DOC · MICRODC-MECH-001v3.4 · BETA

A simple asynchronous job queue for distributed AI inference. Submit, route, execute, deliver — explained in detail below.

The four-step lifecycle.

§01 · FLOW
STEP 01━━━▶

Submit job

Validated, added to the distributed queue with model spec, input prompt, and config parameters.

STEP 02━━━▶

Intelligent routing

Scheduler matches the job to suitable workers based on model requirements, GPU capabilities, and current load.

STEP 03━━━▶

Worker execution

Workers pull jobs, load models (cached if available), execute inference, submit results back encrypted and authenticated.

STEP 04

Result delivery

Results stored; notifications via webhook or polling. Configurable retention period.

Why asynchronous?

§02 · DESIGN CHOICE
CAP · COST

Cost effective

Save up to 90% vs dedicated GPU instances. Pay only for actual compute time, not idle resources.

CAP · SCALE

Massively scalable

Process thousands of jobs in parallel across the distributed worker network. No infrastructure to manage.

CAP · DX

Developer friendly

Simple API, comprehensive SDKs, detailed documentation. Start integrating in minutes.

Context-aware routing.

§03 · TIERS

Every job is labeled with a context tier (1–4) at submission based on prompt length. Workers declare a max_context_tier via heartbeat — the scheduler only sends them jobs they can run efficiently. Better latency everywhere; revenue opportunities for low-spec hardware.

TierPrompt sizeDefault routing
Tier 10–1.5K charsAll workers
Tier 21.5K–6K charsWorkers with tier ≥ 2
Tier 36K–24K charsWorkers with tier ≥ 3
Tier 424K+ charsWorkers with tier 4 (high-end GPUs)

End-to-end encryption flow.

§04 · ENCRYPTION

Payload encrypted with AES-256-GCM before it leaves the client — the server stores ciphertext and never inspects, logs, or decrypts it. The payload key is escrowed only until acknowledgment and released only to the MicroDC-managed worker that claims the job. Results are encrypted to your public key: only you can read them, cryptographically. Full architecture writeup →

STEP 01━━━▶

Client encrypts

Symmetric key generated on your machine, payload encrypted with AES-256-GCM, your RSA public key sent for results. Your private key never leaves your machine.

STEP 02━━━▶

Server: opaque ciphertext

Ciphertext stored as-is; the payload key is escrowed, never used, and handed only to the claiming worker — a MicroDC-managed node with the admin-approved encryption capability.

STEP 03━━━▶

Worker decrypts & runs

In-memory decryption, inference on a local model — then the result is encrypted with a fresh one-time key wrapped to your public key.

STEP 04

You decrypt

Client decrypts with the private key that never left your machine. All key material is deleted from the platform on acknowledgment.

Container job lifecycle.

§05 · CONTAINERS

Docker jobs get live log streaming and per-job heartbeats. Routes only to workers advertising the docker capability.

STEP 01━━━▶

Submit with image

Provide Docker image name, optional args/env, script and code files as inputs.

STEP 02━━━▶

Worker claims

Only workers advertising docker see container jobs. Image pulled and started.

STEP 03━━━▶

Live log heartbeat

Workers ping POST /jobs/{id}/heartbeat with log lines. Resets timeout for long runs.

STEP 04

Result + cleanup

Exit code, stdout/stderr, output files submitted. Local cache means faster subsequent runs.

§06 · ENGAGE

Try it. It's fast.

Free credits to start. No credit card. Five minutes from signup to first job result.