Memelang: Token-Terse Query Language

HOLTWORK LLC released Memelang 11.04, a terse query DSL intermediate representation that it says cuts LLM token costs for text-to-SQL by translating low-token queries into higher-token SQL, citing a 20-token Memelang query that expands to 36 tokens of SQL. The patented language uses an axial grammar of Axis2, Axis1, Axis0 and Cell, with whitespace triggering new cells, and ships with a copy-and-paste prompt for LLMs plus examples covering filtering, grouping, sorting and similarity search. HOLTWORK positions Memelang for systems emitting billions of SQL queries daily, where the token reduction lowers compute spend.

Memelang Memelang is a terse query language that substantially reduces compute costs for LLMs emitting billions of SQL queries daily. Low-token Memelang is emitted as an intermediate representation which is then programatically translated into higher-token SQL for the database. Example: Memelang 20 tokens roles actor :$a="Mark Hamill";movie ;@ @ @;actor $a SQL 36 tokens SELECT x.actor,x.movie,y.movie,y.actor FROM roles AS x,roles AS y WHERE x.actor='Mark Hamill' AND y.id =x.id AND y.movie=x.movie Copy all code Copy-and-paste this code into your LLM to ask how Memelang works info@memelang.net | c 2026 HOLTWORK LLC | Patented MEMELANG is a terse query DSL IR for LLM text-to-SQL Axial grammar: Axis2 - Axis1 - Axis0 - Cell Whitespaces are syntactic and trigger "new Cell" Never space between operator/comparator/comma/flag and values MEMELANG VER = 11.04 basic syntax = ' table WS column WS ":$" var ":" "min"|"max"|"cnt"|"sum"|"avg"|"last"|"grp" ":" "asc"|"des" "<= " "\"" string "\"" "="|" ="|" "|"<"|" ="|"<="|"~"|" ~" string|int|float| "$" var |"@"|" " ";"' examples = ''' %mode=tab; roles id :int 0; rating :DESC="Decimal 0-5 star rating of performance";:dec 0.0;<=5; actor :DESC="Actor's full name";:str; movie :DESC="Movie's full name";:str; character :DESC="Character's full name";:str;; actors id :int 0; name :DESC="Actor's full name";:str; age :DESC="Actor's age in years";:int =0;<200;; movies id :int 0; description :DESC="Brief description of movie plot";:str; year :DESC="Year of production AD";:int 1800;<2100; genre scifi,drama,comedy,documentary;:str; title :DESC="Full movie title";:str;; actors name ; roles actor @;; movies title ; roles movie @;; roles id :gct=1;; roles movie :grp; actor :grp; character :gct=1;; actors id :gct=1;; movies id :gct=1;; %mode=qry; """ All movies """ movies ;; """ Every role """ roles ;; """ Titles and descriptions for movies """ movies title ; description ;; """ Actor name and ages """ actors name ; age ;; """ Actors age 41 years or older """ actors age =41; ;; """ Role 567 and 8901 """ roles id 567,8901; ;; """ Films with dystopian society narratives sim .33 """ movies description <= "dystopian"<0.33; ;; """ Movies titled with Star released in 1977 or 1980 """ movies title ~"Star"; year 1977,1980; ;; """ Actors named like Ana aged 20 to 35 inclusive """ actors name ~"Ana"; age =20;<=35; ;; """ Roles rated below 1.5 for movies before 1980 """ movies year <1980; title ; roles movie @; rating <1.5; ;; """ Roles sort rating descending, movie descending """ roles rating :des; movie :des;; """ All movies before 1970 ordered by year ascending """ movies year :asc<1970; ;; """ Average performer rating at least 4.2 """ roles rating :avg =4.2; actor :grp;; """ Minimum role rating