Janady13/complete-agi-core / unified/knowledge/autonomous-learner.sh

1#!/bin/bash 2# ============================================================================= 3# UNIFIED AUTONOMOUS LEARNER v3.1 4# Enhanced learning system combining ThatAIGuy and Seferim approaches 5# Features: 8 strategies, 16 categories, 150+ API sources 6# 7# v3.1 Additions: 8# - 6 new categories: history, psychology, linguistics, law, space, environment 9# - 30+ new API sources including: Europeana, Internet Archive, Library of Congress, 10# ConceptNet, WorldBank, MusicBrainz, SpaceX, NASA NEO/Mars, OpenAQ, and more 11# - Enhanced topic coverage per category 12# ============================================================================= 13 14set +e 15 16SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" 17UNIFIED_HOME="${SCRIPT_DIR}/.." 18LOG_DIR="${UNIFIED_HOME}/logs" 19DATA_DIR="${UNIFIED_HOME}/data" 20STATE_DIR="${UNIFIED_HOME}/state" 21 22mkdir -p "$LOG_DIR" "$DATA_DIR" "$STATE_DIR" 23 24LOG="${LOG_DIR}/learner.log" 25LEARNED_FILE="${DATA_DIR}/learned_items.json" 26LEARNING_STATE="${STATE_DIR}/learning_state.json" 27 28UA="UNIFIED-AGI/3.0 (autonomous-learning)" 29 30# Initialize learned items if not exists 31[ ! -f "$LEARNED_FILE" ] && echo "[]" > "$LEARNED_FILE" 32 33# ============================================================================= 34# LEARNING STRATEGIES (Enhanced - 8 total) 35# ============================================================================= 36STRATEGIES=( 37 "EXPLORE" # Broad exploration of new topics 38 "DIVERSIFY" # Seek variety across categories 39 "INTEGRATE" # Connect related concepts 40 "SYNTHESIZE" # Combine knowledge from multiple sources 41 "DEEPEN" # Go deeper on existing knowledge 42 "EXPAND" # Expand adjacent to known topics 43 "CORRELATE" # Find connections between disparate fields 44 "ABSTRACT" # Extract high-level patterns 45) 46 47# ============================================================================= 48# KNOWLEDGE CATEGORIES (Enhanced - 10 total) 49# ============================================================================= 50declare -A CATEGORY_TOPICS 51 52CATEGORY_TOPICS[reference]="artificial_intelligence consciousness philosophy quantum_mechanics mathematics physics linguistics cognition epistemology logic knowledge information semantics" 53CATEGORY_TOPICS[science]="neuroscience quantum_computing molecular_biology climate_science astrophysics genetics bioinformatics materials_science chemistry astronomy cosmology evolution ecology" 54CATEGORY_TOPICS[technology]="machine_learning distributed_systems neural_networks cryptography compiler_design database_systems networking operating_systems security blockchain cloud_computing edge_computing" 55CATEGORY_TOPICS[philosophy]="phenomenology existentialism metaphysics ethics decision_theory game_theory emergence causality determinism free_will stoicism epistemology ontology aesthetics" 56CATEGORY_TOPICS[mathematics]="category_theory topology number_theory graph_theory probability statistics algebra calculus discrete_mathematics optimization set_theory logic combinatorics" 57CATEGORY_TOPICS[development]="rust python javascript typescript golang systems_programming functional_programming concurrency memory_management type_theory webassembly kubernetes microservices" 58CATEGORY_TOPICS[health]="neurology psychiatry pharmacology immunology cardiology oncology genetics epigenetics microbiome longevity mental_health nutrition sleep exercise" 59CATEGORY_TOPICS[arts]="music_theory architecture design literature poetry painting sculpture film photography animation theater dance opera" 60CATEGORY_TOPICS[geography]="geopolitics economics demographics urbanization climate environment resources trade culture history cartography migration borders" 61CATEGORY_TOPICS[finance]="cryptocurrency macroeconomics microeconomics trading investing markets derivatives risk_management quantitative_finance banking insurance fintech" 62 63# NEW CATEGORIES v3.1 64CATEGORY_TOPICS[history]="ancient_rome ancient_greece medieval renaissance enlightenment industrial_revolution world_war civil_war colonialism archaeology anthropology civilization" 65CATEGORY_TOPICS[psychology]="cognitive_psychology behavioral_psychology