Patent pending · U.S. Provisional Application No. 64/082,906
Conductor Relay coordinates AI work across your model team, checks, repairs, and approval gates — turning raw model output into governed output your team knows how to handle.
Save money running local or hybrid — see the cost model calculator.
Watch CR Lite check, repair, label, and gate a model’s output — 49 seconds.
Tools like Ollama and LM Studio can run a model on your computer. But they do not tell you whether the answer is correct enough to use, safe to save, or ready to send somewhere else.
A model can give you code, JSON, reports, or plans that look good at first glance. But the output may have broken syntax, missing fields, fake claims, hidden mistakes, or unsafe content.
A normal validator can tell you something failed. CR Lite goes further. It checks the output, gives the model clear repair feedback, checks again, and shows you the final result.
The model can write the answer. A second model can review it. But CR Lite's checks and gates decide the label. The model does not decide what is trusted, saved, exported, committed, deployed, or acted on.
CR Lite sits on top of your runtime — bring your own model. It takes whatever the model produced and puts it through a clear pipeline before you ever rely on it.
CR Lite turns your prompt into a clear task so the model cannot silently change what it is supposed to do.
Your model creates the first output.
CR Lite checks the output for things like syntax, format, missing requirements, source needs, secrets, and basic runtime problems.
When something fails, CR Lite gives the model clear feedback and asks for a better version.
CR Lite gives the final result a label:
VERIFIED passed the needed checks
UNVERIFIED_REVIEW usable for review, not fully proven
NEEDS_REVIEW something important still needs checking
BEST_EFFORT best result available, not safe to trust without review
CR Lite shows the answer and the label. You decide whether to use it, review it, save it, export it, commit it, deploy it, or try again.
Checks find the problems. Repairs fix what they can. Confidence labels the result. You always see the best available output.
CR Lite is not just a chat box. It is a local AI workbench with tools, skills, memory, Git safety, and repair loops around the model.
The model can ask for help. CR Lite decides what is safe to run.
A normal AI tool call can be risky. It may read the wrong file, write to the wrong place, run the wrong command, or act before you approve it. CR Lite adds rules around tool use.
Safe read-only tools can run when needed. Risky actions like writes, commits, deploys, money movement, secrets, or production changes require approval.
These tools provide evidence. They do not decide what is trusted.
AI coding gets risky when it touches real files. CR Lite can help you work with Git safely. It can inspect changes, explain diffs, check what files were touched, and help prepare a clean commit — without letting the model silently push or mutate your repo.
CR Lite lets AI help with code and Git, but keeps repo changes gated, scoped, and reviewable.
Skills are saved ways of doing common jobs. Instead of asking the model to figure out the process every time, CR Lite can use a skill with clear steps, rules, and checks.
Without skills, every prompt starts from scratch. With skills, CR Lite can follow a known process:
CR Lite can use memory, but it does not dump all memory into every prompt. Each role gets only what it needs.
The model writes the answer. A validator model may give advice. But CR Lite's checks and gates decide the label — and what you can safely do next.
CR Lite shows you what passed, what failed, what was repaired, and what still needs review. You decide what gets trusted, saved, exported, committed, deployed, or acted on.
CR Lite works with any model. Use one model for every role, or give each role its own — local, an API, or a mix. No matter what you connect, the label is set by CR Lite's own checks — fixed rules and tests, not another AI grading the work.
A single local model fills every role. The simplest way to start.
One model writes the answer; a second model reviews it.
Give Report, Code, Tool-call, and Validator each their own model.
Run a local model and add a stronger API checker when you need it.
Connect one model to every role, or wire different models to Report, Code, Tool-call, and Validator. Either way, the label comes from CR Lite's checks — fixed rules and tests, not another AI grading the work.
Local-first: when you use local models, work runs on-device. The result still carries a confidence label and a gate before save, export, or action.
When an answer fails, CR Lite can give the model clear feedback and ask for a better version. It does not just say "wrong." It says what failed and what needs to change.
CR Lite can keep useful project context so future runs do not start from zero. Memory is scoped. The model only receives the context needed for that role and task.
For advanced use, CR Lite can use past failures and successful repairs to improve future checks and workflows.
The free hosted demo uses controlled scenarios only. It shows the CR Lite workflow without exposing the engine, accepting private repo data, or running arbitrary customer code.
CR Lite checks, repairs, and labels local AI output before you rely on it.
The model proposes. You decide.