by actor, low to high """ roles rating :min:asc; actor :grp;; """ Roles in movies mentioning robot rated 3+ """ movies description <= "robot"<=$sim; title ; roles movie @; rating =3;; """ Costars seen with Bruce Willis or Uma Thurman """ roles actor :$a~"Bruce Willis","Uma Thurman"; movie ;@ @ @; actor $a;; """ War stories before 1980: top 12 movies by minimum role rating """ movies year <1980; description <= "war"<=$sim; title :grp; roles movie @; rating :min:des;%beg=0;%lim=12;; """ Roles for movies Hero or House of Flying Daggers where actor name includes Li, actor A-Z """ movies title "Hero","House of Flying Daggers"; roles movie @; actor :asc~"Li";; """ Titles containing Here about robots between 1900 and 2000 """ movies title ~"Hero"; description <= "robot"; year =1900; <=2000;; %tab=movies; %val; %col=title; ~"Hero"; %col=description; <= "robot"; %col=year; =1900; <=2000;; %tab=movies; title description year; ~"Hero" <= "robot" =1900; <=2000;; %tab=movies; title; ~"Hero"; description; <= "robot"; year; =1900; <=2000;; %tab %val; movies : title~"Hero"; : description<= "robot"; : year =1900; <=2000;; ''' import re, sys, json from typing import Optional, Union, List, Iterator, Pattern, Any Err = SyntaxError SYNTAX CELL PATTERN = 'QUO', r'" ?: ^"\\\n\r |\\. "' , 'EMB', r'\ ?:-?\d+ ?:\.\d+ ? ?:\s ,\s -?\d+ ?:\.\d+ ? \ ' , 'MOD', r'<- |<= |< ' , 'CMP', r' =|<=| ~| =|=| |<|~| ' , 'BIND', r':\$\w+' , 'FLAG', r': a-zA-Z +' , 'VAR', r'\$\w+' , 'REL', r'@\d?|\^' , 'WLD', r' ' , 'EVAR', r'% a-zA-Z0-9 +' , 'SLOT', r' %? a-zA-Z0-9 +' , 'ASSN', r': a-zA-Z0-9 +' , 'TIM', r'\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}' , 'DEC', r'-?\d \.\d+' , 'INT', r'-?\d+' , 'ALN', r' A-Za-z A-Za-z0-9 ' , 'OR', r',' , 'WS', r'\s+' , 'MISMATCH', r'.' , CANON = {' ':' ='} CELL REGEX=re.compile "|".join f" ?P<{k} {p} " for k, p in CELL PATTERN PAD MODES = {'qry','tab'} FLAG KINDS = {'FLAG','BIND','EVAR','ASSN'} LIT KINDS = {'TIM','DEC','INT','ALN','QUO','EMB'} VAR KINDS = {'VAR','WLD','REL','EVAR','SLOT'} DAT KINDS = LIT KINDS | VAR KINDS RELCOORD = { '@0': '-1','-1' , '@1': '-1','-2' , '@2': '-1','-3' , '@3': '-1','-4' , '@4': '-1','-5' , '@' : '-1','+0' , '^' : '-1','end','+0' , } Atomic token class Tok: def init self, kind: str, src: str, canon: Optional str = None : self.kind = kind self.src = src canon = src if canon is None else canon self.canon = CANON.get canon or canon parser = {'QUO': json.loads, 'EMB': json.loads, 'DEC': float, 'INT': int}.get kind self.dat = parser src if parser else src def str self : return self.src def repr self : return self.canon def eq self, other : return repr self == repr other def hash self : return hash self.src def bool self : return bool self.src TOK NULL = Tok 'NULL', '' Sequence of tokens class Seq list Tok : opr: Tok = TOK NULL def init self, items : super . init items self.opr = TOK NULL def str self : return self.opr.src.join str t for t in self if len str t or t.kind=='HOLD' def repr self : return self.opr.src.join repr t for t in self Predicate expression class Cell: flag: Seq left: Seq comp: Tok right: Seq padded = False def init self, src: str : self.left = Seq self.flag = Seq self.comp = Tok 'EQL', '', '=' self.right = Seq Tok 'WLD', '', ' ' toks = for m in CELL REGEX.finditer src : kind = m.lastgroup text = m.group if kind == 'WS': continue if kind == 'MISMATCH': raise Err f'E TOK {text r}' toks.append Tok