Skip to content

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

feat(providers): add NEAR AI Cloud

release-verification2116832bf58c
diff --git a/docs/providers-and-models.md b/docs/providers-and-models.md
index 62552ae01..595946baf 100644
--- a/docs/providers-and-models.md
+++ b/docs/providers-and-models.md
@@ -70,18 +70,18 @@ class BaseLLMProvider {
### Extended provider catalog
-WebBrain also ships 78 disabled-by-default provider cards. Most are sourced
+WebBrain also ships 79 disabled-by-default provider cards. Most are sourced
from the OpenCode provider catalog snapshot at commit
`62e4641235d7847dadc60da37cca8a023dd54fc1`; provider-specific additions use
their official API documentation. Together with the original cards, Settings
-contains **109 built-in providers on Chromium** and **108 on Firefox**; the
+contains **110 built-in providers on Chromium** and **109 on Firefox**; the
difference is the Chromium-only in-browser WebGPU runtime.
| IDs |
|---|
| `302ai`, `abacus`, `aihubmix`, `alibaba-coding-plan`, `alibaba-coding-plan-cn`, `azure-cognitive-services`, `bailing`, `baseten`, `berget`, `cerebras`, `chutes`, `clarifai`, `cloudferro-sherlock`, `cohere`, `cortecs`, `deepinfra`, `digitalocean`, `dinference`, `drun`, `evroc`, `fastrouter`, `friendli` |
| `google-vertex`, `google-vertex-anthropic`, `helicone`, `iflowcn`, `inception`, `inference`, `io-net`, `jiekou`, `kilo`, `kimi-for-coding`, `kuae-cloud-coding-plan`, `llama`, `lucidquery`, `meganova`, `minimax-cn-coding-plan`, `minimax-coding-plan`, `moark`, `modelscope`, `morph` |
-| `nano-gpt`, `nebius`, `nova`, `novita-ai`, `ollama-cloud`, `opencode`, `opencode-go`, `orcarouter`, `ovhcloud`, `perplexity`, `perplexity-agent`, `poe`, `pollinations`, `privatemode-ai`, `qihang-ai`, `qiniu-ai`, `requesty`, `scaleway`, `siliconflow`, `siliconflow-cn`, `stackit` |
+| `nano-gpt`, `nearai`, `nebius`, `nova`, `novita-ai`, `ollama-cloud`, `opencode`, `opencode-go`, `orcarouter`, `ovhcloud`, `perplexity`, `perplexity-agent`, `poe`, `pollinations`, `privatemode-ai`, `qihang-ai`, `qiniu-ai`, `requesty`, `scaleway`, `siliconflow`, `siliconflow-cn`, `stackit` |
| `stepfun`, `submodel`, `synthetic`, `tencent-coding-plan`, `upstage`, `v0`, `venice`, `vercel`, `vivgrid`, `vultr`, `wandb`, `xiaomi`, `zai-coding-plan`, `zenmux`, `zhipuai`, `zhipuai-coding-plan` |
Most use the OpenAI-compatible Chat Completions contract and bearer API keys.
@@ -99,6 +99,26 @@ Morph and standard Perplexity Sonar are text-only integrations in the agent
and advertise `supportsTools: false`. New provider cards remain inactive until
the user saves their credentials and selects the provider.
+#### NEAR AI Cloud
+
+[NEAR AI Cloud](https://cloud.near.ai/) exposes an OpenAI-compatible API at
+`https://cloud-api.near.ai/v1`. TEE-hosted models (such as `z-ai/glm-5.3-flash`)
+run inside Trusted Execution Environments so prompts and outputs stay private
+and verifiable; third-party models proxied through the same gateway use the
+same API and billing but do not inherit the TEE privacy guarantees. See the
+[quickstart](https://docs.near.ai/cloud/quickstart),
+[models](https://docs.near.ai/cloud/models), and
+[OpenAI compatibility](https://docs.near.ai/cloud/guides/openai-compatibility)
+guides.
+
+In WebBrain, open **Settings -> Providers -> NEAR AI Cloud**. Generate an API
+key from the [NEAR AI Cloud dashboard](https://cloud.near.ai/), paste it into
+the card, keep the default `z-ai/glm-5.3-flash` model, then click **Test
+Connection**. If selecting a model with a smaller context window, such as
+`Qwen/Qwen3.8-27B` (262144 tokens), set **Context window** to its documented
+limit. Interactive Ask streaming, tool calls, and vision work through the
+existing OpenAI-compatible path.
