diff --git a/src/tokeniser.test.ts b/src/tokeniser.test.ts
new file mode 100644
index 000000000..10ce37ea1
--- /dev/null
+++ b/src/tokeniser.test.ts
@@ -0,0 +1,186 @@
+import {
+  isBlockEnd,
+  isBlockStart,
+  isNumber,
+  isOperator,
+  isParanEnd,
+  isParanStart,
+  isString,
+  isWhitespace,
+  isWord,
+  lexer,
+} from "./tokeniser";
+
+describe("testing helpers", () => {
+  it("test is number", () => {
+    expect(isNumber("1")).toBe(true);
+    expect(isNumber("5?")).toBe(true);
+    expect(isNumber("5 + 6")).toBe(true);
+    expect(isNumber("5 + a")).toBe(true);
+
+    expect(isNumber("a")).toBe(false);
+    expect(isNumber("?")).toBe(false);
+    expect(isNumber("?5")).toBe(false);
+  });
+  it("test is whitespace", () => {
+    expect(isWhitespace(" ")).toBe(true);
+    expect(isWhitespace("  ")).toBe(true);
+    expect(isWhitespace(" a")).toBe(true);
+    expect(isWhitespace("a ")).toBe(true);
+
+    expect(isWhitespace("a")).toBe(false);
+    expect(isWhitespace("?")).toBe(false);
+  });
+  it("test is word", () => {
+    expect(isWord("a")).toBe(true);
+    expect(isWord("a ")).toBe(true);
+    expect(isWord("a5")).toBe(true);
+    expect(isWord("a5a")).toBe(true);
+
+    expect(isWord("5")).toBe(false);
+    expect(isWord("5a")).toBe(false);
+    expect(isWord("5a5")).toBe(false);
+  });
+  it("test is string", () => {
+    expect(isString('""')).toBe(true);
+    expect(isString('"a"')).toBe(true);
+    expect(isString('"a" ')).toBe(true);
+    expect(isString('"a"5')).toBe(true);
+    expect(isString("'a'5")).toBe(true);
+    expect(isString('"with escaped \\" backslash"')).toBe(true);
+
+    expect(isString('"')).toBe(false);
+    expect(isString('"a')).toBe(false);
+    expect(isString('a"')).toBe(false);
+    expect(isString(' "a"')).toBe(false);
+    expect(isString('5"a"')).toBe(false);
+  });
+  it("test is operator", () => {
+    expect(isOperator("+")).toBe(true);
+    expect(isOperator("+ ")).toBe(true);
+    expect(isOperator("-")).toBe(true);
+    expect(isOperator("<=")).toBe(true);
+    expect(isOperator("<= ")).toBe(true);
+    expect(isOperator(">=")).toBe(true);
+    expect(isOperator(">= ")).toBe(true);
+    expect(isOperator("> ")).toBe(true);
+    expect(isOperator("< ")).toBe(true);
+    expect(isOperator("| ")).toBe(true);
+    expect(isOperator("|> ")).toBe(true);
+    expect(isOperator("^ ")).toBe(true);
+    expect(isOperator("% ")).toBe(true);
+    expect(isOperator("+* ")).toBe(true);
+
+    expect(isOperator("5 + 5")).toBe(false);
+    expect(isOperator("a")).toBe(false);
+    expect(isOperator("a+")).toBe(false);
+    expect(isOperator("a+5")).toBe(false);
+    expect(isOperator("5a+5")).toBe(false);
+  });
+  it("test is paran start", () => {
+    expect(isParanStart("(")).toBe(true);
+    expect(isParanStart("( ")).toBe(true);
+    expect(isParanStart("(5")).toBe(true);
+    expect(isParanStart("(5 ")).toBe(true);
+    expect(isParanStart("(5 + 5")).toBe(true);
+    expect(isParanStart("(5 + 5)")).toBe(true);
+    expect(isParanStart("(5 + 5) ")).toBe(true);
+
+    expect(isParanStart("5")).toBe(false);
+    expect(isParanStart("5 + 5")).toBe(false);
+    expect(isParanStart("5( + 5)")).toBe(false);
+    expect(isParanStart(" ( + 5)")).toBe(false);
+  });
+  it("test is paran end", () => {
+    expect(isParanEnd(")")).toBe(true);
