Bonsai-demo: Instructions file for Codex

AGENTS.md

Bonsai-demo AGENTS.md is an instructions file for Codex, OpenCode from PrismML-Eng/Bonsai-demo. It costs 4,251 tokens per session, scanned C, original, Apache-2.0.

A repository guide for tuning and running a Bonsai demonstration with local language models. It explains the models, hardware-related settings, image input, tool calling, reasoning output, and long conversations.

In plain words
What is it for?
Use it when configuring the Bonsai demo, selecting model and server options, adjusting reasoning or context settings, or adding tool connections.
Why use it?
It helps an agent choose suitable settings for the user's computer and intended demonstration without relying on untested performance assumptions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is PrismML-Eng/Bonsai-demo's own configuration. It tells Codex and OpenCode how to work on Bonsai-demo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Bonsai-demo configures →

About the project

Bonsai Demo is an application for running Bonsai and Ternary-Bonsai language models locally on computers using supported hardware acceleration or CPUs. It lets users chat with the models, send images and documents, and use tool-calling features through its demo interfaces. The catalogue instruction helps coding agents set up and operate the demo.

PrismML-Eng/Bonsai-demo · 2,279 stars · on GitHub · prismml.com

Reuse

Borrowing it

Nothing to install: this file belongs to PrismML-Eng/Bonsai-demo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/PrismML-Eng/Bonsai-demo/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/PrismML-Eng/Bonsai-demo

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for Bonsai-demo AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/prismml-eng/bonsai-demo/agents-md.svg)](https://agentmods.dev/instructions/prismml-eng/bonsai-demo/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/prismml-eng/bonsai-demo/agents-md"><img src="https://agentmods.dev/badge/instructions/prismml-eng/bonsai-demo/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,251 This file is loaded in full into every session.
When invoked 4,251 The same file — it is already loaded in full.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.04251 $0.04251
Opus 5 $0.02125 $0.02125
Sonnet 5 $0.00850 $0.00850
Haiku 4.5 $0.00425 $0.00425

Measured 9d ago against content hash 9a90564077cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

Bonsai-demo AGENTS.md scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s http://localhost:8080/props | python3 -m json.tool | head -30

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:8080/props | python3 -m json.tool | head -30
AGENTS.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent guide — tuning the Bonsai demo

For AI agents (and humans) helping someone set up this demo. Goal: pick the right flags for the user's hardware and use case. The behavior notes below come from real testing; measure on the user's own hardware before promising performance (the timings object in every API response has the numbers).

Why the 27B models (what to show off)

The 27B generation is a step change over the earlier 8B/4B/1.7B demos:

  • Vision — image input end to end (photos, screenshots) via the mmproj on llama-server.
  • Agentic / tool calling — much stronger at tool use; both llama-server (--jinja) and mlx_lm.server emit native OpenAI tool_calls, verified with full tool round-trips.
  • Thinking — a reasoning model; thought is streamed separately (reasoning_content) and can be budgeted (--reasoning-budget N) or picked per chat in the web UI.
  • Long context — 256k+ tokens per conversation on a 48 GB Mac (hybrid GDN keeps KV cheap).
  • Tiny footprint — the binary 27B packs to ~1.125 bits per weight: it fits on a modern iPhone without memory offloading. The ternary build (~1.7 bpw, packed into 2-bit for faster acceleration) is the higher-quality option and the default.

The models

BONSAI_FAMILY / BONSAI_MODEL Weights Notes
ternary / 27B (default) GGUF ~6.7-7.1 GB + mmproj 0.9 GB; MLX 2-bit ~7.9 GB Higher quality. Two GGUF formats since the mainline rebase (prism-b10658+): PQ2_0 (group 128, 6.66 GiB, smallest/fastest where supported: CUDA, Metal, CPU, ROCm) and official Q2_0 group 64 (Ternary-Bonsai-27B-Q2_g64.gguf, 7.05 GiB, adds Vulkan/SYCL); smaller sizes use *-Q2_0_g64.gguf naming. The scripts pick per backend. Legacy *-Q2_0.gguf files (no g64) only load on old prism-v5 releases; new binaries refuse them with an error
bonsai / 27B GGUF Q1_0 ~3.5 GB + mmproj 0.9 GB; MLX 1-bit ~4.8 GB Smallest and fastest; fits on a modern iPhone without offloading
8B / 4B / 1.7B (both families) smaller Text-only, no tools wiring, legacy tested flag set

Read the full file on GitHub · 190 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 190 lines · 4,251 tokens per session scan C 9a90564077cb

Subscribe to this mod's changes

Bonsai-demo AGENTS.md is an instructions file published in the GitHub repository PrismML-Eng/Bonsai-demo (2,279 stars, last pushed 5d ago), licensed Apache-2.0. It adds 4,251 tokens to every session, about $0.0213 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens