Skip to content
Mr-Jacks0nPublic

About

ARIA · symbolic, learning AI (v1.3.1): 14 declarative skills + proof router + disciplined memory + self-audit + branded console/GUI. 100% local, no LLM, no cloud. / IA symbolique apprenante : 14 compétences déclaratives, routeur à preuve, interfaces de marque.

Topics

Resources

Contributing

Stars

0 stars

Watchers

0 watching

Forks

Repository files navigation

ARIA · Symbolic, learning AI

ARIA · Local Learnable Intelligence

ARIA is a symbolic, adaptive AI · version 1.3.1: a declarative catalog of 14 skills, an intent router with proof, a rule engine, a disciplined memory and a security self-audit · no LLM, no machine learning model, no cloud. It learns exclusively from the conversations you have with it and runs 100% on your machine.

CI (Python 3.10 → 3.12) License: MIT Python

🇫🇷 Une version française de ce README est disponible : README.fr.md

✨ Features

  • Declarative skill catalog · every skill is a skills/<name>/SKILL.md folder with frontmatter (name · description · risk · command · triggers): declaring it is enough to make it routable, the catalog validates consistency and lists invalid declarations. Shipped (14): · utilities: date/time, current-month calendar (today marked), unit converter (km/mi, m/ft, kg/lb, °C/°F, Mo/Go), world clock (zoneinfo, no network); · project & docs: local task list (add / list / complete), change journal draft built from local git history, session report; · review & analysis: charter inspector (em-dashes, artifacts, credential literals · positions only, never the content), text statistics, CSV preview; · search & math: DuckDuckGo web search, calculator (safe AST evaluator); · local randomness: value generator (secrets module, displayed · NEVER stored), draws (dice, coin flip, 1 to 100).
  • Intent router with proof · skills, logic and learned rules are all candidate routes with a confidence score; only the winner runs (lazy) and the choice is traceable ([route: … · risk: … · confidence: … · source: …]).
  • IF/THEN rule learning · answers are matched against learned rules; every unknown input is a teaching opportunity (Réponse correcte ? → new rule written to disk). Feedback only applies to learned rules: no misleading duplicates.
  • Memory discipline · secrets are never stored (filter on BOTH fact and rule writes, explicit refusal), hygiene bounds (200 facts · 500 rules), every erasure request ("oublie …") is honored without hidden copies, session compaction with topic archives.
  • Output masking · any sensitive value that would be returned is masked line by line (defense in depth).
  • Security self-audit · python main.py --audit: six offline phases (surface survey → guided hunt → reproducible validation → data/findings.json → independent re-read → neutral report) chasing secrets in data/ and dangerous calls.
  • Persistent memory · rules, facts, experiences and context are plain JSON files in data/, readable and editable by hand.
  • Fuzzy understanding · difflib.get_close_matches maps typos and variants to known rules ("qu'elle heure" → "quelle heure est-il").
  • Automatic calculations · detects expressions anywhere in the input ("1550 + 12500" → Le résultat est : 14050) through a safe AST evaluator (no raw eval, bounded exponents · see changelog).
  • Fact-based reasoning · statements ("je m'appelle Martin") are stored as facts and later recalled ("quel est mon nom" → "Tu t'appelles martin.").
  • Web search · "recherche python" triggers a real DuckDuckGo Instant Answer query over requests (the only network dependency).
  • Reflection · a short-term memory of the last exchanges gives ARIA self-observations: it flags unknown answers, notices repeated topics, asks follow-up questions.
  • Special commands · time/date, open browser, session report, web search (skill mapping CMD:* handled by core/skills.py).
  • Two interfaces · console (works without tkinter) and Tkinter GUI.
  • Diagnostic modes · --debug (decision trace, fuzzy matches, facts), --stats (memory state + catalog summary), --audit (security self-audit).

🖼 What it looks like

Real Tkinter window, captured during a genuine session · the "1550 + 12500" calculation and the remembered name are live answers:

ARIA GUI, real session

🚀 Getting started

git clone https://github.com/Mr-Jacks0n/IA.git
cd IA
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt        # requests is the only dependency

python main.py          # console mode
python main.py --gui    # graphical mode (needs python3-tk)
python main.py --debug  # console + decision logs
python main.py --stats  # memory state + catalog summary
python main.py --audit  # security self-audit (report data/findings.json)
python utils/clean_data.py   # lowercase-normalize saved rules

Console works on servers with no tkinter installed; --gui prints an actionable install hint (sudo apt install python3-tk) if Tk is absent.