+    expect(isParanEnd(") ")).toBe(true);
+    expect(isParanEnd(")5")).toBe(true);
+    expect(isParanEnd(")5 ")).toBe(true);
+
+    expect(isParanEnd("5")).toBe(false);
+    expect(isParanEnd("5 + 5")).toBe(false);
+    expect(isParanEnd("5) + 5")).toBe(false);
+    expect(isParanEnd(" ) + 5")).toBe(false);
+  });
+  it("test is block start", () => {
+    expect(isBlockStart("{")).toBe(true);
+    expect(isBlockStart("{ ")).toBe(true);
+    expect(isBlockStart("{5")).toBe(true);
+    expect(isBlockStart("{a")).toBe(true);
+    expect(isBlockStart("{5 ")).toBe(true);
+
+    expect(isBlockStart("5")).toBe(false);
+    expect(isBlockStart("5 + 5")).toBe(false);
+    expect(isBlockStart("5{ + 5")).toBe(false);
+    expect(isBlockStart("a{ + 5")).toBe(false);
+    expect(isBlockStart(" { + 5")).toBe(false);
+  });
+  it("test is block end", () => {
+    expect(isBlockEnd("}")).toBe(true);
+    expect(isBlockEnd("} ")).toBe(true);
+    expect(isBlockEnd("}5")).toBe(true);
+    expect(isBlockEnd("}5 ")).toBe(true);
+
+    expect(isBlockEnd("5")).toBe(false);
+    expect(isBlockEnd("5 + 5")).toBe(false);
+    expect(isBlockEnd("5} + 5")).toBe(false);
+    expect(isBlockEnd(" } + 5")).toBe(false);
+  });
+
+});
+
+describe("testing lexer", () => {
+  it("test lexer", () => {
+    expect(lexer("1 + 2")).toEqual([
+      { type: "number", value: "1" },
+      { type: "operator", value: "+" },
+      { type: "number", value: "2" },
+    ]);
+    expect(lexer("54 + 22500 + 6")).toEqual([
+      { type: "number", value: "54" },
+      { type: "operator", value: "+" },
+      { type: "number", value: "22500" },
+      { type: "operator", value: "+" },
+      { type: "number", value: "6" },
+    ]);
+    expect(lexer("a + bo + t5 - 6")).toEqual([
+      { type: "word", value: "a" },
+      { type: "operator", value: "+" },
+      { type: "word", value: "bo" },
+      { type: "operator", value: "+" },
+      { type: "word", value: "t5" },
+      { type: "operator", value: "-" },
+      { type: "number", value: "6" },
+    ]);
+    expect(lexer('a + "a str" - 6')).toEqual([
+      { type: "word", value: "a" },
+      { type: "operator", value: "+" },
+      { type: "string", value: '"a str"' },
+      { type: "operator", value: "-" },
+      { type: "number", value: "6" },
+    ]);
+    const sameWithOrWithoutWhiteSpaces = [
+      { type: "word", value: "a" },
+      { type: "operator", value: "+" },
+      { type: "string", value: "'str'" },
+    ];
+    expect(lexer("a + 'str'")).toEqual(sameWithOrWithoutWhiteSpaces);
+    expect(lexer("a +'str'")).toEqual(sameWithOrWithoutWhiteSpaces);
+
+    expect(lexer("a + (sick)")).toEqual([
+      { type: "word", value: "a" },
+      { type: "operator", value: "+" },
+      { type: "brace", value: "(" },
+      { type: "word", value: "sick" },
+      { type: "brace", value: ")" },
+    ]);
+
+    expect(lexer("a + {sick}")).toEqual([
+      { type: "word", value: "a" },
+      { type: "operator", value: "+" },
+      { type: "brace", value: "{" },
+      { type: "word", value: "sick" },
+      { type: "brace", value: "}" },
+    ]);
+  });
+});
diff --git a/src/tokeniser.ts b/src/tokeniser.ts
new file mode 100644
index 000000000..44aef8c3b
--- /dev/null
+++ b/src/tokeniser.ts
@@ -0,0 +1,119 @@
+import fsp from "node:fs/promises";
