OPSIE
Health Pass
- License — License: NOASSERTION
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Community trust — 25 GitHub stars
Code Fail
- exec() — Shell command execution in kun.py
- network request — Outbound network request in mail.py
Permissions Pass
- Permissions — No dangerous permissions requested
No AI report is available for this listing yet.
OPSIIE (OPSIE) is an advanced Self-Centered Intelligence (SCI) prototype that represents a new paradigm in AI-human interaction.
███ ███████ ███████████ █████████ █████ █████ ██████████
░░░███ ███░░░░░███ ░░███░░░░░███ ███░░░░░███░░███ ░░███ ░░███░░░░░█
░░░███ ███ ░░███ ░███ ░███░███ ░░░ ░███ ░███ ░███ █ ░
░░░███ ░███ ░███ ░██████████ ░░█████████ ░███ ░███ ░██████
███░ ░███ ░███ ░███░░░░░░ ░░░░░░░░███ ░███ ░███ ░███░░█
███░ ░░███ ███ ░███ ███ ░███ ░███ ░███ ░███ ░ █
███░ ░░░███████░ █████ ░░█████████ █████ █████ ██████████
░░░ ░░░░░░░ ░░░░░ ░░░░░░░░░ ░░░░░ ░░░░░ ░░░░░░░░░░
OPSIIE 0.3.80 XP
A Self-Centered Intelligence (SCI) Prototype
By ARPA HELLENIC LOGICAL SYSTEMS · 03 Jul 2025 · Main entry OPSIIE_0_3_80_XP.py
OPSIE is a terminal personality with agency and memory that can act as a daily driver assistant for technical work: recall what you said last week, riff on files and URLs, spin up images or clips, pull market or chain data, draft and send mails, and run structured DNA workflows, all under one session and your own infrastructure. Slash commands, boot flow, and module layout are documented in docs/.
Mission · Layout · Quick start · Docs · Runtime · Access · ARPA links · License
Related ARPA repositories
| Project | Use when you need |
|---|---|
| Skillware | Modular, installable agent skills (logic + governance + tool schemas) decoupled from a single monolith. |
| Hermes3 | Standalone, production-oriented Web3 agent and parsing stack beyond the bundled /0x handler here. |
| Gatekeeper | Standalone facial recognition and emotion gateway patterns (liveness, policy layers) instead of only the built-in boot gate. |
| Rooms | Standalone multi-agent room runtime and tooling when you want collaboration spaces decoupled from the OPSIIE monolith; the bundled /room command here is the in-session counterpart. |
| vic_aisaq_demo | Reference demos around VIC / AISAQ style agent and evaluation flows. |
For coordinated disclosure and secret handling, see SECURITY.md.
Mission
OPSIIE (also referred to as OPSIE) is a terminal-first SCI prototype: a single long-running Python application that combines local LLM conversation (Ollama), durable conversation storage (PostgreSQL), semantic recall (ChromaDB with query expansion and embedding classification), multimodal tooling (image via Hugging Face Inference, music via MusicGen, video via diffusers, URL vision via BLIP, web text extraction), agent routing (OpenAI Assistants for Nyx, Google Gemini for G1, ElevenLabs for TTS and live G1), Yahoo Finance markets, Web3 (/0x), SMTP and IMAP mail, collaborative multi-agent rooms (see also the standalone Rooms project), and GDDA biosequence analysis. It is designed as an integrated research and demonstration stack rather than a minimal chat wrapper.
Boot-time logs mirror the experience you see when running locally: [Security] facial and emotion checks, [System] prompt and SoulSig verification, [Network] mnemonic matrix and mail, [Hardware] Chroma population (for example a full progress bar when hydrating embeddings), [SCI Systems] response engine, sensors, dream engine, DNA and market probes, and agentic nexus readiness—aligned with the OPSIIE branding in the splash and terminal gradient.
