GALOR Technologies · AI agents that actPeoria, Illinois

GALOR World · agents that act under your approval

Meaninginto motion.

AI that does the work, shows the evidence, and waits for your yes. Bird runs your day. Mini builds your website. ANVIL fixes what’s broken.

Every claim here is evidence-backedRecord reviewed 29 Oct 2026 · see the Proof Room
01

What GALOR sells

Agents that act.
Priced to use today.

Six products, one rule: every agent does real work, shows its evidence, and waits for your approval before anything leaves your hands.

01 / THE FLAGSHIPFrom $20 / month

Bird by GALOR

An assistant that acts, not one that answers.

Bird reads your inbox, plans your day, books, follows up and reports back — every outside action waiting for your tap. ChatGPT talks. Bird works.

Every action under your approval rules · never moves money
02 / FASTEST WIN$74.25 build (25% off $99) + $19.99 / month hosting, billed yearly

Lil’ Tueiq Mini

Your website, built in one pass.

Describe your business. Lil’ Tueiq Mini plans the whole site, builds it, tests every page and delivers it. Four edits and a year of hosting included.

One payment · no monthly bills · your own domain
03 / BRING WHAT’S BROKENFree diagnostic · Pro $49 / month

ANVIL

Diagnosed, ranked, and the worst one fixed free.

Your agent misbehaves, your app crashes, your code won’t ship. ANVIL finds every problem, orders them by impact, and fixes the top one at no charge.

You keep the report and the fix
04 / FREE TO STARTFree · $20 / month unlimited

Remote Watchtower

Your computers, from anywhere, with any AI.

Connect ChatGPT, Claude or any agent to your own machines. You set what it may do; risky steps wait for your tap; a watchman calls you if a machine goes quiet.

10,000 free tool calls a month
05 / NEVER MISS A CALL$199 setup + $149 / month

Digital Receptionist

A receptionist that answers every call.

Knows your business, holds a real conversation, books the caller, and texts you before it hands anyone to a human. Free browser trial before you pay.

Free browser trial · number connected after payment
06 / LEARN TO BUILD THISFree · founding plans from $29 / month

GALOR Developer Network

The Developer Network.

Watch the builds live, get the Bird build manuals tier by tier, studio time, the Watchtower unlimited, and credits to build with. Free to join.

Founding rates lock for life
KEEP THE MOMENTUM

Every plan carries monthly credits, credits never expire, and every request shows its cost before it runs. Three founding clients can still have a website built for them with monthly care at a founding rate.

Founding packages ↗

GALOR FIELD GUIDE / 01

AI, opened up.

Follow the computation. Understand the boundaries. A closer look at how a language-model system turns a request into an answer.

DECODER-ONLY TRANSFORMER / REFERENCE ARCHITECTURE

This illustrates computation in a common language-model architecture. It is not a readout of private thoughts or a claim that every AI system works identically.

FIG. 01 / THE REQUEST PATHSELECT A STAGE BELOW
A request through a decoder-only language-model systemInstructions, history, and a user message enter context assembly. Optional retrieval adds selected records. The assembled input passes through a tokenizer, embeddings, transformer layers, and next-token selection. Generated tokens loop into the sequence. Optional tool calls pass through application checks and execution, then return results to context. Training supplies the weights separately.INPUT / APPLICATIONInstructions + conversationUser request, selected history, constraintsRetrieved recordsSelected documents + source identifiers01Context assemblyFormat messages · budget window · attach evidenceMODEL / INFERENCE02TokenizerText → vocabulary IDs03Embedding + positionToken vectors · sequence-order information04Decoder transformer × L layersCausal attention · feed-forward · residual pathsOutput head + next-token selectionVocabulary logits → decoding strategy → next tokenAPPEND TOKEN ID + REPEATReply to the userPresent answer · inspect sources or test resultsOptional tool requestValidate → authorize → executeTOOL RESULT + RECEIPT → CONTEXTBlue: inference path · amber: optional application/tool loop

Scroll sideways to inspect the full diagram.

01 / 06

First, assemble what the model can see.

The application combines your request with instructions and relevant conversation. If retrieval is enabled, selected records can be added too.

ILLUSTRATIVE TRACE
User: What does the annual GALOR plan include?
Retrieved plan: $314.13/year · one V1 · four edits.
WHAT TO WATCH

A missing or outdated source can produce a wrong answer before generation even starts.

THE SMALL LAB / NUMBERS YOU CAN INSPECT

Two calculations.
A much clearer picture.

Hand-made vectors and logits, computed in your browser. These are teaching examples, not measurements from a trained model.

FIG. 02 / CAUSAL ATTENTIONLIVE TOY CALCULATION

Which positions can contribute?

Select the query position. Earlier positions and the current one are available; later positions are masked.

