lmstudio-cli

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

LM Studio CLI

Use this skill when the real job is operating LM Studio itself: confirming whether

lms

exists, checking whether a local or remote LM Studio server is actually running, discovering exact model IDs, deciding whether the OpenAI-compatible endpoints are enough, and wiring a downstream tool to the correct base URL and model identifier.

Do not use this as a generic local-LLM comparison skill. Route broad provider comparison or platform selection to research/survey work. Route downstream-tool-specific scanning or appsec operation to that tool's skill (for example

strix

) once LM Studio itself is verified.

当实际任务是操作LM Studio本身时使用此技能：确认

lms

是否存在、检查本地或远程LM Studio服务器是否实际运行、查找确切的模型ID、判断OpenAI兼容端点是否足够，以及将下游工具连接到正确的基础URL和模型标识符。

请勿将此作为通用本地大模型（LLM）对比技能。将宽泛的服务商对比或平台选择需求引导至调研/调查工作。在确认LM Studio本身可用后，将下游工具特定的扫描或应用安全操作引导至对应工具的技能（例如

strix

）。

When to use this skill

何时使用此技能

A user mentions LM Studio,
```
lms
```
, or an LM Studio server directly
You need to verify whether LM Studio is running locally or on another authorized host
You need the exact model IDs returned by
```
/v1/models
```
before wiring another tool
You need to choose between LM Studio's OpenAI-compatible endpoints and its native REST API
You need to load, inspect, or confirm models before an agent or CLI can use them
A downstream tool works with OpenAI-compatible endpoints, but the user needs LM Studio-specific setup help
A remote/headless LM Studio workflow is failing and you need a deterministic verification path

用户直接提及LM Studio、
```
lms
```
或LM Studio服务器
需要验证LM Studio是在本地运行还是在其他授权主机上运行
在连接其他工具前，需要获取
```
/v1/models
```
返回的确切模型ID
需要在LM Studio的OpenAI兼容端点与其原生REST API之间做出选择
需要在代理（Agent）或CLI使用模型前，加载、检查或确认模型
下游工具可与OpenAI兼容端点配合使用，但用户需要LM Studio特定的设置帮助
远程/无界面LM Studio工作流失败，需要确定性的验证路径

Instructions

操作说明

Step 1: Identify the operating mode

步骤1：确定运行模式

Classify the request before touching commands:

Local native CLI mode — the machine should have LM Studio installed and
```
lms
```
available
Remote HTTP mode — you only need to test or consume an authorized LM Studio endpoint
LM Studio-native management mode — the user needs model loading / listing / unload behavior that goes beyond generic OpenAI-compatible calls
Downstream wiring mode — the user already has LM Studio running and needs to point another tool at it

Use the smallest mode that answers the request.

在执行命令前先对请求进行分类：

本地原生CLI模式 — 机器应已安装LM Studio且
```
lms
```
可用
远程HTTP模式 — 仅需测试或使用授权的LM Studio端点
LM Studio原生管理模式 — 用户需要模型加载/列出/卸载操作，这些操作超出了通用OpenAI兼容调用的范围
下游配置模式 — 用户已启动LM Studio，需要将其他工具指向它

使用能满足请求的最小模式。

Step 2: Check whether local

lms

exists

步骤2：检查本地

lms

是否存在

If local CLI operation is expected, verify it first:

bash

command -v lms
lms --help

lms

is missing, do not hallucinate local CLI output. Continue with remote HTTP verification only if the host/endpoint is explicitly authorized.

