Every account gets an isolated agent workspace with its own team and memory. What makes the platform compound is a shared, privacy-scrubbed learning layer — so generalized lessons can help the wider fleet without exposing private server data.
Every paid plan deploys the full team into your own workspace. You’re not buying capability unlocks, only scale. The Orchestrator reads intent and hands each job to the right specialist, and every action is metered and capped.
Your team’s main loop. Reads Discord messages and server events, answers directly, delegates to a specialist, and keeps your account context available.
Analyzes server evidence and prepares bounded operations for crashes, power, files, and modpacks when the connected capability is verified.
Answers your players’ and staff questions from your own docs, rules, and chat history. Read-only and focused on fast answers.
Watches chat and enforces your rules through a cost-safe pipeline: a deterministic pre-filter (zero tokens), then a small triage model, then an Orchestrator escalation only when needed.
Builds mods, plugins, and integrations for you — including crash-fix patches — compiled and boot-tested in an isolated scratch sandbox, then delivered via a signed link or pushed to your server on your approval.
The Development Team’s read-only second pair of eyes: adversarially reviews the Developer’s code and crash-fix patches for correctness, concurrency, loader/version compatibility, supply-chain provenance and security — then escalates findings. It reviews and reports; it never ships or mutates.
Plus the platform services Tectonic Agents runs for everyone
Onboarding
The signup → connect bot → add server → pick agents journey. Tectonic Agents handles the setup so you can focus on your community and servers.
Billing & metering
Tracks each action, enforces your caps, and keeps pay-as-you-go spend bounded. This is a platform service, not another agent persona.
Learning curator
Turns public sources and privacy-scrubbed lessons into reusable knowledge for the agent team.
Credits track real usage. Each request is billed by the tokens the agent actually consumes to do the work — a quick chat costs a little, a deep crash-diff or build costs more. You pay for work done, not per seat.
A credit is pinned to a fixed slice of baseline-model usage, so its value stays predictable. Heavier models cost proportionally more credits because their tokens genuinely cost more — the rate is derived from real token cost, never a number someone made up.
Run each agent on the model that fits its job — a light model for Support, a heavyweight for crash-diffs. You pick per agent, and credits reflect what each model’s tokens actually cost.
Every paid tier carries a credit cap and a hard-stop, so a runaway agent can never overspend or surprise you. Temporary scratch is included from Starter up.
This is how the platform compounds. Isolated agent teams contribute lessons up through a privacy scrub, and read a shared knowledge base and skills library back down. Every server’s lessons make every other server’s agents smarter. The shared knowledge base and learning curator are designed to compound useful lessons; the ingest pipeline is still being built out, so we do not claim a pre-indexed catalog of mods as live.
A curated store of facts, crash-signature → cause → fix entries, light how-tos, and public mod/modpack metadata. The team can reuse generalized lessons instead of starting from zero.
Versioned, industry-grade how-to procedures any agent can load and reuse. The agent that solved a Forge mixin conflict once turns that fix into a skill the whole fleet can run instantly.
When an agent learns something worth sharing, identifiers, paths, IPs, and world names are removed before the lesson is generalized. Account-private data never enters the shared layer.
A platform learning service scrubs, generalizes, deduplicates, and promotes lessons without exposing raw account data.
Sharing knowledge and sharing data are not the same thing. Your raw data — servers, secrets, chat, memory — stays sealed inside the account boundary. Only generalized, scrubbed lessons can leave, and only through the platform learning service.
Your agent team gets its own workspace and context. Other customers cannot access your servers, secrets, or operating history.
Every action is checked against the allowlist you control — observe, propose, or act — before it can affect a connected system.
Run on managed keys with token-priced credits. If you bring your own key, it is encrypted before storage and never shown back to you.
Agents run on platform-managed keys with token-priced credits. Pick a model per agent — heavier models spend more, lighter ones less.
Use a supported provider or compatible endpoint when available. Keys are encrypted before storage, and destinations are checked against private network addresses.
Managed plans from $9/mo. Full agent team on every paid tier. Cancel anytime.