@blockrun/clawrouter 0.12.86 → 0.12.87
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +37 -10
- package/dist/cli.js +4213 -47
- package/dist/cli.js.map +1 -1
- package/dist/index.js +4210 -46
- package/dist/index.js.map +1 -1
- package/docs/11-free-ai-models-zero-cost-blockrun.md +28 -27
- package/package.json +4 -4
- package/skills/imagegen/SKILL.md +69 -35
- package/skills/predexon/SKILL.md +169 -0
package/README.md
CHANGED
|
@@ -92,6 +92,7 @@ Done. Smart routing (`blockrun/auto`) is now your default model.
|
|
|
92
92
|
No OpenClaw required. ClawRouter runs as a local proxy on port 8402.
|
|
93
93
|
|
|
94
94
|
**1. Start the proxy**
|
|
95
|
+
|
|
95
96
|
```bash
|
|
96
97
|
npx @blockrun/clawrouter
|
|
97
98
|
```
|
|
@@ -102,7 +103,29 @@ Your wallet address is printed on first run. Send a few USDC on Base or Solana
|
|
|
102
103
|
**3. Point your client at `http://localhost:8402`**
|
|
103
104
|
|
|
104
105
|
<details>
|
|
105
|
-
<summary><strong>continue.dev</strong> — <code>~/.continue/config.
|
|
106
|
+
<summary><strong>continue.dev</strong> — <code>~/.continue/config.yaml</code></summary>
|
|
107
|
+
|
|
108
|
+
> **Important:** `apiBase` must end with `/v1/` (including the trailing slash). Without it, continue.dev constructs the URL as `/chat/completions` instead of `/v1/chat/completions`, and the proxy returns 404.
|
|
109
|
+
|
|
110
|
+
```yaml
|
|
111
|
+
models:
|
|
112
|
+
- name: ClawRouter Auto
|
|
113
|
+
provider: openai
|
|
114
|
+
model: blockrun/auto
|
|
115
|
+
apiBase: http://localhost:8402/v1/
|
|
116
|
+
apiKey: x402
|
|
117
|
+
roles:
|
|
118
|
+
- chat
|
|
119
|
+
- edit
|
|
120
|
+
- apply
|
|
121
|
+
```
|
|
122
|
+
|
|
123
|
+
To pin a specific model, replace `blockrun/auto` with any model from [blockrun.ai/models](https://blockrun.ai/models), e.g. `anthropic/claude-opus-4.6`, `xai/grok-4-0709`.
|
|
124
|
+
|
|
125
|
+
Both `provider: openai` and `provider: clawrouter` work — just make sure `apiBase` ends with `/v1/`.
|
|
126
|
+
|
|
127
|
+
<details>
|
|
128
|
+
<summary>Legacy JSON format (<code>~/.continue/config.json</code>)</summary>
|
|
106
129
|
|
|
107
130
|
```json
|
|
108
131
|
{
|
|
@@ -111,18 +134,21 @@ Your wallet address is printed on first run. Send a few USDC on Base or Solana
|
|
|
111
134
|
"title": "ClawRouter Auto",
|
|
112
135
|
"provider": "openai",
|
|
113
136
|
"model": "blockrun/auto",
|
|
114
|
-
"apiBase": "http://localhost:8402",
|
|
137
|
+
"apiBase": "http://localhost:8402/v1/",
|
|
115
138
|
"apiKey": "x402"
|
|
116
139
|
}
|
|
117
140
|
]
|
|
118
141
|
}
|
|
119
142
|
```
|
|
143
|
+
|
|
144
|
+
</details>
|
|
120
145
|
</details>
|
|
121
146
|
|
|
122
147
|
<details>
|
|
123
148
|
<summary><strong>Cursor</strong> — Settings → Models → OpenAI-compatible</summary>
|
|
124
149
|
|
|
125
150
|
Set base URL to `http://localhost:8402`, API key to `x402`, model to `blockrun/auto`.
|
|
151
|
+
|
|
126
152
|
</details>
|
|
127
153
|
|
|
128
154
|
<details>
|
|
@@ -133,6 +159,7 @@ from openai import OpenAI
|
|
|
133
159
|
client = OpenAI(base_url="http://localhost:8402", api_key="x402")
|
|
134
160
|
response = client.chat.completions.create(model="blockrun/auto", messages=[...])
|
|
135
161
|
```
|
|
162
|
+
|
|
136
163
|
</details>
|
|
137
164
|
|
|
138
165
|
---
|
|
@@ -490,14 +517,14 @@ Run Claude Code with 50+ models, no rate limits, no Anthropic account, no phone
|
|
|
490
517
|
|
|
491
518
|
### Blog
|
|
492
519
|
|
|
493
|
-
| Article
|
|
494
|
-
|
|
|
495
|
-
| [11 Free AI Models, Zero Cost](docs/11-free-ai-models-zero-cost-blockrun.md)
|
|
496
|
-
| [ClawRouter Cuts LLM API Costs 500×](docs/clawrouter-cuts-llm-api-costs-500x.md)
|
|
497
|
-
| [ClawRouter vs OpenRouter](docs/clawrouter-vs-openrouter-llm-routing-comparison.md)
|
|
498
|
-
| [Smart LLM Router: 14-Dimension Classifier](docs/smart-llm-router-14-dimension-classifier.md)
|
|
499
|
-
| [LLM Router Benchmark: 46 Models, Sub-1ms](docs/llm-router-benchmark-46-models-sub-1ms-routing.md) | Performance benchmarks
|
|
500
|
-
| [Anthropic Cost Savings](docs/anthropic-cost-savings.md)
|
|
520
|
+
| Article | Topic |
|
|
521
|
+
| -------------------------------------------------------------------------------------------------- | ------------------------------------------------------- |
|
|
522
|
+
| [11 Free AI Models, Zero Cost](docs/11-free-ai-models-zero-cost-blockrun.md) | How BlockRun gives developers top-tier LLMs for nothing |
|
|
523
|
+
| [ClawRouter Cuts LLM API Costs 500×](docs/clawrouter-cuts-llm-api-costs-500x.md) | Deep dive into cost savings |
|
|
524
|
+
| [ClawRouter vs OpenRouter](docs/clawrouter-vs-openrouter-llm-routing-comparison.md) | Head-to-head comparison |
|
|
525
|
+
| [Smart LLM Router: 14-Dimension Classifier](docs/smart-llm-router-14-dimension-classifier.md) | How the routing engine works |
|
|
526
|
+
| [LLM Router Benchmark: 46 Models, Sub-1ms](docs/llm-router-benchmark-46-models-sub-1ms-routing.md) | Performance benchmarks |
|
|
527
|
+
| [Anthropic Cost Savings](docs/anthropic-cost-savings.md) | Reducing Claude API spend |
|
|
501
528
|
|
|
502
529
|
---
|
|
503
530
|
|