The local-first AI workspace that pairs deterministic execution with recursive agents — a complete environment to build, test and ship with confidence. Fully offline by default.
Most AI tools ask you to trade control for capability. DEXR refuses that trade — every result is private, reproducible and provable.
No cloud, no accounts, no telemetry. Your projects and files never leave the machine. DEXR works fully offline out of the box.
The NeuroRoute engine uses deterministic routing and policy selection. Same input, same output — every run, on every machine.
Break a task down, execute within bounded depth, validate, repeat. A mesh of specialised agents self-corrects until the rules pass.
Every build is quined and byte-compared against a canonical capsule. If it doesn't match, it isn't approved. Nothing to trust — everything to check.
A desktop shell wraps a deterministic routing engine, a recursive agent mesh and a versioned file workspace — with an optional local model runtime that never touches the network.
Every task travels the same bounded, auditable path. If validation fails, DEXR repairs and re-validates — up to four times — before it ever calls a task done.
You provide a task or request
Task analysed & decomposed
Agents run within bounded limits
Output checked against rules
Bounded retry · 0–4 attempts
Result committed & logged
DEXR builds in a deterministic environment, hashes the output into a canonical capsule, then rebuilds from scratch and compares byte-for-byte. Approval is earned, not assumed.
DEXR 1.6 ships as a Quine AIO: the application carries a sealed capsule of its own source (DXRCAP01) and can reproduce its complete source tree into an empty directory — then prove the copy is exact, generation after generation.
The reproduction kernel is statically verified before every run. An AST-enforced import allowlist (base64, hashlib, os, sys) forbids dynamic execution, subprocess creation, environment inspection and all network APIs. It writes only into an explicitly empty directory — and never imports or runs its output.
Reproduction runs in Python isolated mode with a pinned deterministic environment (LC_ALL=C, TZ=UTC, NPROC=1, hash seed 0), stdin disconnected and output captured — plus network-namespace isolation via unshare -n where the host permits it.
Proven candidates land in a content-addressed registry with an atomic pointer move — the running source tree is never overwritten. Promotion requires the successful proof file and a candidate whose root matches all three proven generation roots.
DEXR has no cloud to leak to. It runs offline, and the single exception is a loopback call to a local runtime you control:
HTTP → 127.0.0.1
DEXR is in private beta. Book early access and we'll send you a build for your platform — no sign-up, no subscription, no data leaving your machine.