+
+const NUMBER = /^[0-9]+/;
+const WHITESPACE = /\s+/;
+const WORD = /^[a-zA-Z_][a-zA-Z0-9_]*/;
+// regex that captures everything between two non escaped quotes and the quotes aren't captured in the match
+const STRING = /^(["'])(?:(?=(\\?))\2.)*?\1/;
+// regex for operators
+const OPERATOR = /^[>=|<=|+|\-|*|/|>|<|^|%]/;
+const BLOCK_START = /^\{/
+const BLOCK_END = /^\}/
+const PARAN_START = /^\(/;
+const PARAN_END = /^\)/;
+
+
+export const isNumber = (character: string) => NUMBER.test(character);
+export const isWhitespace = (character: string) => WHITESPACE.test(character);
+export const isWord = (character: string) => WORD.test(character);
+export const isString = (character: string) => STRING.test(character);
+export const isOperator = (character: string) => OPERATOR.test(character);
+export const isBlockStart = (character: string) => BLOCK_START.test(character);
+export const isBlockEnd = (character: string) => BLOCK_END.test(character);
+export const isParanStart = (character: string) => PARAN_START.test(character);
+export const isParanEnd = (character: string) => PARAN_END.test(character);
+
+
+function matchFirst(str: string, regex: RegExp) {
+  const theMatch = str.match(regex);
+  if (!theMatch) {
+    throw new Error("Should always be a match:" + str);
+  }
+  return theMatch[0];
+}
+
+// type TokenTypes = 
+interface Token {
+  type: 'number' | 'word' | 'operator' | 'string' | 'brace'
+  value: string;
+}
+
+export const lexer = (str: string): Token[] => {
+  const tokens: Token[] = [];
+  let currentIndex = 0;
+
+  const returnTokenAtIndex = (
+    str: string,
+    startIndex: number
+  ): Token | null => {
+    const strFromIndex = str.slice(startIndex);
+    if (isOperator(strFromIndex)) {
+      return {
+        type: "operator",
+        value: matchFirst(strFromIndex, OPERATOR),
+      };
+    }
+    if (isString(strFromIndex)) {
+      return {
+        type: "string",
+        value: matchFirst(strFromIndex, STRING),
+      };
+    }
+    if(isParanEnd(strFromIndex)){
+      return {
+        type: "brace",
+        value: matchFirst(strFromIndex, PARAN_END),
+      };
+    }
+    if(isParanStart(strFromIndex)){
+      return {
+        type: "brace",
+        value: matchFirst(strFromIndex, PARAN_START),
+      };
+    }
+    if(isBlockStart(strFromIndex)){
+      return {
+        type: "brace",
+        value: matchFirst(strFromIndex, BLOCK_START),
+      };
+    }
+    if(isBlockEnd(strFromIndex)){
+      return {
+        type: "brace",
+        value: matchFirst(strFromIndex, BLOCK_END),
+      };
+    }
+    if (isNumber(strFromIndex)) {
+      return {
+        type: "number",
+        value: matchFirst(strFromIndex, NUMBER),
+      };
+    }
+    if(isWord(strFromIndex)) {
+      return {
+        type: "word",
+        value: matchFirst(strFromIndex, WORD),
+      };
+    }
+    return null;
+  };
+  while (currentIndex < str.length) {
+    const token = returnTokenAtIndex(str, currentIndex);
+    if (token) {
+      tokens.push(token);
+      currentIndex += token.value.length;
+    } else {
+      currentIndex++;
+    }
+  }
+
+  return tokens
+};
+
+async function main() {
+  const example1 = await fsp.readFile("./examples/addition.cado", "ascii");
+  const parsed = lexer(example1);
+  console.log(parsed);
+}
+
+// main()