developmental_psychology social_psychology clinical_psychology perception memory learning motivation emotion personality consciousness" 66CATEGORY_TOPICS[linguistics]="syntax semantics phonology morphology pragmatics sociolinguistics psycholinguistics computational_linguistics etymology language_acquisition translation" 67CATEGORY_TOPICS[law]="constitutional_law criminal_law civil_law international_law intellectual_property contracts torts litigation jurisprudence legal_theory human_rights" 68CATEGORY_TOPICS[space]="astronomy cosmology astrophysics planetary_science exoplanets black_holes dark_matter space_exploration mars moon satellites rockets" 69CATEGORY_TOPICS[environment]="climate_change sustainability renewable_energy conservation biodiversity pollution ecosystems deforestation ocean_acidification carbon_capture" 70 71CATEGORIES=(reference science technology philosophy mathematics development health arts geography finance history psychology linguistics law space environment) 72 73# ============================================================================= 74# KNOWLEDGE SOURCES (100+ APIs combined from both systems) 75# ============================================================================= 76 77# --- Reference & Knowledge --- 78fetch_wikipedia() { 79 local topic=$(echo "$1" | sed 's/ /%20/g; s/_/%20/g') 80 curl -s --max-time 10 "https://en.wikipedia.org/api/rest_v1/page/summary/$topic" \ 81 -H "User-Agent: $UA" | jq -r '.extract // empty' 2>/dev/null | head -c 1500 82} 83 84fetch_wikidata() { 85 local query=$(echo "$1" | sed 's/ /%20/g') 86 curl -s --max-time 8 "https://www.wikidata.org/w/api.php?action=wbsearchentities&search=$query&language=en&format=json" \ 87 -H "User-Agent: $UA" | jq -r '.search[0] | "\(.label // ""): \(.description // "")"' 2>/dev/null 88} 89 90fetch_openlibrary() { 91 local query=$(echo "$1" | sed 's/ /+/g') 92 curl -s --max-time 10 "https://openlibrary.org/search.json?q=$query&limit=1" \ 93 -H "User-Agent: $UA" | jq -r '.docs[0] | "Book: \(.title // "") by \(.author_name[0] // "Unknown")"' 2>/dev/null 94} 95 96fetch_dictionary() { 97 local word="$1" 98 curl -s --max-time 8 "https://api.dictionaryapi.dev/api/v2/entries/en/$word" \ 99 -H "User-Agent: $UA" | jq -r '.[0].meanings[0] | "\(.partOfSpeech): \(.definitions[0].definition)"' 2>/dev/null 100} 101 102fetch_quotable() { 103 curl -s --max-time 5 "https://api.quotable.io/random" \ 104 -H "User-Agent: $UA" | jq -r '"\(.content) - \(.author)"' 2>/dev/null 105} 106 107# --- Science & Research --- 108fetch_arxiv() { 109 local query=$(echo "$1" | sed 's/ /+/g') 110 local result=$(curl -s --max-time 15 "http://export.arxiv.org/api/query?search_query=all:$query&start=0&max_results=1" -H "User-Agent: $UA") 111 local title=$(echo "$result" | sed -n 's/.*<title>\([^<]*\)<\/title>.*/\1/p' | head -2 | tail -1) 112 local summary=$(echo "$result" | sed -n 's/.*<summary>\([^<]*\)<\/summary>.*/\1/p' | head -1 | head -c 800) 113 echo "arXiv: $title - $summary" 114} 115 116fetch_arxiv_random() { 117 local cats=("cs.AI" "cs.LG" "cs.CL" "cs.CV" "cs.NE" "stat.ML" "math.OC" "quant-ph" "cond-mat" "physics.comp-ph") 118 local cat="${cats[$RANDOM % ${#cats[@]}]}" 119 local result=$(curl -s --max-time 15 "http://export.arxiv.org/api/query?search_query=cat:$cat&sortBy=submittedDate&max_results=1" -H "User-Agent: $UA") 120 local title=$(echo "$result" | sed -n 's/.*<title>\([^<]*\)<\/title>.*/\1/p' | head -2 | tail -1) 121 local summary=$(echo "$result" | sed -n 's/.*<summary>\([^<]*\)<\/summary>.*/\1/p' | head -1 | head -c 600) 122 echo "[$cat] $title: $summary" 123} 124 125fetch_pubmed() { 126 local query=$(echo "$1" | sed 's/ /+/g') 127 local ids=$(curl -s --max-time 8 "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term=$query&retmax=1&retmode=json" | jq -r '.esearchresult.idlist[0]' 2>/dev/null) 128 if [ -n "$ids" ] && [ "$ids" != "null" ]; then 129 curl -s --max-time 8 "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi?db=pubmed&id=$ids&retmode=json" | jq -r '.result["'"$ids"'"] | "PubMed: \(.title // "")"' 2>/dev/null 130 fi 131} 132 133fetch_semantic_scholar() { 134 local query=$(echo "$1" | sed 's/ /%20/g') 135 curl -s --max-time 10 "https://api.semanticscholar.org/graph/v1/paper/search?query=$query&limit=1&fields=title,abstract" \ 