This skill covers using LM Studio as the embedding provider for GrepAI, offering a user-friendly GUI for managing local models.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versiongrepai-embeddings-lmstudioExecute the skills CLI command in your project's root directory to begin installation:
Fetches grepai-embeddings-lmstudio from yoanbernabeu/grepai-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate grepai-embeddings-lmstudio. Access via /grepai-embeddings-lmstudio in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
0
total installs
0
this week
16
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
16
stars
This skill covers using LM Studio as the embedding provider for GrepAI, offering a user-friendly GUI for managing local models.
LM Studio is a desktop application for running local LLMs with:
Visit lmstudio.ai and download for your platform:
nomic-embed-text-v1.5bge-small-en-v1.5bge-large-en-v1.5http://localhost:1234)# .grepai/config.yaml
embedder:
provider: lmstudio
model: nomic-embed-text-v1.5
endpoint: http://localhost:1234
embedder:
provider: lmstudio
model: nomic-embed-text-v1.5
endpoint: http://localhost:8080
embedder:
provider: lmstudio
model: nomic-embed-text-v1.5
endpoint: http://localhost:1234
dimensions: 768
| Property | Value |
|---|---|
| Dimensions | 768 |
| Size | ~260 MB |
| Quality | Excellent |
| Speed | Fast |
embedder:
provider: lmstudio
model: nomic-embed-text-v1.5
| Property | Value |
|---|---|
| Dimensions | 384 |
| Size | ~130 MB |
| Quality | Good |
| Speed | Very fast |
Best for: Smaller codebases, faster indexing.
embedder:
provider: lmstudio
model: bge-small-en-v1.5
dimensions: 384
| Property | Value |
|---|---|
| Dimensions | 1024 |
| Size | ~1.3 GB |
| Quality | Very high |
| Speed | Slower |
Best for: Maximum accuracy.
embedder:
provider: lmstudio
model: bge-large-en-v1.5
dimensions: 1024
| Model | Dims | Size | Speed | Quality |
|---|---|---|---|---|
bge-small-en-v1.5 |
384 | 130MB | ⚡⚡⚡ | ⭐⭐⭐ |
nomic-embed-text-v1.5 |
768 | 260MB | ⚡⚡ | ⭐⭐⭐⭐ |
bge-large-en-v1.5 |
1024 | 1.3GB | ⚡ | ⭐⭐⭐⭐⭐ |
1234 (default)Look for the green indicator showing the server is running.
# Check server is responding
curl http://localhost:1234/v1/models
# Test embedding
curl http://localhost:1234/v1/embeddings \
-H "Content-Type: application/json" \
-d '{
"model": "nomic-embed-text-v1.5",
"input": "function authenticate(user)"
}'
In LM Studio's Local Server tab:
| Setting | Recommended Value |
|---|---|
| Port | 1234 |
| Enable CORS | Yes |
| Context Length | Auto |
| GPU Layers | Max (for speed) |
LM Studio automatically uses:
Adjust GPU layers in settings for memory/speed balance.
For server environments, LM Studio supports CLI mode:
# Start server without GUI (check LM Studio docs for exact syntax)
lmstudio server start --model nomic-embed-text-v1.5 --port 1234
❌ Problem: Connection refused ✅ Solution: Ensure LM Studio server is running:
❌ Problem: Model not found ✅ Solution:
❌ Problem: Slow embedding generation ✅ Solutions:
❌ Problem: Port already in use ✅ Solution: Change port in LM Studio settings:
embedder:
endpoint: http://localhost:8080 # Different port
❌ Problem: LM Studio closes and server stops ✅ Solution: Keep LM Studio running in the background, or consider using Ollama which runs as a system service
| Feature | LM Studio | Ollama |
|---|---|---|
| GUI | ✅ Yes | ❌ CLI only |
| System service | ❌ App must run | ✅ Background service |
| Model management | ✅ Visual | ✅ CLI |
| Ease of use | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐ |
| Server reliability | ⭐⭐⭐ | ⭐⭐⭐⭐⭐ |
Recommendation: Use LM Studio if you prefer a GUI, Ollama for always-on background service.
If you need a more reliable background service:
brew install ollama
ollama serve &
ollama pull nomic-embed-text
embedder:
provider: ollama
model: nomic-embed-text
endpoint: http://localhost:11434
rm .grepai/index.gob
grepai watch
nomic-embed-text-v1.5 for best balanceSuccessful LM Studio configuration:
✅ LM Studio Embedding Provider Configured
Provider: LM Studio
Model: nomic-embed-text-v1.5
Endpoint: http://localhost:1234
Dimensions: 768 (auto-detected)
Status: Connected
Note: Keep LM Studio running for embeddings to work.
Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
davila7/claude-code-templates
intellectronica/agent-skills
am-will/codex-skills
sickn33/antigravity-awesome-skills
myzy-ai/dokie-ai-ppt
sickn33/antigravity-awesome-skills
Useful defaults in grepai-embeddings-lmstudio — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
We added grepai-embeddings-lmstudio from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
I recommend grepai-embeddings-lmstudio for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
grepai-embeddings-lmstudio fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
grepai-embeddings-lmstudio has been reliable in day-to-day use. Documentation quality is above average for community skills.
Solid pick for teams standardizing on skills: grepai-embeddings-lmstudio is focused, and the summary matches what you get after install.
Useful defaults in grepai-embeddings-lmstudio — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
grepai-embeddings-lmstudio is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
Useful defaults in grepai-embeddings-lmstudio — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
grepai-embeddings-lmstudio reduced setup friction for our internal harness; good balance of opinion and flexibility.
showing 1-10 of 50