shipping releases, so the maintained path runs through Cursor's own editor. Continue's VS Code extension, frozen at 2.0.0 with a 2.1.0 pre-release since June 19, 2026, and its JetBrains plugin at 1.0.67 still run in the editors engineers already use. A move to Cursor gives up completion on local models, since Tab runs only on Cursor's models.
Choosing between Continue and Cursor
Choose Continue if
- Engineers must stay in VS Code or a JetBrains IDE they already run.
- Completion must run on a local model; Cursor's own API keys cover chat models only, and Tab stays on Cursor's models.
- You are keeping Continue for a defined period while a successor is piloted.
Choose Cursor if
- You want a maintained editor with agents, completion, and model access from one vendor.
- Admins need Teams seats with SSO and Privacy Mode enforced for the whole team.
- Engineers are ready to switch editors; Cursor documents moving VS Code settings and extensions over.
Side by side
| Dimension | Continue | Cursor |
|---|---|---|
| Maintenance | Read-only repository; final VS Code release 2.0.0, plus a 2.1.0 pre-release, on Jun 19, 2026 | Maintained by Cursor, the company that acquired Continue |
| Individual priceList prices in US dollars. Cursor's plans include model usage; Continue's price does not. | Free under Apache 2.0; paid plans ended | Premium: US$30 per month in the X Subscription Cursor announced Oct 12, 2026, with a weekly pool for Cursor's own models; Pro at US$20 is a legacy plan closed to new customers |
| Team price | No seats; model usage paid to your provider | The Teams docs list Premium at US$30, Super at US$100, or Ultra at US$200 per seat a month in the X Subscription announced Oct 12, 2026; Standard US$40 and Premium US$120 apply only to teams created before it. Enterprise is custom |
| Where it runs | Extension for VS Code and JetBrains IDEs, and the cn CLI | Its own desktop editor built on the VS Code codebase, plus a CLI and cloud agents |
| Your own models | Any provider or local runtime, for chat, edits, autocomplete, and embeddings | API keys from OpenAI, Anthropic, Google, Azure, or AWS Bedrock for chat models; Tab uses Cursor's built-in models |
| Approvals | Agent mode asks before each tool call unless its policy is Automatic | Agents read files and edit workspace files without approval, except configuration files; sensitive actions need approval |
| Admin controls | None; the hosted Continue Hub and team plans closed | SSO on Teams and Enterprise, and Privacy Mode enforceable for the whole team |
What practitioners report, side by side
Each product's figures come from its own practitioners, for the group you pick.
Overall signal
All practitioners rate Cursor +6, 15 points above Continue at −9. Most of the gap is in praise, with 49 of Cursor's 117 sources positive against 18 of Continue's 69. Cursor has 41 negative and Continue 23.
The score counts the authors from all practitioners that take a side, one vote each with their latest view, and is how far positive votes lead negative ones, per 100 votes, so Continue's −9 rests on votes split 17 positive, 26 mixed and 23 negative and Cursor's +6 on 48, 27 and 41.
A lead of a fifth of the votes reads positive and a lead of half strong positive, with the same lines below zero. The dots show each source, positive, mixed, negative. Use a task pilot to measure accepted work and review time.
Footprint on the Agentic Software Development stack
They differ on three of 12 layers. Cursor owns one that Continue does not. Coverage is each product's placement on this stack, as its product page shows it. Core is a job the product owns; Supports and Touches are jobs it helps with. Coverage says nothing about how well a product does them.
| Layer | Continue | Cursor |
|---|---|---|
| Plan | ||
| Work planning | Touches | Supports |
| Build | ||
| Codebase context | Supports | Core |
| Validate | ||
| Code review | Touches | Supports |
The 9 layers where they match
| Layer | Continue | Cursor |
|---|---|---|
| Build | ||
| Coding | Core | Core |
| Agent runtime | Core | Core |
| Tool execution | Supports | Supports |
| Validate | ||
| Debugging | Supports | Supports |
| Testing | Supports | Supports |
| Application security | Touches | Touches |
| Ship | ||
| Source control | Touches | Touches |
| CI/CD | Touches | Touches |
| Operate | ||
| Observability | Touches | Touches |
What practitioners praise
Among all practitioners, Cursor alone has seven praise themes that reach 5 sources from 3 authors. Model Choice and Tab Completion lead, at 20 of 25 and 10 of 13. Continue alone has five praise themes that reach 5 sources from 3 authors. Local and Self-Hosted Models and Model and Provider Choice lead, at 28 of 31 and 8 of 8.
| Praised for | Continue | Cursor |
|---|---|---|
| Local and Self-Hosted Models | 28 of 31 | Not a theme in its sources |
| Model and Provider Choice | 8 of 8 | Not a theme in its sources |
| Open Source and Configurable | 5 of 5 | Not a theme in its sources |
| Codebase and Docs Context | 4 of 6 | Not a theme in its sources |
| Tab Autocomplete | 4 of 15 | Not a theme in its sources |
| Model Choice | Not a theme in its sources | 20 of 25 |
| Tab Completion | Not a theme in its sources | 10 of 13 |
| Agent Execution | Not a theme in its sources | 9 of 12 |
| Codebase Understanding | Not a theme in its sources | 9 of 15 |
| Cloud Agents | Not a theme in its sources | 8 of 9 |
| Speed | Not a theme in its sources | 8 of 10 |
| Value for Money | Not a theme in its sources | 7 of 13 |
Each count is the sources that praise a theme, or raise it as a concern, out of those that discuss it. A row pairs the two products when both carry a theme under the same or an equivalent name.
A count ending in "so far" has under 5 sources from 3 authors among all practitioners. "Not a theme in its sources" means GILD found no theme of that name in that product's sources.
What practitioners raise as concerns
Among all practitioners, Cursor alone has six concern themes that reach 5 sources from 3 authors. Usage / Cost and Inconsistent Quality lead, at 25 of 35 and 14 of 15. Continue alone has five concern themes that reach 5 sources from 3 authors. Reliability and Update Regressions and End of Maintenance lead, at 18 of 18 and 11 of 11.
| Raised as a concern | Continue | Cursor |
|---|---|---|
| Reliability and Update Regressions | 18 of 18 | Not a theme in its sources |
| End of Maintenance | 11 of 11 | Not a theme in its sources |
| Results Depend on the Model | 10 of 10 | Not a theme in its sources |
| Setup and Configuration Effort | 10 of 11 | Not a theme in its sources |
| JetBrains Plugin Stability | 7 of 9 | Not a theme in its sources |
| Usage / Cost | Not a theme in its sources | 25 of 35 |
| Inconsistent Quality | Not a theme in its sources | 14 of 15 |
| Requires Strong Review | Not a theme in its sources | 14 of 19 |
| Reliability & Performance | Not a theme in its sources | 12 of 12 |
| Needs Close Steering | Not a theme in its sources | 10 of 12 |
| Editor Lock-in | Not a theme in its sources | 7 of 11 |
16 sources
- Continue (acquired by Cursor)
- Continue on GitHub (continuedev/continue)
- Continue releases on GitHub
- Continue docs: Model providers overview
- Continue docs: Autocomplete setup
- Continue docs: How Agent mode works
- Cursor pricing
- Cursor forum: Introducing The X Subscription, staff announcement (Oct 12, 2026)
- Cursor docs: Teams pricing
- Cursor docs: SSO
- Cursor docs: Privacy & data governance
- Cursor docs: Agent security
- Cursor docs: CLI
- Cursor docs: Cloud agents
- Cursor docs: VS Code migration
- Cursor docs: Bring your own API key