@vybestack/llxprt-code-core 0.9.0 → 0.10.0-nightly.260304.84decda38
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 +14 -11
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -1,7 +1,10 @@
|
|
|
1
|
-
|
|
1
|
+
<h1>
|
|
2
|
+
<img src="docs/assets/llxprt.svg" alt="LLxprt logo" width="42" />
|
|
3
|
+
<a href="https://vybestack.dev/llxprt-code.html">LLxprt Code</a>
|
|
4
|
+
</h1>
|
|
2
5
|
|
|
3
6
|
[](https://github.com/vybestack/llxprt-code/actions/workflows/ci.yml)
|
|
4
|
-
[](https://discord.gg/Wc6dZqWWYv) 
|
|
5
8
|
|
|
6
9
|

|
|
7
10
|
|
|
@@ -45,7 +48,7 @@ Get started immediately with powerful LLM options:
|
|
|
45
48
|
- **Load Balancer Profiles**: Balance requests across providers or accounts with automatic failover
|
|
46
49
|
- **Free Tier Support**: Start coding immediately with Gemini or Qwen free tiers
|
|
47
50
|
- **Provider Flexibility**: Switch between any Anthropic, Gemini, OpenAI, Kimi, or OpenAI-compatible provider
|
|
48
|
-
- **Top Open Models**: Works seamlessly with GLM
|
|
51
|
+
- **Top Open Models**: Works seamlessly with GLM 5, Kimi K2.5, MiniMax M2.5, and Qwen 3 Coder Next
|
|
49
52
|
- **Local Models**: Run models locally with LM Studio, llama.cpp for complete privacy
|
|
50
53
|
- **Privacy First**: No telemetry by default, local processing available
|
|
51
54
|
- **Subagent Flexibility**: Create agents with different models, providers, or settings
|
|
@@ -103,7 +106,7 @@ llxprt
|
|
|
103
106
|
- **Multi-Account Failover** - Configure multiple OAuth buckets that failover automatically on rate limits
|
|
104
107
|
- **Load Balancer Profiles** - Balance across providers/accounts with roundrobin or failover policies
|
|
105
108
|
- **Extensive Provider Support** - Anthropic, Gemini, OpenAI, Kimi, and any OpenAI-compatible provider [**Provider Guide →**](./docs/providers/quick-reference.md)
|
|
106
|
-
- **Top Open Models** - GLM
|
|
109
|
+
- **Top Open Models** - GLM 5, Kimi K2.5, MiniMax M2.5, Qwen 3 Coder Next
|
|
107
110
|
- **Local Model Support** - LM Studio, llama.cpp, Ollama for complete privacy
|
|
108
111
|
- **Profile System** - Save provider configurations and model settings
|
|
109
112
|
- **Advanced Subagents** - Isolated AI assistants with different models/providers
|
|
@@ -138,7 +141,7 @@ llxprt "Generate unit tests for payment module" > tests/payment.test.js
|
|
|
138
141
|
|
|
139
142
|
LLxprt Code works seamlessly with the best open-weight models:
|
|
140
143
|
|
|
141
|
-
### Kimi K2
|
|
144
|
+
### Kimi K2.5
|
|
142
145
|
|
|
143
146
|
- **Context Window**: 262,144 tokens
|
|
144
147
|
- **Architecture**: Trillion-parameter MoE (32B active)
|
|
@@ -147,27 +150,27 @@ LLxprt Code works seamlessly with the best open-weight models:
|
|
|
147
150
|
|
|
148
151
|
```bash
|
|
149
152
|
/provider kimi
|
|
150
|
-
/model kimi-
|
|
153
|
+
/model kimi-for-coding
|
|
151
154
|
# Or via Synthetic/Chutes:
|
|
152
155
|
/provider synthetic
|
|
153
|
-
/model hf:moonshotai/Kimi-K2
|
|
156
|
+
/model hf:moonshotai/Kimi-K2.5
|
|
154
157
|
```
|
|
155
158
|
|
|
156
|
-
### GLM
|
|
159
|
+
### GLM 5
|
|
157
160
|
|
|
158
161
|
- **Context Window**: 200,000 tokens
|
|
159
162
|
- **Max Output**: 131,072 tokens
|
|
160
163
|
- **Architecture**: Mixture-of-Experts with 355B total parameters (32B active)
|
|
161
164
|
- **Strengths**: Coding, multi-step planning, tool integration
|
|
162
165
|
|
|
163
|
-
### MiniMax M2.
|
|
166
|
+
### MiniMax M2.5
|
|
164
167
|
|
|
165
168
|
- **Context Window**: 196,608 tokens
|
|
166
169
|
- **Architecture**: MoE with 230B total parameters (10B active)
|
|
167
170
|
- **Strengths**: Coding workflows, multi-step agents, tool calling
|
|
168
171
|
- **Cost**: Only 8% of Claude Sonnet, ~2x faster
|
|
169
172
|
|
|
170
|
-
###
|
|
173
|
+
### Qwen 3 Coder Next
|
|
171
174
|
|
|
172
175
|
- **Context Window**: 262,144 tokens
|
|
173
176
|
- **Max Output**: 65,536 tokens
|
|
@@ -211,7 +214,7 @@ Create specialized AI assistants with isolated contexts and different configurat
|
|
|
211
214
|
Each subagent can be configured with:
|
|
212
215
|
|
|
213
216
|
- **Different providers** (Gemini vs Anthropic vs Qwen vs Local)
|
|
214
|
-
- **Different models** (Flash vs Sonnet vs GLM
|
|
217
|
+
- **Different models** (Flash vs Sonnet vs GLM 5 vs Custom)
|
|
215
218
|
- **Different tool access** (Restrict or allow specific tools)
|
|
216
219
|
- **Different settings** (Temperature, timeouts, max turns)
|
|
217
220
|
- **Isolated runtime context** (No memory or state crossover)
|