+
### Ask response streaming
Providers with `supportsAskStreaming` stream visible text during interactive
diff --git a/src/chrome/icons/providers/SOURCES.md b/src/chrome/icons/providers/SOURCES.md
index 032c3fcb7..c54fdfa65 100644
--- a/src/chrome/icons/providers/SOURCES.md
+++ b/src/chrome/icons/providers/SOURCES.md
@@ -16,5 +16,6 @@ Most brand marks come from [Lobe Icons](https://github.com/lobehub/lobe-icons)
| webbrain_cloud | WebBrain extension icon |
| 302ai, abacus, aihubmix, alibaba-coding-plan, alibaba-coding-plan-cn, azure-cognitive-services, bailing, baseten, berget, cerebras, chutes, clarifai, cloudferro-sherlock, cohere, cortecs, deepinfra, digitalocean, dinference, drun, evroc, fastrouter, friendli, google-vertex, google-vertex-anthropic, helicone, iflowcn, inception, inference, io-net, jiekou, kilo, kimi-for-coding, kuae-cloud-coding-plan, llama, lucidquery, meganova, minimax-cn-coding-plan, minimax-coding-plan, moark, modelscope, morph, nano-gpt, nebius, nova, novita-ai, ollama-cloud, opencode, opencode-go, ovhcloud, perplexity, perplexity-agent, poe, privatemode-ai, qihang-ai, qiniu-ai, requesty, scaleway, siliconflow, siliconflow-cn, stackit, stepfun, submodel, synthetic, tencent-coding-plan, upstage, v0, venice, vercel, vivgrid, vultr, wandb, xiaomi, zai-coding-plan, zenmux, zhipuai, zhipuai-coding-plan | OpenCode provider icon set at commit `62e4641235d7847dadc60da37cca8a023dd54fc1` (MIT); DInference SVG normalized with a `viewBox` |
| orcarouter | OrcaRouter official docs favicon (`Continuum-AI-Corp/docs`, MIT) |
+| nearai | WebBrain-authored simple N mark (not an official NEAR brand asset) |
Brand trademarks remain property of their owners; used only for provider identification in the settings UI.
diff --git a/src/chrome/icons/providers/nearai.svg b/src/chrome/icons/providers/nearai.svg
new file mode 100644
index 000000000..f69388bf8
--- /dev/null
+++ b/src/chrome/icons/providers/nearai.svg
@@ -0,0 +1 @@
+<svg width="24" height="24" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>NEAR AI Cloud</title><path fill="currentColor" d="M5 4h3.4l7.1 10.2V4H19v16h-3.4L8.5 9.8V20H5z"/></svg>
diff --git a/src/chrome/src/providers/provider-catalog.js b/src/chrome/src/providers/provider-catalog.js
index 371f6f485..504da7833 100644
--- a/src/chrome/src/providers/provider-catalog.js
+++ b/src/chrome/src/providers/provider-catalog.js
@@ -102,6 +102,7 @@ const PROVIDERS = [
provider('modelscope', 'ModelScope', 'https://api-inference.modelscope.cn/v1', 'Qwen/Qwen3.8-27B', 262144, { apiKeyUrl: 'https://modelscope.cn/docs/model-service/API-Inference/intro', supportsVision: true }),
provider('morph', 'Morph', 'https://api.morphllm.com/v1', 'morph-v3-fast', 16000, { category: 'cloud', apiKeyUrl: 'https://docs.morphllm.com/api-reference/introduction', supportsTools: false, inputCostPerMillionUsd: 0.8, outputCostPerMillionUsd: 1.2 }),
provider('nano-gpt', 'NanoGPT', 'https://nano-gpt.com/api/v1', 'claude-opus-4-thinking:8192', 200000, { apiKeyUrl: 'https://docs.nano-gpt.com', supportsVision: true, inputCostPerMillionUsd: 14.994, outputCostPerMillionUsd: 75.004 }),
+ provider('nearai', 'NEAR AI Cloud', 'https://cloud-api.near.ai/v1', 'z-ai/glm-5.3-flash', 1048576, { apiKeyUrl: 'https://cloud.near.ai/', supportsVision: true, inputCostPerMillionUsd: 0.15, cacheReadCostPerMillionUsd: 0.035, outputCostPerMillionUsd: 0.5, suggestions: ['z-ai/glm-5.3-flash', 'Qwen/Qwen3.8-27B'] }),
provider('nebius', 'Nebius Token Factory', 'https://api.tokenfactory.nebius.com/v1', 'meta-llama/Llama-3.3-70B-Instruct', 128000, { apiKeyUrl: 'https://docs.tokenfactory.nebius.com/', inputCostPerMillionUsd: 0.13, cacheReadCostPerMillionUsd: 0.013, cacheWriteCostPerMillionUsd: 0.16, outputCostPerMillionUsd: 0.4 }),
