Instructions to use ajh-code/Jev-Bonsai-Compass with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ajh-code/Jev-Bonsai-Compass with jev-style:

pip install jev-style
# GGUF builds score through llama.cpp: build the jev-score binary once
hf download ajh-code/Jev-Bonsai-Compass build_jev_score.sh jev_score.cpp --local-dir jev-score
export JEV_SCORE_BIN=$(sh jev-score/build_jev_score.sh /path/to/llama.cpp | tail -n 1)

from jev_style import JevStyle, noul, choice

js = JevStyle.from_pretrained("ajh-code/Jev-Bonsai-Compass")
out = js.decide("I was charged twice for one order.", {
    "billing": noul("This message is about billing."),
    "team": choice("Which team should handle it?", ["billing", "shipping", "tech"]),
})
print(out["answers"]["team"]["choice"])

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ajh-code/Jev-Bonsai-Compass with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ajh-code/Jev-Bonsai-Compass:Q2_0
# Run inference directly in the terminal:
llama cli -hf ajh-code/Jev-Bonsai-Compass:Q2_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ajh-code/Jev-Bonsai-Compass:Q2_0
# Run inference directly in the terminal:
llama cli -hf ajh-code/Jev-Bonsai-Compass:Q2_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ajh-code/Jev-Bonsai-Compass:Q2_0
# Run inference directly in the terminal:
./llama-cli -hf ajh-code/Jev-Bonsai-Compass:Q2_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ajh-code/Jev-Bonsai-Compass:Q2_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ajh-code/Jev-Bonsai-Compass:Q2_0

Use Docker

docker model run hf.co/ajh-code/Jev-Bonsai-Compass:Q2_0

LM Studio
Jan
Ollama
How to use ajh-code/Jev-Bonsai-Compass with Ollama:
```
ollama run hf.co/ajh-code/Jev-Bonsai-Compass:Q2_0
```
Unsloth Desktop

How to use ajh-code/Jev-Bonsai-Compass with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ajh-code/Jev-Bonsai-Compass:Q2_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ajh-code/Jev-Bonsai-Compass:Q2_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ajh-code/Jev-Bonsai-Compass with Docker Model Runner:
```
docker model run hf.co/ajh-code/Jev-Bonsai-Compass:Q2_0
```

Lemonade

How to use ajh-code/Jev-Bonsai-Compass with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ajh-code/Jev-Bonsai-Compass:Q2_0

Run and chat with the model

lemonade run user.Jev-Bonsai-Compass-Q2_0

List all available models

lemonade list

Hermes Agent

How to use ajh-code/Jev-Bonsai-Compass with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ajh-code/Jev-Bonsai-Compass:Q2_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default ajh-code/Jev-Bonsai-Compass:Q2_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ajh-code/Jev-Bonsai-Compass with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ajh-code/Jev-Bonsai-Compass:Q2_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "ajh-code/Jev-Bonsai-Compass:Q2_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Jev-Bonsai-Compass / NOTICE

ajh-code

Publish Jev-Bonsai-Compass runtime, adapter, card and evidence

b4b0f75 verified 11 days ago

Raw History Blame Contribute Delete

1.92 kB

	Bonsai decision runtime

	The newly packaged bonsai_runtime software is distributed under Apache-2.0.
	This statement applies to the runtime package, not all files in the research
	workspace, and does not relicense the bundled model or adapter weights.

	Letter-option prompting/readout follows OpenJev's Apache-2.0 helper interface.
	The local implementation is modified for the Prism native server, explicit
	adapter profiles, compact numerical tools, and bounded local API entry points.
	OpenJev project: https://huggingface.co/openjev/openjev
	Its helper/ and serve/ code are Apache-2.0; its weights are CC-BY-NC-4.0.
	This bundle includes a locally modified adapter descended from OpenJev weight
	deltas. Its terms retain OpenJev's CC-BY-NC-4.0 noncommercial lineage. The
	adapter is not licensed under the software's Apache-2.0 terms.
	Changes from OpenJev: rank-32 factors were extracted from OpenJev/Qwen3.8-27B
	weight differences, adapted for the unmodified Bonsai PQ2_0 base, and further
	trained in local decision-preservation and fast-route experiments. The selected
	artifact is `adapters/broad-lr0.0001.adapter` (GGUF-formatted bytes). OpenJev's original weights, license
	and notice are at https://huggingface.co/openjev/openjev; the CC terms are at
	https://creativecommons.org/licenses/by-nc/4.0/.

	The bundled native llama.cpp runtime is MIT-licensed by the ggml authors. It
	was built from PrismML-Eng/llama.cpp commit f0a2b5dc9ea066780b9b410d2c0f95d675859bf7
	with the local qwen35 source change in native/source/local-qwen35.patch.
	The bundled, byte-identical Prism Ternary-Bonsai-2-27B weights are Apache-2.0;
	their ancestor Qwen3.8-27B is Apache-2.0. Preserve their licenses and notices.

	The Python decision core has no tzdata dependency. The experimental agent
	controller is excluded from this bundle. See MANIFEST.json for exact
	artifacts and native-runtime.json for the tested build and its system dependencies.