Roo Code: discontinued. Last release, local setup and alternatives

Roo Code was a VS Code agent extension with modes (Code, Architect, Ask, Debug) and MCP support. It was shut down on 15 May 2026 and is no longer maintained; the final release is 3.54.0. Its README points users to the community fork ZooCode and to Cline.

Source code Compare all agents

At a glance

Type: vscode-extension
Licence: Apache-2.0
Latest release: 3.54.0 (2026-05-15)
Status: Discontinued
Local backends: ollama, lmstudio
Needs native tool calling: Not verified
MCP support: Yes
Recommended minimum context: Not stated in its docs
Start-up prompt: Not measured
GitHub stars: 24.3k (2026-10-19)

How to set it up with a local model

Pick your backend. Each command has its own Copy button. Where a step uses an example model, swap in the one you run; the table below lists the ones that fit your machine.

Install it (VS Code extension (final release 3.54.0)):
```
code --install-extension RooVeterinaryInc.roo-cline
```
Pull a model that supports native tool calling (replace qwen3-coder:30b with your choice).
```
ollama pull qwen3-coder:30b
```
Roo uses the num_ctx saved in the Ollama model, so write a Modelfile that sets at least 32K context.
Modelfile
```
FROM qwen3-coder:30b
PARAMETER num_ctx 32768
```

Create the model with that context.

ollama create qwen3-coder-32k -f Modelfile

In Roo Code, click the settings gear, set API Provider to Ollama and enter the new model name (base URL defaults to http://localhost:11434).
```
qwen3-coder-32k
```

Check that it works

Start a task in Code mode and ask Roo to read a file. A failed tool call means the model does not support native tool calling. To check what Ollama loaded, run:

ollama ps

Which local models fit, by machine

Checked by this site's engine at the context Roo Code needs, with 32 GB of system RAM for MoE offload. A Mac counts three quarters of unified memory as usable.

Machine	Model	Quant	Context	Fit	Ollama
12 GB GPU	Qwen 3.5 9B	Q4_K_M	32,768	Comfortable (7.4 GB of 12 GB)	`qwen3.5:9b`
	Qwen 3.6 35B-A3B	Q4_K_M	32,768	With CPU offload (MoE) (22.7 GB of 12 GB)	`qwen3.6:35b-a3b`
16 GB GPU	Qwen 3.5 9B	Q4_K_M	32,768	Comfortable (7.4 GB of 16 GB)	`qwen3.5:9b`
	Qwen 3.6 35B-A3B	Q4_K_M	32,768	With CPU offload (MoE) (22.7 GB of 16 GB)	`qwen3.6:35b-a3b`
24 GB GPU	Qwen3.8 27B	Q4_K_M	32,768	Comfortable (19.9 GB of 24 GB)	`qwen3.8:27b`
	Qwen 3.6 27B	Q4_K_M	32,768	Comfortable (19.9 GB of 24 GB)	`qwen3.6:27b`
	Devstral Small 2 24B	Q4_K_M	32,768	Comfortable (20.7 GB of 24 GB)	`devstral-small-2:24b`
	Qwen 3.6 35B-A3B	Q4_K_M	65,536	Tight (23.3 GB of 24 GB)	`qwen3.6:35b-a3b`
32 GB GPU	Qwen3.8 27B	Q4_K_M	32,768	Comfortable (19.9 GB of 32 GB)	`qwen3.8:27b`
	Qwen 3.6 27B	Q4_K_M	32,768	Comfortable (19.9 GB of 32 GB)	`qwen3.6:27b`
	Devstral Small 2 24B	Q4_K_M	32,768	Comfortable (20.7 GB of 32 GB)	`devstral-small-2:24b`
	Qwen 3.6 35B-A3B	Q4_K_M	65,536	Comfortable (23.3 GB of 32 GB)	`qwen3.6:35b-a3b`
	Qwen3-Coder 30B-A3B (MoE)	Q4_K_M	65,536	Comfortable (25.7 GB of 32 GB)	`qwen3-coder:30b`
Mac, 64 GB	Qwen 3.6 35B-A3B	Q8_0	131,072	Comfortable (40.7 GB of 48 GB)	—

Your exact machine: filter the matrix or check any model in the analyzer.

Common problems with local models

The extension was shut down on 15 May 2026, and it receives no updates or fixes for new models or VS Code changes.
Roo uses native tool calling only, with no XML fallback, so a model without OpenAI-style tool calls cannot be used.
On a cold start Ollama may allocate a larger context than expected and run out of memory; pin num_ctx in a Modelfile or preload the model with ollama run.

Other coding agents

How they rank for local models: the best agent harness for local LLMs.

Sources (10), checked 2026-10-20