🗂 Project structure

.
├── main.py                    # entry point: console | --gui | --debug | --audit | --stats
├── config.py                  # DEBUG_MODE + debug_print helper
├── skills/                    # 14 declarative skills (SKILL.md)
│   ├── annonce-date/ · rapport-session/ · calculatrice-sure/ · recherche-web/
│   ├── gestion-taches/ · journal-changements/ · inspecteur-charte/
│   ├── analyse-texte/ · apercu-csv/ · convertisseur-unites/
│   └── fuseaux-horaires/ · calendrier-mois/ · generateur-jetons/ · tirage-hasard/
├── core/
│   ├── decision_engine.py     # pipeline: winning route → execution → verification
│   ├── router.py              # candidate routes, scores, routing proof
│   ├── catalog.py             # frontmatter parser + validation + secret guard
│   ├── rules.py               # DEFAULT_RULES (seed rules)
│   ├── memory.py              # disciplined JSON memory (rules/facts/context)
│   ├── reflection.py          # short-term memory + self-observations
│   ├── selfaudit.py           # security self-audit (6 phases, offline)
│   └── skills.py              # date, calculator (AST-safe), web search, browser, report
├── interface/
│   ├── console.py             # REPL + oui/non feedback loop (clean EOF)
│   └── gui.py                 # Tkinter chat window
├── learning/feedback.py       # learn(rule) → Memory.add_rule (MemoryRefused on secrets)
├── utils/clean_data.py        # normalize saved rule keys
├── data/*.json                # persistent state (defaults shipped)
├── docs/                      # banner + real GUI screenshot
└── .github/                   # CI + issue/PR templates

🧪 Quality & CI

Every push runs a 3-version CI (Python 3.10 → 3.12) that:

  1. lints the codebase (flake8 E9/F63/F7/F82, blocking),
  2. runs a scripted console session (greet → teach confirmation → calculation → name memorization → recall → date command → clean exit) and asserts the exact expected answers,
  3. runs the security self-audit (python main.py --audit) and validates data/findings.json (confirmed/rejected fields) · the catalog must load 14 skills, 0 invalid,
  4. launches ARIA from an unrelated working directory to guarantee the data paths are anchored to the project root,
  5. fails if any __pycache__/*.pyc sneaks back into the index.

📜 Version history

  • 1.0.0 · rule engine, fuzzy matching, persistent memory, feedback learning, facts, reflection, web search, GUI.
  • 1.1.0 · reliability pass: fixed the reflection engine comparing an exchange with itself, the web-search routing that never fired, an eval() DoS in the calculator, the hard tkinter dependency, and CWD-relative data paths.
  • 1.2.0 · move to a declarative architecture: skill catalog (skills/*/SKILL.md), intent router with proof, memory discipline (no secrets ever, bounds, honored erasure), output masking and a security self-audit (--audit), --stats command, hardened console and GUI.
  • 1.3.0 · catalog grew to 14 skills: task list, change journal, charter inspector, text statistics, CSV preview, unit conversions, world clock, calendar, local random values; reflection on its own line for multi-line answers.
  • 1.3.1 · interface pass: branded console banner + integrated aide/stats/audit commands (routing traces only in --debug), GUI restyled to the brand (colors, routing status bar, chat clearing). See CHANGELOG.md.

🗺 Roadmap

  • Richer fact schemas (age, city, preferences) + follow-up reasoning
  • Multi-shot learning: keep several candidate answers per rule
  • Accent/diacritics normalization before fuzzy matching
  • Export/import of a memory as shareable "knowledge pack"
  • critical-risk skills: explicit confirmation before execution
  • Voice input via speech_recognition (optional extra)

🤝 Contributing

Issues and PRs are welcome · see CONTRIBUTING.md. Templates are provided for bugs, ideas and pull requests.

⚖️ License

MIT · © 2026 Mr Jackson.

About

ARIA · symbolic, learning AI (v1.3.1): 14 declarative skills + proof router + disciplined memory + self-audit + branded console/GUI. 100% local, no LLM, no cloud. / IA symbolique apprenante : 14 compétences déclaratives, routeur à preuve, interfaces de marque.

Topics

Resources

Contributing

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages