🎁 Get the FREE AI Skills Starter Guide β€” Subscribe β†’
BytesAgainBytesAgain
πŸ¦€ ClawHub

Local-First LLM

by @joelnishanth

Routes LLM requests to a local model (Ollama, LM Studio, llamafile) before falling back to cloud APIs. Tracks token savings and cost avoidance in a persisten...

Versionv1.0.0
Downloads1,193
Stars⭐ 1
TERMINAL
clawhub install local-first-llm

πŸ“– About This Skill


name: local-first-llm description: "Routes LLM requests to a local model (Ollama, LM Studio, llamafile) before falling back to cloud APIs. Tracks token savings and cost avoidance in a persistent dashboard. Use when: (1) user asks to run a task with a local model first, (2) user wants to reduce cloud API costs or keep requests private, (3) user asks to see their token savings or LLM routing dashboard, (4) any request where local-vs-cloud routing should be decided automatically. Supports Ollama, LM Studio, and llamafile as local providers." metadata: { "openclaw": { "emoji": "🏠", "requires": { "bins": ["python3"] }, "install": [] } }

Local-First LLM

Route requests to a local LLM first; fall back to cloud only when necessary. Track every decision to show real token and cost savings.

Quick Start

1. Check if a local LLM is running

python3 skills/local-first-llm/scripts/check_local.py

Returns JSON: { "any_available": true, "best": { "provider": "ollama", "models": [...] } }

2. Route a request

python3 skills/local-first-llm/scripts/route_request.py \
  --prompt "Summarize this meeting transcript" \
  --tokens 800 \
  --local-available \
  --local-provider ollama

Returns: { "decision": "local", "reason": "...", "complexity_score": -1 }

3. Log the outcome

After executing the request, record it:

python3 skills/local-first-llm/scripts/track_savings.py log \
  --tokens 800 \
  --model gpt-4o \
  --routed-to local

4. Show the dashboard

python3 skills/local-first-llm/scripts/dashboard.py


Full Routing Workflow

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚  1. check_local.py  β†’  is a local provider running? β”‚
β”‚                                                      β”‚
β”‚  2. route_request.py  β†’  local or cloud?             β”‚
β”‚     - sensitivity check  (private data β†’ local)      β”‚
β”‚     - complexity score   (high score β†’ cloud)        β”‚
β”‚     - availability gate  (no local β†’ cloud)          β”‚
β”‚                                                      β”‚
β”‚  3. Execute with the chosen provider                 β”‚
β”‚                                                      β”‚
β”‚  4. track_savings.py log  β†’  record the outcome      β”‚
β”‚                                                      β”‚
β”‚  5. dashboard.py  β†’  show cumulative savings         β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜


Routing Rules (Summary)

| Condition | Route | | ----------------------------------------------------------------------------- | -------- | | No local provider available | ☁️ Cloud | | Prompt contains sensitive data (password, secret, api key, ssn, etc.) | 🏠 Local | | Complexity score β‰₯ 3 | ☁️ Cloud | | Complexity score < 3 | 🏠 Local |

For full scoring details, see references/routing-logic.md.


Executing with a Local Provider

Once route_request.py returns "decision": "local", send the request:

Ollama

curl http://localhost:11434/api/generate \
  -d '{"model": "llama3.2", "prompt": "YOUR_PROMPT", "stream": false}'

LM Studio / llamafile (OpenAI-compatible)

curl http://localhost:1234/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "local-model", "messages": [{"role": "user", "content": "YOUR_PROMPT"}]}'


Dashboard

The dashboard reads from ~/.openclaw/local-first-llm/savings.json (auto-created).

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚    🧠  Local-First LLM β€” Dashboard      β”‚
β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€
β”‚  Local LLM:  βœ…  ollama (llama3.2...)   β”‚
β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€
β”‚  Total requests:         42             β”‚
β”‚  Routed locally:         31  (73.8%)    β”‚
β”‚  Routed to cloud:        11             β”‚
β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€
β”‚  Tokens saved:       84,200             β”‚
β”‚  Cost saved:           $0.4210          β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

Reset savings data:

python3 skills/local-first-llm/scripts/track_savings.py reset


Additional References

  • Routing scoring details: references/routing-logic.md
  • Local provider setup (Ollama, LM Studio, llamafile): references/local-providers.md
  • Token estimation & cloud cost table: references/token-estimation.md
  • πŸ’‘ Examples

    1. Check if a local LLM is running

    python3 skills/local-first-llm/scripts/check_local.py
    

    Returns JSON: { "any_available": true, "best": { "provider": "ollama", "models": [...] } }

    2. Route a request

    python3 skills/local-first-llm/scripts/route_request.py \
      --prompt "Summarize this meeting transcript" \
      --tokens 800 \
      --local-available \
      --local-provider ollama
    

    Returns: { "decision": "local", "reason": "...", "complexity_score": -1 }

    3. Log the outcome

    After executing the request, record it:

    python3 skills/local-first-llm/scripts/track_savings.py log \
      --tokens 800 \
      --model gpt-4o \
      --routed-to local
    

    4. Show the dashboard

    python3 skills/local-first-llm/scripts/dashboard.py