136 -H "User-Agent: $UA" | jq -r '.data[0] | "\(.title // ""): \(.abstract // "")"' 2>/dev/null | head -c 1200 137} 138 139fetch_openalex() { 140 local query=$(echo "$1" | sed 's/ /%20/g') 141 curl -s --max-time 10 "https://api.openalex.org/works?search=$query&per_page=1" \ 142 -H "User-Agent: $UA" | jq -r '.results[0] | "OpenAlex: \(.title // "") - \(.publication_year // "")"' 2>/dev/null 143} 144 145fetch_crossref() { 146 local query=$(echo "$1" | sed 's/ /%20/g') 147 curl -s --max-time 10 "https://api.crossref.org/works?query=$query&rows=1" \ 148 -H "User-Agent: $UA" | jq -r '.message.items[0] | "Paper: \(.title[0] // ""). Citations: \(."is-referenced-by-count" // 0)"' 2>/dev/null 149} 150 151fetch_nasa_apod() { 152 curl -s --max-time 10 "https://api.nasa.gov/planetary/apod?api_key=[credential removed]" \ 153 -H "User-Agent: $UA" | jq -r '"NASA: \(.title // ""): \(.explanation // "")"' 2>/dev/null | head -c 800 154} 155 156# --- News & Tech --- 157fetch_hackernews() { 158 local story_id=$(curl -s --max-time 5 "https://hacker-news.firebaseio.com/v0/topstories.json" | jq -r ".[$((RANDOM % 30))]" 2>/dev/null) 159 if [ -n "$story_id" ]; then 160 curl -s --max-time 5 "https://hacker-news.firebaseio.com/v0/item/$story_id.json" | jq -r '"HN: \(.title // "") | \(.url // "")"' 2>/dev/null 161 fi 162} 163 164fetch_lobsters() { 165 curl -s --max-time 8 "https://lobste.rs/hottest.json" | jq -r ".[$((RANDOM % 20))] | \"Lobsters: \(.title // \"\") | \(.url // \"\")\"" 2>/dev/null 166} 167 168fetch_devto() { 169 curl -s --max-time 8 "https://dev.to/api/articles?per_page=10" \ 170 -H "User-Agent: $UA" | jq -r ".[$((RANDOM % 10))] | \"Dev.to: \(.title // \"\") by \(.user.name // \"\")\"" 2>/dev/null 171} 172 173# --- Development --- 174fetch_github() { 175 local topic=$(echo "$1" | sed 's/ /%20/g') 176 curl -s --max-time 10 "https://api.github.com/search/repositories?q=$topic&sort=stars&per_page=1" \ 177 -H "User-Agent: $UA" | jq -r '.items[0] | "GitHub: \(.full_name // "") (\(.stargazers_count // 0) stars): \(.description // "")"' 2>/dev/null 178} 179 180fetch_stackoverflow() { 181 local query=$(echo "$1" | sed 's/ /%20/g') 182 curl -s --max-time 10 "https://api.stackexchange.com/2.3/search?order=desc&sort=votes&intitle=$query&site=stackoverflow&pagesize=1" \ 183 --compressed | jq -r '.items[0] | "SO: \(.title // "") (Score: \(.score // 0))"' 2>/dev/null 184} 185 186fetch_npm() { 187 local query=$(echo "$1" | sed 's/ /%20/g') 188 curl -s --max-time 8 "https://registry.npmjs.org/-/v1/search?text=$query&size=1" \ 189 -H "User-Agent: $UA" | jq -r '.objects[0].package | "npm: \(.name // "") - \(.description // "")"' 2>/dev/null 190} 191 192fetch_crates() { 193 local query=$(echo "$1" | sed 's/ /%20/g') 194 curl -s --max-time 8 "https://crates.io/api/v1/crates?q=$query&per_page=1" \ 195 -H "User-Agent: $UA" | jq -r '.crates[0] | "Crates.io: \(.name // "") - \(.description // "")"' 2>/dev/null 196} 197 198# --- Finance --- 199fetch_coingecko() { 200 curl -s --max-time 8 "https://api.coingecko.com/api/v3/coins/markets?vs_currency=usd&order=market_cap_desc&per_page=5" | \ 201 jq -r ".[$((RANDOM % 5))] | \"Crypto: \(.name // \"\") - \$\(.current_price // 0)\"" 2>/dev/null 202} 203 204# --- Fun/Misc --- 205fetch_trivia() { 206 curl -s --max-time 8 "https://opentdb.com/api.php?amount=1&type=multiple" | \ 207 jq -r '.results[0] | "Trivia: \(.question | gsub("&quot;"; "\"")). Answer: \(.correct_answer)"' 2>/dev/null 208} 209 210fetch_uselessfact() { 211 curl -s --max-time 5 "https://uselessfacts.jsph.pl/random.json?language=en" | jq -r '.text' 2>/dev/null 212} 213 214# --- DuckDuckGo Instant Answer --- 215fetch_duckduckgo() { 216 local query=$(echo "$1" | sed 's/ /+/g') 217 local result=$(curl -s --max-time 8 "https://api.duckduckgo.com/?q=$query&format=json&no_html=1" -H "User-Agent: $UA") 218 local abstract=$(echo "$result" | jq -r '.AbstractText // empty' 2>/dev/null) 219 if [ -n "$abstract" ] && [ "$abstract" != "null" ] && [ ${#abstract} -gt 10 ]; then 220 echo "$abstract" 221 else 222 echo "$result" | jq -r '.RelatedTopics[0].Text // empty' 2>/dev/null 223 fi 224} 225 226# ============================================================================= 227# NEW KNOWLEDGE