如果需要本地CLI操作，先进行验证：

bash

command -v lms
lms --help

如果

lms

不存在，请勿虚构本地CLI输出。仅当主机/端点已明确授权时，才继续进行远程HTTP验证。

Step 3: Verify server status or endpoint reachability

步骤3：验证服务器状态或端点可达性

For local native checks:

bash

lms server status
lms server status --json --quiet

For a remote or client-style smoke test:

bash

curl -fsS http://HOST:PORT/v1/models

Optional minimal response test:

bash

curl -fsS http://HOST:PORT/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "MODEL_ID",
    "messages": [{"role": "user", "content": "reply with exactly OK"}],
    "temperature": 0,
    "max_tokens": 8
  }'

If you want a reusable parser instead of copy-pasting curl, use

python3 scripts/check_lmstudio_endpoint.py --base-url http://HOST:PORT/v1

对于本地原生检查：

bash

lms server status
lms server status --json --quiet

对于远程或客户端式冒烟测试：

bash

curl -fsS http://HOST:PORT/v1/models

可选的最小响应测试：

bash

curl -fsS http://HOST:PORT/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "MODEL_ID",
    "messages": [{"role": "user", "content": "reply with exactly OK"}],
    "temperature": 0,
    "max_tokens": 8
  }'

如果需要可复用的解析器而非复制粘贴curl命令，使用

python3 scripts/check_lmstudio_endpoint.py --base-url http://HOST:PORT/v1

。

Step 4: Discover exact model identifiers

步骤4：查找确切的模型标识符

Do not guess model names.

Use one of these:

bash

lms ls
lms ls --llm
lms ps --json
curl -fsS http://HOST:PORT/v1/models

If the user needs the exact loaded instance or runtime state, prefer

lms ps

or the native REST API over a generic downstream client view.

请勿猜测模型名称。

使用以下方式之一：

bash

lms ls
lms ls --llm
lms ps --json
curl -fsS http://HOST:PORT/v1/models

如果用户需要确切的已加载实例或运行时状态，优先使用

lms ps

或原生REST API，而非通用下游客户端视图。

Step 5: Escalate to LM Studio-native management only when needed

步骤5：仅在必要时升级到LM Studio原生管理

Use the native REST API or LM Studio-native commands when OpenAI compatibility is not enough:

bash

curl -fsS http://HOST:PORT/api/v1/models
curl -fsS http://HOST:PORT/api/v1/models/load \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "MODEL_KEY",
    "context_length": 262144,
    "echo_load_config": true
  }'

And locally:

bash

lms load MODEL_KEY --identifier my-model
lms ps --json

Use this path for context-length, load-state, or instance-specific questions. Do not treat every integration problem as a native-management problem if

/v1/models

and

/v1/chat/completions

already answer the user's need.

当OpenAI兼容性不足以满足需求时，使用原生REST API或LM Studio原生命令：

bash

curl -fsS http://HOST:PORT/api/v1/models
curl -fsS http://HOST:PORT/api/v1/models/load \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "MODEL_KEY",
    "context_length": 262144,
    "echo_load_config": true
  }'

本地操作：

bash

lms load MODEL_KEY --identifier my-model
lms ps --json

此路径适用于上下文长度、加载状态或实例特定问题。如果

/v1/models

和

/v1/chat/completions

已能满足用户需求，请勿将每个集成问题都视为原生管理问题。

Step 6: Wire downstream tools carefully

步骤6：谨慎配置下游工具

For tools that expect an OpenAI-compatible server, pass the exact model ID and base URL:

bash

export LLM_API_BASE="http://HOST:PORT/v1"
export STRIX_LLM="openai/MODEL_ID"

Some OpenAI-compatible clients still insist on an API key field even when LM Studio itself does not need a real provider key. When that happens, set the client-required dummy key only in the downstream tool's config, not as a claim about LM Studio authentication.

对于需要OpenAI兼容服务器的工具，传入确切的模型ID和基础URL：

bash

export LLM_API_BASE="http://HOST:PORT/v1"
export STRIX_LLM="openai/MODEL_ID"

部分OpenAI兼容客户端即使LM Studio本身不需要真实的服务商密钥，仍会要求填写API密钥字段。此时，仅在下游工具的配置中设置客户端所需的虚拟密钥，而非将其作为LM Studio的认证要求。

Step 7: Report the operating facts, not guesses

步骤7：报告实际情况，而非猜测

A good final report should include:

whether
```
lms
```
was present locally
whether the server was verified locally, remotely, or both
exact base URL tested
exact model IDs discovered
whether the user needed OpenAI-compatible calls only or LM Studio-native management
the final env/config snippet or command needed by the downstream tool

一份优质的最终报告应包含：

本地是否存在
```
lms
```
服务器是在本地、远程还是两者都已验证
测试的确切基础URL
发现的确切模型ID
用户仅需OpenAI兼容调用还是需要LM Studio原生管理
下游工具所需的最终环境变量/配置片段或命令

Examples

示例

Example 1: Local machine with LM Studio installed

示例1：已安装LM Studio的本地机器

User asks: "Is

lms

installed and what model is loaded?"

Recommended flow:

bash

command -v lms
lms server status --json --quiet
lms ps --json

用户提问：“

lms

是否已安装，当前加载了什么模型？”

推荐流程：

bash

command -v lms
lms server status --json --quiet
lms ps --json

Example 2: Remote LM Studio host for another tool

示例2：为其他工具使用的远程LM Studio主机

User asks: "Point Strix at my LM Studio box."

Recommended flow:

bash

curl -fsS http://HOST:PORT/v1/models
python3 scripts/check_lmstudio_endpoint.py --base-url http://HOST:PORT/v1
export STRIX_LLM="openai/MODEL_ID"
export LLM_API_BASE="http://HOST:PORT/v1"

用户提问：“将Strix指向我的LM Studio主机。”

推荐流程：

bash

curl -fsS http://HOST:PORT/v1/models
python3 scripts/check_lmstudio_endpoint.py --base-url http://HOST:PORT/v1
export STRIX_LLM="openai/MODEL_ID"
export LLM_API_BASE="http://HOST:PORT/v1"

Example 3: Need more than OpenAI-compatible smoke tests

示例3：需要超出OpenAI兼容冒烟测试的功能

User asks: "Load the model with a bigger context length and tell me the effective settings."

Recommended flow:

bash

curl -fsS http://HOST:PORT/api/v1/models
curl -fsS http://HOST:PORT/api/v1/models/load \
  -H 'Content-Type: application/json' \
  -d '{"model":"MODEL_KEY","context_length":262144,"echo_load_config":true}'

用户提问：“加载更大上下文长度的模型，并告诉我实际设置。”

推荐流程：

bash

curl -fsS http://HOST:PORT/api/v1/models
curl -fsS http://HOST:PORT/api/v1/models/load \
  -H 'Content-Type: application/json' \
  -d '{"model":"MODEL_KEY","context_length":262144,"echo_load_config":true}'

Example 4: Headless failure triage

示例4：无界面故障排查

User asks: "

lms server start

broke on my Linux VM. What should I check first?"

Recommended flow:

verify
```
lms --help
```
run
```
lms server status --json --quiet
```
rerun with verbose logging if needed
separate local daemon/server failure from downstream OpenAI-client failure before editing configs

用户提问：“我的Linux虚拟机上

lms server start

运行失败，首先应该检查什么？”

推荐流程：

验证
```
lms --help
```
运行
```
lms server status --json --quiet
```
如有需要，启用详细日志重新运行
在修改配置前，区分本地守护进程/服务器故障与下游OpenAI客户端故障

Best practices

最佳实践

Separate local CLI availability from remote HTTP reachability; they are related but not the same fact.
Use the exact model IDs returned by LM Studio instead of shortening names by hand.
Prefer the OpenAI-compatible endpoints for downstream-tool wiring, and the native REST/CLI surfaces for model-management questions.
When a downstream client insists on an API key field, describe it as a client compatibility quirk rather than an LM Studio requirement.
Treat remote private-network hosts as sensitive; only probe endpoints the user has authorized.
Escalate to load-state or context-length guidance only when the simpler
```
/v1/models
```
path is not enough.
Keep the boundary clear:
```
lmstudio-cli
```
verifies and configures LM Studio itself; downstream-tool skills own what happens after the endpoint is working.

