Overview
TPipe is an Agent Operating Substrate - infrastructure that autonomous AI agents run inside, rather than a library they call. It's built for agents that operate for days, not minutes, and it addresses the two failure modes that most agent frameworks leave to the developer: memory loss across long sessions and silent failure when something goes wrong mid-task. Core capabilities:
- Reasoning Pipes - structured JSON control over token prediction that forces any LLM to think in a defined pattern (Chain-of-Draft, Role Play, and 6 other modes), independent of whether the model has native reasoning. Reported 75% token reduction and 78% latency decrease with Chain-of-Draft.
- ContextBank - thread-safe, persistent memory across distributed runs, with weighted lorebook-style retrieval, substring-triggered activation, and token-budget-aware selection. Designed to survive 120+ turn conversations without degradation.
- Pipelines - sequential orchestration with declarative pause, resume, and jump points, plus 18 named hooks (DITL) across the pipe/pipeline lifecycle for validation, transformation, and human-in-the-loop review.
- Manifold, Junction, and DistributionGrid - three distinct multi-agent patterns: manager-worker state machines, democratic voting/handoff between agents, and peer-to-peer cluster orchestration (8,773 LOC of distributed infrastructure).
- PCP (Pipe Context Protocol) - secure, multi-language function/tool calling across Stdio, HTTP, Python, Kotlin, and JavaScript transports, with per-language access controls.
- KillSwitch and loop limits - forced, non-catchable termination on token overrun or runaway loops, so failures stop cleanly instead of degrading silently. Deployment: TPipe is JVM-native (Kotlin, JVM 24) and headless-first. It also ships as a GraalVM Native Image - a ~50MB binary with no JVM at runtime, sub-128MB memory footprint, millisecond startup, and support for Linux, macOS, Windows, and ARM. It works with any LLM reachable through a standard transport executor, including AWS Bedrock, Ollama, and OpenRouter.
Proof points from production use: Autogenesis, a headless game-master agent, runs 25 rounds and 120+ turns of inference without degradation. TPipeWriter maintains coherence across a 300-page manuscript through multi-stage refinement. TStep is a multi-agent debugger that tests, captures crashes, and steps through code via DAP/ADB. TPipe is a persistent substrate with topdown token governance and cross-session memory built in from the start.
Highlights
- Reasoning Pipes force structured, auditable thinking in any LLM via Chain-of-Draft and 7 other modes - <br>a reported 75% token reduction, independent of the model's native reasoning ability.
- ContextBank gives agents persistent, thread-safe memory across distributed runs, with weighted retrieval<br>and token-budget-aware selection - built for 120+ turn tasks without context loss.
- Three multi-agent patterns (Manifold, Junction, DistributionGrid) plus a GraalVM native binary - 50MB,<br>no JVM at runtime, millisecond startup, sub-128MB footprint.
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Description | Cost/12 months |
|---|---|---|
Base Enterprise | A fee for access to the platform and its core capabilities. | $35,000.00 |
The following dimensions are not included in the contract terms, which will be charged based on your usage.
Dimension | Description | Cost/unit |
|---|---|---|
usage_based | Pricing based on the customer's actual usage of the platform. | $0.01 |
Dimensions summary
Top-of-mind questions for buyers
Vendor refund policy
All fees are non-refundable and non-cancellable except as required by law.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Resources
Vendor resources
Support
Vendor support
Email support services are available from Monday to Friday.
Email:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.