kind, text i, n = 0, len toks def peek : return toks i .kind if i < n else '' def take : nonlocal i if i = n: raise Err 'E EOF' t = toks i i += 1 return t FLAGS while peek in FLAG KINDS: self.flag.append take LEFT prefix MOD if peek == 'MOD': self.left.opr = take self.left.append Tok 'HOLD', '' t = take if not t.kind in DAT KINDS: raise Err 'E TERM DAT' self.left.append t COMPARATOR if peek == 'CMP': self.comp = take if not peek in DAT KINDS: raise Err 'E DAT' RIGHT values, OR-joined if peek in DAT KINDS: self.right.clear while peek in DAT KINDS: self.right.append take if peek == 'OR': self.right.opr = take if not peek in DAT KINDS: raise Err 'E OR TRAIL' if i = n: raise Err f'E EXPR TRAIL {toks i: }' PLACEHOLDER: OVERWRITE WITH YOUR EMBEDDING FUNCTION def vectorize self, tok: Tok - Tok: if tok.kind == 'EMB': return tok if tok.kind not in {'QUO', 'ALN'}: raise Err 'E EMBED' return Tok 'EMB', json.dumps 0.1, 0.2 @property def single self - Tok: return self.right 0 if self.comp.canon == '=' and len self.right == 1 else TOK NULL @property def literal self - Tok: tok = self.single return tok if tok.kind in LIT KINDS else TOK NULL def find self, kind:str - Tok: return next flag for flag in self.flag if flag.kind == kind , TOK NULL def bind self, tok: Tok : if tok not in self.flag: self.flag.append tok def str self - str: return f"{self.flag}{self.left}{self.comp}{self.right}" def repr self - str: return f"{self.flag r}{self.left r}{self.comp r}{self.right r}" def bool self - bool: return bool self.flag or self.left or self.right GRAMMAR class Axis list : src: str = '' sep: str = None SEPERATOR TOKEN sepreg: str = None SEPERATOR REG EXP sepstr: str = None SEPERATOR OUT empt: bool = False ALLOW EMPTY SUB-AXES? sub = None SUB-AXIS NAME def init self, src: str : if self.sep is None: raise Err 'E AXIS SEP' if not self.sepreg: self.sepreg = re.escape self.sep if not self.sepstr: self.sepstr = self.sep + ' ' self.src= src self.parse src.strip @property def regex self - Pattern str : return re.compile rf''' ?P<COMM """ ?: ? """ ^\n\r\\ |\\. """ | ?P<EXPQ " ?: ^"\\\n\r |\\. " | ?P<SEP {self.sepreg} | ?P<EXPM ^"{re.escape self.sep 0 } + | ?P<EXPS . ''', re.VERBOSE def parse self, src: str : exprs: List str = for m in self.regex.finditer src : if m.lastgroup == 'SEP': if exprs or self.empt: self.append self.sub "".join exprs exprs.clear elif m.lastgroup = 'COMM': exprs.append m.group debuffer expression if exprs: self.append self.sub "".join exprs def pull self, coords : value = self for coord in coords: value = value coord return value def str self - str: items = str t for t in self return self.sepstr.join s for s in items if s or self.empt "Table column value" semantic sequence of Cell predicates class Axis0 Axis : sep = ' ' sepstr = ' ' sepreg = r'\s+' sub = Cell AND-joined sequence of Axis0 class Axis1 Axis : sep = ';' sub = Axis0 OR-joined sequence of Axis1 class Axis2 Axis : sep = ';;' sub = Axis1 @staticmethod def coordrel coords, rel : rel = "+0" max 0, len coords - len rel + str op for op in rel out = for coord, op in zip coords, rel : if op == "end": v=-1 elif v:= coord + int op <0: raise ValueError 'E REL BIND' out.append v return out Rectangularize Left-pad Axis0 Replace relatives @ with coordinate vars $x y z Assign slots def rect self : env = {'mode':'qry'} slots = Tok 'EVAR','','%tab' , Tok 'EVAR','','%col' , Tok 'EVAR','','%val' for idx2, axis1 in