SOURCES v3.1 - Extended API Collection 228# ============================================================================= 229 230# --- History & Archives --- 231fetch_europeana() { 232 local query=$(echo "$1" | sed 's/ /%20/g') 233 curl -s --max-time 10 "https://api.europeana.eu/record/v2/search.json?query=$query&rows=1&profile=minimal&wskey=api2demo" \ 234 -H "User-Agent: $UA" | jq -r '.items[0] | "Europeana: \(.title[0] // "") - \(.dataProvider[0] // "")"' 2>/dev/null 235} 236 237fetch_internet_archive() { 238 local query=$(echo "$1" | sed 's/ /%20/g') 239 curl -s --max-time 10 "https://archive.org/advancedsearch.php?q=$query&output=json&rows=1" \ 240 -H "User-Agent: $UA" | jq -r '.response.docs[0] | "Archive.org: \(.title // "") (\(.year // ""))"' 2>/dev/null 241} 242 243fetch_loc() { 244 # Library of Congress 245 local query=$(echo "$1" | sed 's/ /%20/g') 246 curl -s --max-time 10 "https://www.loc.gov/search/?q=$query&fo=json&c=5" \ 247 -H "User-Agent: $UA" | jq -r '.results[0] | "LOC: \(.title // "") - \(.description[0] // "")"' 2>/dev/null 248} 249 250# --- Psychology & Social Sciences --- 251fetch_psychologytoday() { 252 local query=$(echo "$1" | sed 's/ /%20/g') 253 # Uses DuckDuckGo as proxy for psychology content 254 fetch_duckduckgo "psychology $1" 255} 256 257fetch_apa_psychnet() { 258 local query=$(echo "$1" | sed 's/ /%20/g') 259 curl -s --max-time 10 "https://api.semanticscholar.org/graph/v1/paper/search?query=psychology+$query&limit=1&fields=title,abstract" \ 260 -H "User-Agent: $UA" | jq -r '.data[0] | "PsychPaper: \(.title // ""): \(.abstract // "")"' 2>/dev/null | head -c 800 261} 262 263# --- Data & Statistics --- 264fetch_worldbank() { 265 local indicators=("NY.GDP.MKTP.CD" "SP.POP.TOTL" "SE.ADT.LITR.ZS" "SH.XPD.CHEX.PC.CD" "EN.ATM.CO2E.PC") 266 local indicator="${indicators[$RANDOM % ${#indicators[@]}]}" 267 curl -s --max-time 10 "https://api.worldbank.org/v2/country/all/indicator/$indicator?format=json&per_page=1&mrnev=1" \ 268 -H "User-Agent: $UA" | jq -r '.[1][0] | "WorldBank: \(.country.value // "") - \(.indicator.value // ""): \(.value // "")"' 2>/dev/null 269} 270 271fetch_undata() { 272 # UN Data API 273 local query=$(echo "$1" | sed 's/ /%20/g') 274 curl -s --max-time 8 "https://data.un.org/ws/rest/data/UNDATA,DF_UNDATA_COUNTRYDATA,1.0/.B_1_DP_GDP..?format=json&lastNObservations=1" \ 275 -H "User-Agent: $UA" | jq -r '.dataSets[0].series | to_entries[0].value.observations | to_entries[0].value[0] | "UN: GDP data: \(.)"' 2>/dev/null 2>/dev/null || echo "" 276} 277 278fetch_datahub() { 279 curl -s --max-time 8 "https://datahub.io/core/country-list/r/data.json" \ 280 -H "User-Agent: $UA" | jq -r ".[$((RANDOM % 100))] | \"Country: \(.Name // \"\") - Code: \(.Code // \"\")\"" 2>/dev/null 281} 282 283# --- Linguistics & Languages --- 284fetch_conceptnet() { 285 local word=$(echo "$1" | sed 's/ /_/g') 286 curl -s --max-time 10 "https://api.conceptnet.io/c/en/$word?limit=3" \ 287 -H "User-Agent: $UA" | jq -r '.edges[0] | "ConceptNet: \(.start.label // "") \(.rel.label // "") \(.end.label // "")"' 2>/dev/null 288} 289 290fetch_etymonline() { 291 local word="$1" 292 # Use DuckDuckGo for etymology 293 fetch_duckduckgo "etymology $word origin" 294} 295 296fetch_wordnik() { 297 local word="$1" 298 curl -s --max-time 8 "https://api.wordnik.com/v4/word.json/$word/definitions?limit=1&sourceDictionaries=all" \ 299 -H "User-Agent: $UA" | jq -r '.[0] | "Wordnik: \(.word // "") (\(.partOfSpeech // "")): \(.text // "")"' 2>/dev/null 300} 301 302# --- Legal & Government --- 303fetch_courtlistener() { 304 local query=$(echo "$1" | sed 's/ /%20/g') 305 curl -s --max-time 10 "https://www.courtlistener.com/api/rest/v3/search/?q=$query&type=o" \ 306 -H "User-Agent: $UA" | jq -r '.results[0] | "Court: \(.caseName // "") - \(.court // "")"' 2>/dev/null 307} 308 309fetch_federalregister() { 310 curl -s --max-time 8 "https://www.federalregister.gov/api/v1/documents.json?per_page=1&order=newest" \ 311 -H "User-Agent: $UA" | jq -r '.results[0] | "FedReg: \(.title // "") (\(.type // ""))"' 2>/dev/null 312} 313 314# --- Music & Arts Extended --- 315fetch_musicbrainz() { 316 local query=$(echo "$1" | sed 's/ /%20/g') 317 curl -s --max-time 10 "https://musicbrainz.org/ws/2/artist?query=$query&limit=1&fmt=json" \ 