provider('nova', 'Amazon Nova', 'https://api.nova.amazon.com/v1', 'nova-2-pro-v1', 1000000, { category: 'cloud', apiKeyUrl: 'https://nova.amazon.com/dev/documentation', supportsVision: true }),
provider('novita-ai', 'NovitaAI', 'https://api.novita.ai/openai', 'inclusionai/ling-2.6-1t', 262144, { apiKeyUrl: 'https://novita.ai/docs/guides/introduction', inputCostPerMillionUsd: 0.3, cacheReadCostPerMillionUsd: 0.06, outputCostPerMillionUsd: 2.5 }),
diff --git a/src/firefox/icons/providers/SOURCES.md b/src/firefox/icons/providers/SOURCES.md
index 24a877d58..5af534379 100644
--- a/src/firefox/icons/providers/SOURCES.md
+++ b/src/firefox/icons/providers/SOURCES.md
@@ -16,5 +16,6 @@ Most brand marks come from [Lobe Icons](https://github.com/lobehub/lobe-icons)
| webbrain_cloud | WebBrain extension icon |
| 302ai, abacus, aihubmix, alibaba-coding-plan, alibaba-coding-plan-cn, azure-cognitive-services, bailing, baseten, berget, cerebras, chutes, clarifai, cloudferro-sherlock, cohere, cortecs, deepinfra, digitalocean, dinference, drun, evroc, fastrouter, friendli, google-vertex, google-vertex-anthropic, helicone, iflowcn, inception, inference, io-net, jiekou, kilo, kimi-for-coding, kuae-cloud-coding-plan, llama, lucidquery, meganova, minimax-cn-coding-plan, minimax-coding-plan, moark, modelscope, morph, nano-gpt, nebius, nova, novita-ai, ollama-cloud, opencode, opencode-go, ovhcloud, perplexity, perplexity-agent, poe, privatemode-ai, qihang-ai, qiniu-ai, requesty, scaleway, siliconflow, siliconflow-cn, stackit, stepfun, submodel, synthetic, tencent-coding-plan, upstage, v0, venice, vercel, vivgrid, vultr, wandb, xiaomi, zai-coding-plan, zenmux, zhipuai, zhipuai-coding-plan | OpenCode provider icon set at commit `62e4641235d7847dadc60da37cca8a023dd54fc1` (MIT); DInference SVG normalized with a `viewBox` |
| orcarouter | OrcaRouter official docs favicon (`Continuum-AI-Corp/docs`, MIT) |
+| nearai | WebBrain-authored simple N mark (not an official NEAR brand asset) |
Brand trademarks remain property of their owners; used only for provider identification in the settings UI.
diff --git a/src/firefox/icons/providers/nearai.svg b/src/firefox/icons/providers/nearai.svg
new file mode 100644
index 000000000..f69388bf8
--- /dev/null
+++ b/src/firefox/icons/providers/nearai.svg
@@ -0,0 +1 @@
+<svg width="24" height="24" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>NEAR AI Cloud</title><path fill="currentColor" d="M5 4h3.4l7.1 10.2V4H19v16h-3.4L8.5 9.8V20H5z"/></svg>
diff --git a/src/firefox/src/providers/provider-catalog.js b/src/firefox/src/providers/provider-catalog.js
index 371f6f485..504da7833 100644
--- a/src/firefox/src/providers/provider-catalog.js
+++ b/src/firefox/src/providers/provider-catalog.js
@@ -102,6 +102,7 @@ const PROVIDERS = [
provider('modelscope', 'ModelScope', 'https://api-inference.modelscope.cn/v1', 'Qwen/Qwen3.8-27B', 262144, { apiKeyUrl: 'https://modelscope.cn/docs/model-service/API-Inference/intro', supportsVision: true }),
provider('morph', 'Morph', 'https://api.morphllm.com/v1', 'morph-v3-fast', 16000, { category: 'cloud', apiKeyUrl: 'https://docs.morphllm.com/api-reference/introduction', supportsTools: false, inputCostPerMillionUsd: 0.8, outputCostPerMillionUsd: 1.2 }),
provider('nano-gpt', 'NanoGPT', 'https://nano-gpt.com/api/v1', 'claude-opus-4-thinking:8192', 200000, { apiKeyUrl: 'https://docs.nano-gpt.com', supportsVision: true, inputCostPerMillionUsd: 14.994, outputCostPerMillionUsd: 75.004 }),
+ provider('nearai', 'NEAR AI Cloud', 'https://cloud-api.near.ai/v1', 'z-ai/glm-5.3-flash', 1048576, { apiKeyUrl: 'https://cloud.near.ai/', supportsVision: true, inputCostPerMillionUsd: 0.15, cacheReadCostPerMillionUsd: 0.035, outputCostPerMillionUsd: 0.5, suggestions: ['z-ai/glm-5.3-flash', 'Qwen/Qwen3.8-27B'] }),