enumerate self : idx = idx2, None, None for idx1, axis0 in enumerate axis1 : if not axis0: continue idx 1: = idx1, None %KEY=VAL %KEY=VAL if bool axis0 0 .find 'EVAR' : for cell in axis0: if not bool cell.find 'EVAR' : raise Err 'E AXIS MET' env cell.find 'EVAR' .canon 1: = cell.single.dat continue SLOT SLOT SLOT if axis0 0 .single.kind=='SLOT': slots= for cell in axis0: if cell.single.kind ='SLOT': raise Err 'E AXIS SLOT' if cell.single.canon 1 =='%': slots.append Tok 'EVAR', '', cell.single.canon 1: else: slots.append Tok 'ASSN','',':'+cell.single.canon continue if env 'mode' not in PAD MODES: continue Pad Axis0 axis0len=len slots if len axis0 axis0len: raise Err 'E AXIS0 LONG' for in range axis0len - len axis0 : cell = axis0.sub '@' cell.padded=True axis0.insert 0, cell for idx0, cell in enumerate axis0 : idx 2 = idx0 Assign slot cell.bind slots idx0 Replace relative tokens with coordinate vars for seq in cell.left, cell.right : for n, tok in enumerate seq : if tok.kind ='REL': continue coords=self.coordrel idx, RELCOORD tok.canon src=self.pull coords if src.literal.kind = 'NULL': seq n = src.literal continue name = '$'+' '.join map str, coords .replace '-1','E' seq n = Tok 'VAR', '', name src.bind Tok 'BIND', '', ':'+name PG SQL PH = '%s' Param = List Union int, float, str, list class SQL: def init self, sql: str = '', param: Optional Param = None : self.sql = sql self.param = if param is None else list param def sql value self - "SQL": return self def str self - str: sql = self.sql for p in self.param: sql = sql.replace PH, json.dumps p , 1 return sql def repr self - str: return str self.sql, self.param @staticmethod def uniq terms: "SQL" - list "SQL" : out, seen = , set for term in terms: if term is None: continue key = term.sql, tuple map repr, term.param if key in seen: continue seen.add key out.append term return out class CellSQL Cell : flag2agg = {':cnt':'COUNT', ':sum':'SUM', ':avg':'AVG', ':min':'MIN', ':max':'MAX', ':last':'MAX'} cmp2sql = {'~':' ILIKE ', ' ~':' NOT ILIKE '} mod2sql = {} def init self, src: str : super . init src self.base = self.alias = '' self.param = flags = {t.canon for t in self.flag if t.kind == 'FLAG'} self.agg = next sql for flag, sql in self.flag2agg.items if flag in flags , '' self.grouped = ':grp' in flags self.sort = 'ASC' if ':asc' in flags else 'DESC' if ':des' in flags else '' def deref self, bind: dict str, SQL , with agg: bool = True - Iterator SQL : for t in self.right: if t.kind == 'VAR': key = t.canon 1: if key not in bind: raise Err f'E VAR BIND {key}' ref = bind key else: yield SQL PH, t.dat continue if isinstance ref, CellSQL : yield ref.sql value with agg=with agg else: yield ref.sql value @property def sql groupby self - Optional SQL : if not self.grouped: return None if self.agg: raise Err 'E GRP AGG' return SQL self.base, self.param def sql value self, grouped: bool = False, alias: bool = False, order: bool = False, with agg: bool = True - SQL: sql, param = self.base, list self.param if self.left.opr.kind == 'MOD': sql = f' {sql}{self.left.opr.canon}{PH}::VECTOR ' param.append self.vectorize self.left 1 .canon agg = self.agg or 'MAX' if grouped and not self.grouped else '' if with agg else '' if agg: sql = f'{agg} {sql} ' if alias and self.alias: sql = f'{sql} AS {self.alias}' if order and self.sort: sql = f'{sql} {self.sort}' return SQL sql, param def sql clause self, bind: dict str, SQL - Optional tuple str, SQL : if not self.right or self.single.canon == ' ': return None left = self.sql value rights = list self.deref bind, with agg=bool self.agg comp = self.comp.canon sqlcomp = self.cmp2sql.get self.comp.canon or self.comp.canon if comp in {' ', '<', ' =', '<='} and len rights = 1: raise Err 'E COMP OR' items, params = , for right in rights: items.append f"CONCAT '%', {right.sql}, '%' " if comp in {'~', ' ~'} else right.sql params.extend right.param if len items == 1: beg, end = '', '' elif comp in {'=', '~'}: beg, end = 'ANY ARRAY ', ' ' elif comp in {' =', ' ~'}: beg, end = 'ALL ARRAY ', ' ' else: raise Err 'E COMP OR2' return 'having' if self.agg else 'where' , SQL f"{left.sql}{sqlcomp}{beg}{','.join items }{end}", left.param + params class Grid Axis2 : def select self - List SQL : self.rect out = env = {'mode':'qry', 'sim':0.5,'tab':'','taba':'','cola':''} for axis1 in self: env 'lim' , env 'beg' = 0, 0 bind = {k: SQL PH, v for k, v in env.items } tab cnt = 0 qry = {'select': , 'from': , 'fromall': , 'groupby': , 'where': , 'having': , 'orderby': } grouped = False allselected = False for axis0 in axis1: if env 'mode' ='qry': continue if axis0.src == ' ': allselected = True continue for idx0, cell in enumerate axis0 : print repr cell single = cell.single.dat if cell.padded or cell.single.kind=='SLOT': continue EVAR for TAB/COL evarval = cell.find 'EVAR' .canon if evarval=='%val': pass elif evarval: env evarval 1: = cell.single.dat bind evarval 1: =SQL PH, cell.single.dat if evarval=='%tab': if not re.fullmatch r' A-Za-z A-Za-z0-9 $ {0,62}', single : raise Err 'E TAB NAME' tab cnt += 1 env 'tab' =single env 'taba' =f"t{tab cnt}" qry 'from' .append SQL f"{env 'tab' } AS {env 'taba' }" qry 'fromall' .append env 'taba' elif evarval=='%col': if single == ' ': allselected = True elif not re.fullmatch r' A-Za-z + A-Za-z0-9 $ {0,62}', single : raise Err 'E COL NAME' env 'cola' = single continue SLOT for COL assnval = cell.find 'ASSN' .canon if assnval: env 'cola' = assnval 2: if not env 'taba' : raise Err 'E TAB REQ' valcell = CellSQL repr cell valcell.base = f"{env 'taba' }.{env 'cola' }" qry 'select' .append valcell if valcell.grouped: grouped = True qry 'groupby' .append valcell if valcell.sort: qry 'orderby' .append valcell clause = valcell.sql clause bind if clause: key, term = clause qry key .append term for flag in valcell.flag: if flag.kind = 'BIND': continue if flag.canon 2: in env: raise Err 'E ENV BIND' bind flag.canon 2: = valcell if not qry 'from' : out.append SQL continue parts = 'SELECT', ', ', SQL f"{a}. " for a in qry 'fromall' if allselected else SQL.uniq t.sql value grouped, True for t in qry 'select' , 'FROM', ', ', qry 'from' , 'WHERE', ' AND ', qry 'where' , 'GROUP BY', ', ', SQL.uniq t.sql groupby for t in qry 'groupby' , 'HAVING', ' AND ', qry 'having' , 'ORDER BY', ', ', SQL.uniq t.sql value grouped, False, True for t in qry 'orderby' , sql, param = , for keyword, sep, terms in parts: if not terms: continue sql.append f"{keyword} " + sep.join t.sql for t in terms for t in terms: param.extend t.param if env 'lim' : sql.append f"LIMIT {int env 'lim' }" if env 'beg' : sql.append f"OFFSET {int env 'beg' }" out.append SQL ' '.join sql , param return out This software is free to use for development, testing, and educational purposes. Commercial deployment, redistribution, or production use requires a separate license.