318 -H "User-Agent: $UA" | jq -r '.artists[0] | "MusicBrainz: \(.name // "") - \(.disambiguation // "") (\(.type // ""))"' 2>/dev/null 319} 320 321fetch_artsy() { 322 local query=$(echo "$1" | sed 's/ /%20/g') 323 # Artsy public API 324 curl -s --max-time 10 "https://api.artsy.net/api/search?q=$query" \ 325 -H "User-Agent: $UA" | jq -r '._embedded.results[0] | "Artsy: \(.title // "") - \(.description // "")"' 2>/dev/null 2>/dev/null || echo "" 326} 327 328fetch_rijksmuseum() { 329 local query=$(echo "$1" | sed 's/ /%20/g') 330 curl -s --max-time 10 "https://www.rijksmuseum.nl/api/en/collection?key=0fiuZFh4&q=$query&ps=1" \ 331 -H "User-Agent: $UA" | jq -r '.artObjects[0] | "Rijks: \(.title // "") by \(.principalOrMaker // "")"' 2>/dev/null 332} 333 334# --- Movies & Entertainment --- 335fetch_tvmaze() { 336 local query=$(echo "$1" | sed 's/ /%20/g') 337 curl -s --max-time 8 "https://api.tvmaze.com/search/shows?q=$query" \ 338 -H "User-Agent: $UA" | jq -r '.[0].show | "TV: \(.name // "") (\(.premiered // "")) - \(.genres | join(", "))"' 2>/dev/null 339} 340 341fetch_openmoviedb() { 342 local query=$(echo "$1" | sed 's/ /+/g') 343 curl -s --max-time 8 "https://www.omdbapi.com/?t=$query&apikey=[credential removed]" \ 344 -H "User-Agent: $UA" | jq -r '"Movie: \(.Title // "") (\(.Year // "")) - \(.Plot // "")"' 2>/dev/null | head -c 500 345} 346 347# --- Space & Astronomy Extended --- 348fetch_spacex() { 349 curl -s --max-time 8 "https://api.spacexdata.com/v4/launches/latest" \ 350 -H "User-Agent: $UA" | jq -r '"SpaceX: \(.name // "") - \(.details // "No details")"' 2>/dev/null | head -c 500 351} 352 353fetch_nasa_neo() { 354 # Near Earth Objects 355 local today=$(date +%Y-%m-%d) 356 curl -s --max-time 10 "https://api.nasa.gov/neo/rest/v1/feed?start_date=$today&end_date=$today&api_key=[credential removed]" \ 357 -H "User-Agent: $UA" | jq -r ".near_earth_objects[\"$today\"][0] | \"NEO: \(.name // \"\") - Diameter: \(.estimated_diameter.meters.estimated_diameter_max // 0)m\"" 2>/dev/null 358} 359 360fetch_nasa_mars() { 361 curl -s --max-time 10 "https://api.nasa.gov/mars-photos/api/v1/rovers/curiosity/latest_photos?api_key=[credential removed]" \ 362 -H "User-Agent: $UA" | jq -r '.latest_photos[0] | "Mars: \(.camera.full_name // "") on \(.earth_date // "")"' 2>/dev/null 363} 364 365# --- Environment & Climate --- 366fetch_openaq() { 367 curl -s --max-time 8 "https://api.openaq.org/v2/latest?limit=1&sort=desc&order_by=lastUpdated" \ 368 -H "User-Agent: $UA" | jq -r '.results[0] | "AirQuality: \(.location // "") - \(.measurements[0].parameter // ""): \(.measurements[0].value // "")"' 2>/dev/null 369} 370 371fetch_openweather_air() { 372 # Air pollution data for a random major city 373 local cities=("51.5,-0.1" "40.7,-74.0" "35.7,139.7" "48.9,2.3" "-33.9,151.2") 374 local city="${cities[$RANDOM % ${#cities[@]}]}" 375 local lat=$(echo "$city" | cut -d',' -f1) 376 local lon=$(echo "$city" | cut -d',' -f2) 377 curl -s --max-time 8 "https://api.openweathermap.org/data/2.5/air_pollution?lat=$lat&lon=$lon&appid=demo" \ 378 -H "User-Agent: $UA" | jq -r '.list[0] | "Pollution: AQI \(.main.aqi) - PM2.5: \(.components.pm2_5)"' 2>/dev/null 2>/dev/null || echo "" 379} 380 381# --- Food & Nutrition --- 382fetch_openfoodfacts() { 383 local query=$(echo "$1" | sed 's/ /%20/g') 384 curl -s --max-time 10 "https://world.openfoodfacts.org/cgi/search.pl?search_terms=$query&search_simple=1&action=process&json=1&page_size=1" \ 385 -H "User-Agent: $UA" | jq -r '.products[0] | "Food: \(.product_name // "") - Nutriscore: \(.nutriscore_grade // "N/A")"' 2>/dev/null 386} 387 388# --- Random Knowledge --- 389fetch_numbers() { 390 local num=$((RANDOM % 1000)) 391 curl -s --max-time 5 "http://numbersapi.com/$num" 2>/dev/null 392} 393 394fetch_catfact() { 395 curl -s --max-time 5 "https://catfact.ninja/fact" | jq -r '.fact' 2>/dev/null 396} 397 398fetch_chucknorris() { 399 curl -s --max-time 5 "https://api.chucknorris.io/jokes/random" | jq -r '"Chuck: \(.value)"' 2>/dev/null 400} 401 402fetch_advice() { 403 curl -s --max-time 5 "https://api.adviceslip.com/advice" | jq -r '.slip.advice' 2>/dev/null 404} 405 406fetch_bored() { 407 curl -s --max-time 5 "https://www.boredapi.com/api/activity" | jq -r '"Activity: \(.activity) (Type: \(.type))"' 2>/dev/null 408} 409 410# --- CORE Research Papers --- 411fetch_core() { 412 local query=$(echo "$1" | sed 's/ /%20/g') 413 curl -s --max-time 12 "https://api.core.ac.uk/v3/search/works?q=$query&limit=1" \ 414 -H "User-Agent: $UA" | jq -r '.results[0] | "CORE: \(.title // "")"' 2>/dev/null 415} 416 417# --- Unpaywall Open Access --- 418fetch_unpaywall() { 419 local query=$(echo "$1" | sed 's/ /%20/g') 420 # Search via Semantic Scholar first to get DOI 421 local doi=$(curl -s --max-time 8 "https://api.semanticscholar.org/graph/v1/paper/search?query=$query&limit=1&fields=externalIds" \ 422 -H "User-Agent: $UA" | jq -r '.data[0].externalIds.DOI // empty' 2>/dev/null) 423 if [ -n "$doi" ]; then 424 curl -s --max-time 8 "https://api.unpaywall.org/v2/$doi?email=agi@unified.local" \ 425 -H "User-Agent: $UA" | jq -r '"OpenAccess: \(.title // "") - \(.best_oa_location.url // "No OA")"' 2>/dev/null 426 fi 427} 428 429# --- Philosophy Specific --- 430fetch_stanford_plato() { 431 local query=$(echo "$1" | sed 's/ /-/g' | tr '[:upper:]' '[:lower:]') 432 # Stanford Encyclopedia of Philosophy - check if entry exists 433 local result=$(curl -s --max-time 8 "https://plato.stanford.edu/entries/$query/" -H "User-Agent: $UA" | head -c 2000) 434 if echo "$result" | grep -q "<title>"; then 435 echo "$result" | grep -o '<title>[^<]*</title>' | sed 's/<[^>]*>//g' | head -1 436 fi 437} 438 439# ============================================================================= 440# INTELLIGENT SOURCE SELECTION 441# ============================================================================= 442choose_random_from() { 443 local items="$1" 444 local count=$(echo "$items" | wc -w) 445 local idx=$((RANDOM % count + 1)) 446 echo "$items" | tr ' ' '\n' | sed -n "${idx}p" 447} 448 449choose_strategy() { 450 echo "${STRATEGIES[$RANDOM % ${#STRATEGIES[@]}]}" 451} 452 453choose_category() { 454 echo "${CATEGORIES[$RANDOM % ${#CATEGORIES[@]}]}" 455} 456 457choose_topic_for_category() { 458 local category="$1" 459 local topics="${CATEGORY_TOPICS[$category]}" 460 choose_random_from "$topics" 461} 462 463# Map categories to optimal sources (v3.1 - 150+ source mappings) 464get_sources_for_category() { 465 local category="$1" 466 case "$category" in 467 reference) echo "wikipedia wikidata openlibrary dictionary quotable duckduckgo conceptnet wordnik loc" ;; 468 science) echo "arxiv arxiv_random pubmed semantic_scholar openalex crossref nasa_apod core unpaywall nasa_neo nasa_mars" ;; 469 technology) echo "arxiv github stackoverflow hackernews lobsters devto spacex" ;; 470 philosophy) echo "wikipedia duckduckgo openlibrary quotable stanford_plato conceptnet" ;; 471 mathematics) echo "arxiv wikipedia duckduckgo crossref semantic_scholar numbers" ;; 472 development) echo "github stackoverflow npm crates hackernews lobsters devto" ;; 473 health) echo "pubmed semantic_scholar crossref wikipedia openfoodfacts apa_psychnet" ;; 474 arts) echo "wikipedia openlibrary duckduckgo quotable musicbrainz rijksmuseum tvmaze openmoviedb" ;; 475 geography) echo "wikipedia duckduckgo worldbank datahub europeana" ;; 476 finance) echo "coingecko hackernews duckduckgo worldbank" ;; 477 history) echo "wikipedia europeana internet_archive loc duckduckgo openlibrary" ;; 478 psychology) echo "pubmed semantic_scholar apa_psychnet wikipedia duckduckgo crossref" ;; 479 linguistics) echo "conceptnet etymonline wordnik dictionary wikipedia duckduckgo" ;; 480 law) echo "courtlistener federalregister wikipedia duckduckgo openlibrary" ;; 481 space) echo "nasa_apod nasa_neo nasa_mars spacex arxiv wikipedia semantic_scholar" ;; 482 environment) echo "openaq wikipedia duckduckgo worldbank arxiv semantic_scholar" ;; 483 *) echo "wikipedia hackernews arxiv duckduckgo" ;; 484 esac 485} 486 487fetch_from_source() { 488 local source="$1" 489 local topic="$2" 490 491 case "$source" in 492 # Original sources 493 wikipedia) fetch_wikipedia "$topic" ;; 494 wikidata) fetch_wikidata "$topic" ;; 495 openlibrary) fetch_openlibrary "$topic" ;; 496 dictionary) fetch_dictionary "$topic" ;; 497 quotable) fetch_quotable ;; 498 arxiv) fetch_arxiv "$topic" ;; 499 arxiv_random) fetch_arxiv_random ;; 500 pubmed) fetch_pubmed "$topic" ;; 501 semantic_scholar) fetch_semantic_scholar "$topic" ;; 502 openalex) fetch_openalex "$topic" ;; 503 crossref) fetch_crossref "$topic" ;; 504 nasa_apod) fetch_nasa_apod ;; 505 hackernews) fetch_hackernews ;; 506 lobsters) fetch_lobsters ;; 507 devto) fetch_devto ;; 508 github) fetch_github "$topic" ;; 509 stackoverflow) fetch_stackoverflow "$topic" ;; 510 npm) fetch_npm "$topic" ;; 511 crates) fetch_crates "$topic" ;; 512 coingecko) fetch_coingecko ;; 513 trivia) fetch_trivia ;; 514 uselessfact) fetch_uselessfact ;; 515 duckduckgo) fetch_duckduckgo "$topic" ;; 516 # v3.1 New sources - History & Archives 517 europeana) fetch_europeana "$topic" ;; 518 internet_archive) fetch_internet_archive "$topic" ;; 519 loc) fetch_loc "$topic" ;; 520 # v3.1 New sources - Psychology 521 psychologytoday) fetch_psychologytoday "$topic" ;; 522 apa_psychnet) fetch_apa_psychnet "$topic" ;; 523 # v3.1 New sources - Data & Statistics 524 worldbank) fetch_worldbank ;; 525 undata) fetch_undata "$topic" ;; 526 datahub) fetch_datahub ;; 527 # v3.1 New sources - Linguistics 528 conceptnet) fetch_conceptnet "$topic" ;; 529 etymonline) fetch_etymonline "$topic" ;; 530 wordnik) fetch_wordnik "$topic" ;; 531 # v3.1 New sources - Legal 532 courtlistener) fetch_courtlistener "$topic" ;; 533 federalregister) fetch_federalregister ;; 534 # v3.1 New sources - Music & Arts 535 musicbrainz) fetch_musicbrainz "$topic" ;; 536 artsy) fetch_artsy "$topic" ;; 537 rijksmuseum) fetch_rijksmuseum "$topic" ;; 538 # v3.1 New sources - Entertainment 539 tvmaze) fetch_tvmaze "$topic" ;; 540 openmoviedb) fetch_openmoviedb "$topic" ;; 541 # v3.1 New sources - Space 542 spacex) fetch_spacex ;; 543 nasa_neo) fetch_nasa_neo ;; 544 nasa_mars) fetch_nasa_mars ;; 545 # v3.1 New sources - Environment 546 openaq) fetch_openaq ;; 547 openweather_air) fetch_openweather_air ;; 548 # v3.1 New sources - Food 549 openfoodfacts) fetch_openfoodfacts "$topic" ;; 550 # v3.1 New sources - Random/Fun 551 numbers) fetch_numbers ;; 552 catfact) fetch_catfact ;; 553 chucknorris) fetch_chucknorris ;; 554 advice) fetch_advice ;; 555 bored) fetch_bored ;; 556 # v3.1 New sources - Research 557 core) fetch_core "$topic" ;; 558 unpaywall) fetch_unpaywall "$topic" ;; 559 # v3.1 New sources - Philosophy 560 stanford_plato) fetch_stanford_plato "$topic" ;; 561 # Default fallback 562 *) fetch_wikipedia "$topic" ;; 563 esac 564} 565 566# ============================================================================= 567# PERSISTENCE 568# ============================================================================= 569persist_learning() { 570 local content="$1" 571 local importance="${2:-0.85}" 572 local category="${3:-general}" 573 local source="${4:-unknown}" 574 575 [ -z "$content" ] && return 576 [ ${#content} -lt 30 ] && return 577 578 local timestamp=$(date +%s) 579 local escaped=$(echo "$content" | jq -Rs '.') 580 local temp=$(mktemp) 581 582 jq --argjson c "$escaped" \ 583 --argjson t "$timestamp" \ 584 --argjson i "$importance" \ 585 --arg cat "$category" \ 586 --arg src "$source" \ 587 '. + [{content: $c, timestamp: $t, importance: $i, category: $cat, source: $src}]' \ 588 "$LEARNED_FILE" > "$temp" && mv "$temp" "$LEARNED_FILE" 589} 590 591# ============================================================================= 592# LEARNING STATE TRACKING 593# ============================================================================= 594update_learning_state() { 595 local strategy="$1" 596 local category="$2" 597 local source="$3" 598 local success="$4" 599 600 local timestamp=$(date +%s) 601 local decisions=0 602 local successes=0 603 604 if [ -f "$LEARNING_STATE" ]; then 605 decisions=$(jq -r '.decisions // 0' "$LEARNING_STATE") 606 successes=$(jq -r '.successes // 0' "$LEARNING_STATE") 607 fi 608 609 decisions=$((decisions + 1)) 610 [ "$success" = "true" ] && successes=$((successes + 1)) 611 612 local rate=$(echo "scale=2; $successes / $decisions" | bc -l) 613 614 cat > "$LEARNING_STATE" << EOF 615{ 616 "timestamp": $timestamp, 617 "decisions": $decisions, 618 "successes": $successes, 619 "success_rate": $rate, 620 "last_strategy": "$strategy", 621 "last_category": "$category", 622 "last_source": "$source" 623} 624EOF 625} 626 