区分本地CLI可用性与远程HTTP可达性；它们相关但并非同一事实。
使用LM Studio返回的确切模型ID，而非手动缩短名称。
配置下游工具时优先使用OpenAI兼容端点，处理模型管理问题时优先使用原生REST/CLI界面。
当下游客户端要求填写API密钥字段时，将其描述为客户端兼容性问题，而非LM Studio的要求。
将远程私有网络主机视为敏感内容；仅探测用户已授权的端点。
仅当更简单的
```
/v1/models
```
路径无法满足需求时，才提供加载状态或上下文长度相关指导。
明确边界：
```
lmstudio-cli
```
用于验证和配置LM Studio本身；下游工具技能负责端点可用后的操作。

References

参考资料

references/cli-and-server-basics.md
references/endpoints-and-escalation.md
references/downstream-tool-wiring.md
scripts/check_lmstudio_endpoint.py
LM Studio CLI docs
LM Studio OpenAI compatibility docs
LM Studio REST API docs

references/cli-and-server-basics.md
references/endpoints-and-escalation.md
references/downstream-tool-wiring.md
scripts/check_lmstudio_endpoint.py
LM Studio CLI docs
LM Studio OpenAI compatibility docs
LM Studio REST API docs

lmstudio-cli

Original

Translation

LM Studio CLI

LM Studio CLI

When to use this skill

何时使用此技能

Instructions

操作说明

Step 1: Identify the operating mode

步骤1：确定运行模式

Step 2: Check whether local
`lms`
exists

步骤2：检查本地
`lms`
是否存在

Step 3: Verify server status or endpoint reachability

步骤3：验证服务器状态或端点可达性

Step 4: Discover exact model identifiers

步骤4：查找确切的模型标识符

Step 5: Escalate to LM Studio-native management only when needed

步骤5：仅在必要时升级到LM Studio原生管理

Step 6: Wire downstream tools carefully

步骤6：谨慎配置下游工具

Step 7: Report the operating facts, not guesses

步骤7：报告实际情况，而非猜测

Examples

示例

Example 1: Local machine with LM Studio installed

示例1：已安装LM Studio的本地机器

Example 2: Remote LM Studio host for another tool

示例2：为其他工具使用的远程LM Studio主机

Example 3: Need more than OpenAI-compatible smoke tests

示例3：需要超出OpenAI兼容冒烟测试的功能

Example 4: Headless failure triage

示例4：无界面故障排查

Best practices

最佳实践

References

参考资料

lmstudio-cli

Original

Translation

LM Studio CLI

LM Studio CLI

When to use this skill

何时使用此技能

Instructions

操作说明

Step 1: Identify the operating mode

步骤1：确定运行模式

Step 2: Check whether local lms exists

步骤2：检查本地lms是否存在

Step 3: Verify server status or endpoint reachability

步骤3：验证服务器状态或端点可达性

Step 4: Discover exact model identifiers

步骤4：查找确切的模型标识符

Step 5: Escalate to LM Studio-native management only when needed

步骤5：仅在必要时升级到LM Studio原生管理

Step 6: Wire downstream tools carefully

步骤6：谨慎配置下游工具

Step 7: Report the operating facts, not guesses

步骤7：报告实际情况，而非猜测

Examples

示例

Example 1: Local machine with LM Studio installed

示例1：已安装LM Studio的本地机器

Example 2: Remote LM Studio host for another tool

示例2：为其他工具使用的远程LM Studio主机

Example 3: Need more than OpenAI-compatible smoke tests

示例3：需要超出OpenAI兼容冒烟测试的功能

Example 4: Headless failure triage

示例4：无界面故障排查

Best practices

最佳实践

References

参考资料

Step 2: Check whether local
`lms`
exists

步骤2：检查本地
`lms`
是否存在