provider('nebius', 'Nebius Token Factory', 'https://api.tokenfactory.nebius.com/v1', 'meta-llama/Llama-3.3-70B-Instruct', 128000, { apiKeyUrl: 'https://docs.tokenfactory.nebius.com/', inputCostPerMillionUsd: 0.13, cacheReadCostPerMillionUsd: 0.013, cacheWriteCostPerMillionUsd: 0.16, outputCostPerMillionUsd: 0.4 }),
provider('nova', 'Amazon Nova', 'https://api.nova.amazon.com/v1', 'nova-2-pro-v1', 1000000, { category: 'cloud', apiKeyUrl: 'https://nova.amazon.com/dev/documentation', supportsVision: true }),
provider('novita-ai', 'NovitaAI', 'https://api.novita.ai/openai', 'inclusionai/ling-2.6-1t', 262144, { apiKeyUrl: 'https://novita.ai/docs/guides/introduction', inputCostPerMillionUsd: 0.3, cacheReadCostPerMillionUsd: 0.06, outputCostPerMillionUsd: 2.5 }),
diff --git a/test/run.js b/test/run.js
index f2c3fe4e7..5e07ea558 100644
--- a/test/run.js
+++ b/test/run.js
@@ -68823,7 +68823,7 @@ test('extended provider catalog is complete, mirrored, safe, and excluded-provid
evroc fastrouter friendli google-vertex google-vertex-anthropic helicone
iflowcn inception inference io-net jiekou kilo kimi-for-coding
kuae-cloud-coding-plan llama lucidquery meganova minimax-cn-coding-plan
- minimax-coding-plan moark modelscope morph nano-gpt nebius nova novita-ai
+ minimax-coding-plan moark modelscope morph nano-gpt nearai nebius nova novita-ai
ollama-cloud opencode opencode-go orcarouter ovhcloud perplexity
perplexity-agent poe pollinations privatemode-ai qihang-ai qiniu-ai requesty scaleway siliconflow
siliconflow-cn stackit stepfun submodel synthetic tencent-coding-plan
@@ -68832,7 +68832,7 @@ test('extended provider catalog is complete, mirrored, safe, and excluded-provid
`.trim().split(/\s+/);
const excluded = ['github-models', 'github-copilot', 'gitlab', 'sap-ai-core'];
- assert.equal(expectedIds.length, 78);
+ assert.equal(expectedIds.length, 79);
assert.deepEqual(ProviderCatalogCh.ADDITIONAL_PROVIDER_IDS, expectedIds);
assert.deepEqual(ProviderCatalogFx.ADDITIONAL_PROVIDER_IDS, expectedIds);
assert.deepEqual(
@@ -68846,7 +68846,7 @@ test('extended provider catalog is complete, mirrored, safe, and excluded-provid
['firefox', ProviderManagerFx, 'src/firefox'],
]) {
const defaults = new PM()._defaultConfigs();
- const expectedDefaultCount = label === 'chrome' ? 109 : 108;
+ const expectedDefaultCount = label === 'chrome' ? 110 : 109;
assert.equal(
Object.keys(defaults).length,
expectedDefaultCount,
@@ -68945,6 +68945,30 @@ test('extended provider catalog is complete, mirrored, safe, and excluded-provid
apiKeyUrl: 'https://www.orcarouter.ai/console',
},
);
+ assert.deepEqual(
+ {
+ baseUrl: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.nearai.baseUrl,
+ model: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.nearai.model,
+ contextWindow: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.nearai.contextWindow,
+ supportsVision: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.nearai.supportsVision,
+ supportsTools: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.nearai.supportsTools,
+ supportsAskStreaming: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.nearai.supportsAskStreaming,
+ apiKeyUrl: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.nearai.apiKeyUrl,
+ },
+ {
+ baseUrl: 'https://cloud-api.near.ai/v1',
+ model: 'z-ai/glm-5.3-flash',
+ contextWindow: 1048576,
+ supportsVision: true,
+ supportsTools: true,
+ supportsAskStreaming: true,
+ apiKeyUrl: 'https://cloud.near.ai/',
+ },
+ );
+ assert.deepEqual(
+ ProviderCatalogCh.ADDITIONAL_PROVIDER_UI.nearai.suggestions,
+ ['z-ai/glm-5.3-flash', 'Qwen/Qwen3.8-27B'],
+ );
assert.deepEqual(
ProviderCatalogCh.ADDITIONAL_PROVIDER_UI['kimi-for-coding'].suggestions,
['kimi-for-coding', 'kimi-for-coding-highspeed', 'k3'],