@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.
Files changed (2) hide show
  1. package/README.md +14 -11
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -1,7 +1,10 @@
1
- # LLxprt Code
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
  [![LLxprt Code CI](https://github.com/vybestack/llxprt-code/actions/workflows/ci.yml/badge.svg)](https://github.com/vybestack/llxprt-code/actions/workflows/ci.yml)
4
- &nbsp;[![Mentioned in Awesome Gemini CLI](https://awesome.re/mentioned-badge.svg)](https://github.com/Piebald-AI/awesome-gemini-cli)&nbsp;[![Discord Server](https://dcbadge.limes.pink/api/server/https://discord.gg/Wc6dZqWWYv?style=flat)](https://discord.gg/Wc6dZqWWYv)&nbsp;![CodeRabbit Pull Request Reviews](https://img.shields.io/coderabbit/prs/github/vybestack/llxprt-code?utm_source=oss&utm_medium=github&utm_campaign=vybestack%2Fllxprt-code&labelColor=171717&color=FF570A&link=https%3A%2F%2Fcoderabbit.ai&label=CodeRabbit+Reviews)
7
+ &nbsp;[![Discord Server](https://dcbadge.limes.pink/api/server/https://discord.gg/Wc6dZqWWYv?style=flat)](https://discord.gg/Wc6dZqWWYv)&nbsp;![CodeRabbit Pull Request Reviews](https://img.shields.io/coderabbit/prs/github/vybestack/llxprt-code?utm_source=oss&utm_medium=github&utm_campaign=vybestack%2Fllxprt-code&labelColor=171717&color=FF570A&link=https%3A%2F%2Fcoderabbit.ai&label=CodeRabbit+Reviews)
5
8
 
6
9
  ![LLxprt Code Screenshot](./docs/assets/llxprt-screenshot.png)
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-5, Kimi K 2.5, MiniMax M2.5, and Qwen 3.5 Next Coder
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-5, Kimi K2.5, MiniMax M2.5, Qwen 3.5 Next Coder
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 Thinking
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-k2-thinking
153
+ /model kimi-for-coding
151
154
  # Or via Synthetic/Chutes:
152
155
  /provider synthetic
153
- /model hf:moonshotai/Kimi-K2-Thinking
156
+ /model hf:moonshotai/Kimi-K2.5
154
157
  ```
155
158
 
156
- ### GLM-4.7
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 M2.1
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
- ### Qwen3 Coder 480B
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-5 vs Custom)
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)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@vybestack/llxprt-code-core",
3
- "version": "0.9.0",
3
+ "version": "0.10.0-nightly.260304.84decda38",
4
4
  "description": "LLxprt Code Core",
5
5
  "license": "Apache-2.0",
6
6
  "repository": {