Repository layout
| Path | Role |
|---|---|
OPSIIE_0_3_80_XP.py |
Entry point: theme selection, splash, biometric gate, boot sequence, command router, memory I/O, voice orchestration, streaming chat, URL and file enrichment |
terminal_colors.py |
Pastel and Vibrant ANSI palettes and select_theme() |
utils.py |
System prompt, agent display metadata, dreaming phrases, filename helpers, master greetings |
kun.py |
User registry: ARPA ID, wallet, PostgreSQL db_params, enrollment photo path, mail, soul signature; save_known_user_names() persists edits |
kun.example.py |
Large multi-user template for copying into private kun.py if you outgrow the default profile |
help.py |
/help screen and per-command narrative help (detailed_help_texts) |
agentic_network.py |
Nyx (OpenAI), G1 (Gemini), live G1 WebSocket session, Kronos live scaffold, model dispatch |
markets.py / markets_mappings.py |
Yahoo Finance-backed /markets with sector maps and company extras |
web3_handler.py |
/0x family: swaps, sends, gas, custom tokens and chains (exits process if env incomplete at import) |
mail.py |
SMTP send and IMAP inbox loop |
dna.py |
GDDA DNA, RNA, and protein pipelines |
video.py |
Local diffusers-based text-to-video with pluggable model keys |
room.py |
In-process temporal nexus (/room): multi-agent scoring, Chroma-backed session log, CSV export under outputs/rooms/. For a standalone room stack, see arpahls/rooms. |
requirements.txt |
Dependency intent for the full stack (Python, Ollama client, ChromaDB, and stack versions are reflected in the badges above) |
.env.example |
Environment variable template (copy to .env) |
docs/opsiie-splash.png |
Local copy of the OPSIE splash asset; shown under Quick start in this README |
assets/README.txt |
Guidance for biometric enrollment image enrollment.jpg |
Quick start
1. Prerequisites
- Python 3.8+ (GPU strongly recommended for
/musicand/video) - PostgreSQL 14+ with a
conversationstable in each database referenced bykun.py(see docs/CONFIGURATION.md) - Ollama 0.3+ with
llama3andnomic-embed-textavailable locally - ChromaDB 0.4+ (via
pip/requirements.txt; in-process client in the stock build) - Camera and microphone for default authentication and voice paths
- Windows is the primary tested platform; paths in optional voice assets may use drive letters
2. Install
cd d:\Agents\OPSIIE_0_3_80_XP
py -3.11 -m venv .venv
.\.venv\Scripts\Activate.ps1
python -m pip install -r requirements.txt
3. Configure
- Copy
.env.exampleto.envand fill values. Web3 variables are mandatory for import (see docs/ARCHITECTURE.md). - Set
HUGGINGFACE_API_KEYorHF_TOKENfor default/imagine(Hugging Face Inference API). - Edit
kun.py: replace the templateDemo Operatorprofile with yourdb_params,mail,arpa_id, and paths. Addassets/enrollment.jpg(see assets/README.txt). - Align optional custom voice shortcut media paths in
OPSIIE_0_3_80_XP.py(custom_wordsdictionary) if you use MFCC hooks; defaults reference developer machine paths.
4. Run
python OPSIIE_0_3_80_XP.py
Session flow: theme selection → splash → face and emotion gate → PostgreSQL and Chroma mnemonic checks → Ollama probe → sensor check → Web3 handler construction → mail check → dream engine probes → advanced analysis smoke → agentic network probe → optional five-second voice latch → interactive loop.
Documentation map
| Document | Contents |
|---|---|
| docs/COMMANDS.md | Slash commands, subcommands, voice phrasing, dual dispatch notes, examples |
| docs/ARCHITECTURE.md | Module graph, globals, Web3 import coupling, streaming path |
| docs/BOOT_AND_SECURITY.md | Boot stages, DeepFace policy, face match, /status behavior |
| docs/MEMORY_AND_RAG.md | PostgreSQL schema, Chroma collection, recall and forget semantics |
| docs/VOICE.md | /voice, /voice1, /voice2, ElevenLabs, Google STT, custom sounds |
| docs/CONFIGURATION.md | Environment variables, kun.py schema, output directories |
| docs/MODULES.md | File-by-file responsibilities and extension points |
| docs/PROMPTS_AND_SOULSIG.md | System prompt role, Soul Signature hierarchy, utils.py overview |
| docs/TROUBLESHOOTING.md | Common failures, path migration, model cold starts |
| docs/README.md | Index inside the docs/ folder |
Runtime dependencies
- Ollama:
llama3for chat and query expansion;nomic-embed-textfor mnemonic embeddings (pull both in Ollama). - PostgreSQL: per-user
dbnamefrom the authenticatedkun.pyentry. - ChromaDB: in-process client; global collection name
conversations; room sessions use separate collections. - Optional and remote APIs: OpenAI (Nyx), Google Generative AI (G1), ElevenLabs (TTS and live agents), Hugging Face Inference (default
/imagine), Yahoo Finance, NCBI e-utilities (politeNCBI_EMAIL).
Access control
arpa_idstarting withR: Master access to experimental commands:/ask,/markets,/dna,/0x(and legacysendshows migration text).- Other IDs: Restricted; attempts print a denial path via
handle_restricted_command().
The main input loop and handle_user_query() both enforce gating. 0x is included in the main-loop check so non-master users cannot bypass Web3 commands.
License and support
- Proprietary: see LICENSE.
- Email: [email protected]
- Web: https://arpacorp.net | https://arpa.systems
- Governance: CONTRIBUTING.md, CODE_OF_CONDUCT.md, SECURITY.md
Built & Maintained by ARPA Hellenic Logical Systems & the Community
"We move where life is gonna be, not where it was."
— Ross Peili, Main Human @ ARPA Corp.
Reviews (0)
Sign in to leave a review.
Leave a reviewNo results found