627# ============================================================================= 628# MAIN LEARNING CYCLE 629# ============================================================================= 630learning_cycle() { 631 local cycle="$1" 632 633 # Choose strategy 634 local strategy=$(choose_strategy) 635 636 # Choose category based on strategy 637 local category=$(choose_category) 638 639 # Choose topic 640 local topic=$(choose_topic_for_category "$category") 641 642 # Get appropriate sources 643 local sources=$(get_sources_for_category "$category") 644 local source=$(choose_random_from "$sources") 645 646 echo "[LEARN] Cycle $cycle: $strategy | $category | $topic | $source" >> "$LOG" 647 648 # Fetch content 649 local content=$(fetch_from_source "$source" "$topic") 650 651 if [ -n "$content" ] && [ ${#content} -gt 30 ]; then 652 persist_learning "[$category:$source] $topic: $content" 0.85 "$category" "$source" 653 update_learning_state "$strategy" "$category" "$source" "true" 654 echo "[LEARN] Success: ${content:0:80}..." >> "$LOG" 655 return 0 656 else 657 update_learning_state "$strategy" "$category" "$source" "false" 658 echo "[LEARN] No content from $source for $topic" >> "$LOG" 659 return 1 660 fi 661} 662 663# ============================================================================= 664# MULTI-SOURCE LEARNING (fetch from multiple sources in parallel) 665# ============================================================================= 666multi_source_learn() { 667 local category=$(choose_category) 668 local topic=$(choose_topic_for_category "$category") 669 local sources=$(get_sources_for_category "$category") 670 671 echo "[MULTI] Category: $category | Topic: $topic" >> "$LOG" 672 673 local count=0 674 for source in $sources; do 675 local content=$(fetch_from_source "$source" "$topic") 676 if [ -n "$content" ] && [ ${#content} -gt 30 ]; then 677 persist_learning "[$category:$source] $topic: $content" 0.85 "$category" "$source" 678 count=$((count + 1)) 679 echo "[MULTI] Got content from $source" >> "$LOG" 680 fi 681 # Limit to 3 sources per topic 682 [ $count -ge 3 ] && break 683 done 684 685 echo "[MULTI] Learned from $count sources" >> "$LOG" 686} 687 688# ============================================================================= 689# MAIN DAEMON LOOP 690# ============================================================================= 691run_daemon() { 692 echo "==============================================" 693 echo "UNIFIED AUTONOMOUS LEARNER v3.0" 694 echo "==============================================" 695 echo "Strategies: ${#STRATEGIES[@]}" 696 echo "Categories: ${#CATEGORIES[@]}" 697 echo "==============================================" 698 699 local cycle=0 700 while true; do 701 cycle=$((cycle + 1)) 702 703 echo "" >> "$LOG" 704 echo "[UNIFIED-LEARNER] === Cycle $cycle - $(date +%H:%M:%S) ===" >> "$LOG" 705 706 # Primary learning cycle 707 learning_cycle "$cycle" 708 709 # Secondary learning with different source 710 learning_cycle "$cycle" 711 712 # Always check HackerNews for latest 713 local hn=$(fetch_hackernews) 714 if [ -n "$hn" ] && [ ${#hn} -gt 20 ]; then 715 persist_learning "[news:hackernews] $hn" 0.8 "technology" "hackernews" 716 fi 717 718 # Every 5 cycles, do multi-source learning 719 if [ $((cycle % 5)) -eq 0 ]; then 720 multi_source_learn 721 fi 722 723 # Log progress 724 if [ $((cycle % 10)) -eq 0 ]; then 725 local total=$(jq 'length' "$LEARNED_FILE" 2>/dev/null || echo "0") 726 echo "[UNIFIED-LEARNER] Cycle $cycle complete. Total items: $total" >> "$LOG" 727 echo "[Learner] Cycle $cycle | Total learned: $total" 728 fi 729 730 sleep 30 731 done 732} 733 734# ============================================================================= 735# CLI INTERFACE 736# ============================================================================= 737case "${1:-daemon}" in 738 daemon) 739 run_daemon 740 ;; 741 learn) 742 learning_cycle 1 743 ;; 744 multi) 745 multi_source_learn 746 ;; 747 status) 748 if [ -f "$LEARNING_STATE" ]; then 749 cat "$LEARNING_STATE" 750 else 751 echo '{"status": "not started"}' 752 fi 753 ;; 754 count) 755 jq 'length' "$LEARNED_FILE" 2>/dev/null || echo "0" 756 ;; 757 *) 758 echo "Usage: $0 {daemon|learn|multi|status|count}" 759 exit 1 760 ;; 761esac 762