The
18.7%
bridge
37.8%
is
43.5%
open
MASKED
WEIGHTED VALUE VECTOR / ∑ aᵢvᵢ[0.508, 0.442]These weights combine value vectors. They are not truth scores.
FIG. 03 / NEXT-TOKEN SELECTIONILLUSTRATIVE LOGITS

One next token, many possibilities.

Example context: “The bridge is”. Temperature changes a sampling distribution; it does not establish the condition of a real bridge.

More concentratedMore spread out
open
62.6%
closed
25.5%
safe
7.7%
old
4.2%
GREEDY CHOICE / HIGHEST LOGITThe bridge is openA sampled token may differ. In a real model, probabilities span the full vocabulary.

SEPARATE PROCESS / TRAINING

Where the weights come from.

Training and ordinary inference are different processes. During training, an objective drives weight updates. During a typical request, those weights are held fixed.

  1. 01Training examplesTokenized sequences
  2. 02Forward pass + lossCompare predictions with targets
  3. 03Gradients + optimizerUpdate trainable parameters
  4. 04Model checkpointWeights loaded for inference

A model can learn facts, patterns, and sometimes memorize training sequences. Its weights are not a dependable searchable archive. Conversation history, application memory, retrieved records, and the KV cache are distinct forms of state.

Engineer’s notes, limits, and primary references ↗

Read the diagram precisely.

The figure covers a common decoder language model. It omits batching, distributed serving, routing, multimodal encoders, and implementation-specific kernels. Reasoning models may generate additional intermediate tokens. A visible explanation is not a guaranteed account of all internal computation.

Tool execution and validation belong to the surrounding application. The illustrated checks are an engineering design pattern, not a promise that every agent implements them.

Prefill processes the supplied sequence; decoding extends it. Model weights, runtime KV state, and external records consume different resources and have different lifetimes.

02

GALOR World

One purpose. Many engines.

GALOR holds the direction. Each engine carries a distinct task. Proof returns to the center.

GALOR / ecosystem map

Light leaves. Evidence returns.

A signal traveling outward is only motion. Trust begins when the result travels back as something observable, attributable, and preserved.

One purpose / Bird example

See the built-in automation work.

Bird is the coordinating engine: it keeps the owner's intent at the center, assembles the useful context, and returns the result to the same private workspace.

Active stage01
Request

The owner names one outcome

A conversation becomes a concrete objective for Today, a Project, a File, or a connected service. The purpose stays human; Bird organizes the work around it.

Example tracePrepare today around the launch and surface anything still blocked.The request and chosen destination remain visible in the private workstation.
Built in sourceAgent loop · recall · connectors · key vault
Runs todayBey’s Bird on the GALOR machine · customer plans on /bird
Honest boundaryNothing sends, signs, pays or deletes without approval
Next proofFirst customer Bird, delivered and ledgered
Engineering lesson / closed-loop systems

The return path is where trust is built.

A reliable system defines success before execution, limits what may happen, measures the real result, and returns proof strong enough for another person to verify.

01 / INTENTName the state changeWrite the expected result, the failure condition, and the outcomes that must never occur before work begins.
02 / BOUNDARYConstrain the actionValidate identity and inputs. Set permissions, timeouts, retry rules, idempotency, and a recovery path.
03 / OBSERVATIONMeasure the worldRead the destination after execution. A model saying “done” is a claim; an observed state change is a measurement.
04 / EVIDENCEReturn durable proofPreserve tests, receipts, logs, artifacts, timestamps, and before-and-after state so the result can be audited or repaired.
The rule

An open loop creates confidence. A closed loop creates knowledge.

request → action → observation → evidence → decision
01 / 08 Running on Headquarters · diagnostics opening

Agent hardening engine

ANVIL

GALOR’s drill sergeant for other systems: it diagnoses a codebase or agent, ranks every problem, repairs them in order and drills the result. A fixed gate outside the model decides what ANVIL may do, and every action is written to a ledger.

Present evidence

  • The registry loader, conflict analyzer, deterministic gate, model adapter and typed tool registry are in the canonical repository.
  • A kernel test suite exists in source; this review did not rerun it.
  • Approval claimed inside model output, documents, web pages or tool results is denied by the gate as forged.
Workstation
ANVIL’s intake on galorweb.works/anvil, with the engine running privately on the GALOR Headquarters machine.
Domain
galorweb.works/anvil
How it works

Diagnostics and fixes happen on GALOR’s machine against a copy of the customer’s system; ANVIL never holds a customer’s production credentials.

Open galorweb.works/anvil
03

Work in the world

Made beautiful. Made useful.

Real websites designed to be useful, memorable, and ready for the people they serve.

GALOR World / next movement

Bring meaning.
We move.

Open the store Or email m.penningtonbey@galorweb.worksHuman judgment · disciplined motion · evidence