What is Porrima AGENTS.md?

Instructions for Porrima, a web-based agent framework with saved memory, project context, image generation, and tool execution. It is organised as a monorepo, meaning one repository containing separate server and client applications.

It helps with local development, building the Express and TypeScript server, running the React client, checking types, and understanding stored data and model services.

It gives developers the commands, ports, folders, services, and architecture details needed to run and maintain both parts of the application.

How asa-degroff/Porrima configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to asa-degroff/Porrima. 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/asa-degroff/Porrima/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/asa-degroff/Porrima

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/asa-degroff/porrima/agents-md/github.svg)](https://agentmods.dev/instructions/asa-degroff/porrima/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/asa-degroff/porrima/agents-md"><img src="https://agentmods.dev/badge/instructions/asa-degroff/porrima/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/asa-degroff/porrima/agents-md"><img src="https://agentmods.dev/badge/instructions/asa-degroff/porrima/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,082 This file is loaded in full into every session.

When invoked 3,082 The same file — it is already loaded in full.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.03082	$0.03082
Opus 5	$0.01541	$0.01541
Sonnet 5	$0.00616	$0.00616
Haiku 4.5	$0.00308	$0.00308

Measured 9d ago against content hash 4953f91026a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Porrima AGENTS.md scanned grade A with 0 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project

Porrima — A feature-rich agent framework and user interface with persistent memory, project context, image generation, and agentic tool execution. npm workspaces monorepo: server/ (Express + TypeScript) and client/ (React + Vite + Tailwind).

Quick Reference

Server port: 3001 — cd server && npm run dev (tsx watch mode)
Client port: 5173 — cd client && npm run dev (Vite, proxies /api to server)
Build server: cd server && npm run build (outputs to server/dist/)
Build client: cd client && npm run build (outputs to client/dist/)
Type check: npx tsc --noEmit from either server/ or client/
Data dir: ~/.porrima/ (chats, projects, settings, memories, artifacts)
Models dir: ~/.local/share/llama-models/ (symlinked GGUFs for llama.cpp router)
systemd services:
- porrima.service — main server (auto-starts on boot)
- llama-server.service — llama.cpp router (port 32100, GPU inference)
- extraction-model.service — memory extraction server (port 32101, CPU-only)
- reranker.service — Qwen3-Reranker-0.6B (port 32102, CPU-only, memory retrieval)
- embedding-model.service — embedding server (port 32103, CPU-only)
- title-generation.service — title/recap server (port 32104, CPU-only)
- sync-llama-models.timer — auto-syncs HuggingFace GGUF downloads every 5 min

Architecture

See docs/architecture.md for full details.

Three chat types: agent (memory-augmented), quick (standalone), and system (synthesis, wake cycles, and automations). The chat route (server/src/routes/chat.ts) owns memory augmentation, SSE/persistence, compaction, and extraction around the shared agent loop in agent-loop-runner.ts. Chat storage is SQLite with FTS5 full-text search. LLM system uses OpenAI-compatible (llama.cpp) backend for all inference.

Tool System

See docs/tool-system.md for full details.

Native pi-ai tool calling with TypeBox schemas. Registry in agent-tools.ts with memory, filesystem, and sandbox tools. The low-level loop lives in agent-loop-runner.ts; the HTTP chat route and headless automation runner provide their own callbacks for transport, persistence, compaction, and follow-up prompts. ask_user pauses the HTTP loop and persists state. Message reconstruction splits persisted messages back into the pi-ai multi-message format.

Read the full file on GitHub · 180 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.

9d ago First seen · 180 lines · 3,082 tokens per session scan A 4953f91026a0

Subscribe to this mod's changes

Porrima AGENTS.md is an instructions file published in the GitHub repository asa-degroff/Porrima (21 stars, last pushed today), licensed Apache-2.0. It adds 3,082 tokens to every session, about $0.0154 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Planning React agent-harness ai ai-agents llama-cpp pwa

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

Porrima: Instructions file for Codex