Skip to content

Stoat

Commercial · JasperFx Forthcoming

Stoat

The design-time surface for Critter Stack development

The model, the work it implies, and the evidence that closes it - one host, one browser tab.

Stoat is where a Critter Stack system is designed and where the work to build it is coordinated. Draw the system as an Event Model, turn it into a plan of work that AI agents can claim across repositories, keep what those agents learn between sessions, and watch the Bobcat test runs that say the work is done.

Stoat is a work in progress and not yet generally available. When it ships it will be bundled with every paid CritterWatch license at no additional cost.

Not yet generally available. Preview the documentation now; Stoat ships bundled with paid CritterWatch licenses.

What Stoat Gives You

The Event Model as a document

Slices, chapters, hotspots, and the specs bound to them, assembled from your running application and drawn on one canvas.

Work as a cross-repo plan

A graph of GitHub issues, NuGet publishes, and test-run gates across repositories. Stoat derives what is ready.

Agents park, they don't poll

AI agents wait on upstream dependencies and package publishes over MCP without burning tokens in a loop.

Memory that outlives the session

What one agent session learned, the next one recalls, scoped to a session, a repository, or everything.

The run board

Every Bobcat suite on the box, live, with retries and flakiness reported honestly and CTRF and JUnit exports for CI.

Bundled with CritterWatch

Included with every paid CritterWatch license when it ships.

Start Here

New to Stoat? These is the post to read first, in order.

  1. 1CritterWatch 1.1, Bobcat 1.0, AI Skills 1.17, and a First Look at StoatOne release wave, four products: CritterWatch 1.1 with 83 MCP tools, cron schedules, a Document Explorer and a long list of scalability fixes earned on real systems; Bobcat 1.0, the successor to Storyteller and our answer for spec-driven development; AI Skills 1.17; and the first public preview of Stoat.

Latest on Stoat

5 posts from the JasperFx blog cover Stoat. Here are the most recent.

Critter Stack AI Skills 1.18: Caught Up With CritterWatch 1.2Critter Stack AI Skills 1.18: Caught Up With CritterWatch 1.2AI Skills 1.18 brings every CritterWatch skill up to the 1.2 MCP tools, checked tool by tool against the source: a new sagas skill, the get_command_outcome tool, dead letters ranged by failure time, event queries over bodies and metadata, and six corrections to advice that had gone wrong, including the Prometheus series names every Grafana example used.CritterWatch 1.1, Bobcat 1.0, AI Skills 1.17, and a First Look at StoatCritterWatch 1.1, Bobcat 1.0, AI Skills 1.17, and a First Look at StoatOne release wave, four products: CritterWatch 1.1 with 83 MCP tools, cron schedules, a Document Explorer and a long list of scalability fixes earned on real systems; Bobcat 1.0, the successor to Storyteller and our answer for spec-driven development; AI Skills 1.17; and the first public preview of Stoat.Critter Stack AI Skills 1.17: One Month of Releases, Checked Against the SourceCritter Stack AI Skills 1.17: One Month of Releases, Checked Against the SourceAI Skills 1.17 is the result of a review of everything Wolverine, Marten, CritterWatch, Bobcat and Stoat shipped in the last month, checked against the product source rather than the changelogs. Thirty-six skill changes, seven of them correcting advice that had quietly gone wrong, and the CritterWatch 1.1 paired updates that were waiting in 1.16.Critter Stack AI Skills 1.14: Troubleshooting Guides, and Why the Skills Pay for ThemselvesCritter Stack AI Skills 1.14: Troubleshooting Guides, and Why the Skills Pay for ThemselvesAI Skills 1.14 ships eight troubleshooting skills that decode Critter Stack exceptions from the stack trace. It's also a good excuse to make the bigger case: skills that know Wolverine's idioms produce terser code, cheaper agent sessions, and an agent that can actually reason through concurrency, parallelism, and production diagnostics.Full-Text, Vector, and Hybrid Search in Polecat, Fisher, and MartenFull-Text, Vector, and Hybrid Search in Polecat, Fisher, and MartenPolecat, Fisher, and Marten now share one search surface: full-text search, vector similarity search with filters, hybrid search fused by reciprocal rank fusion, and event-sourced vector projections, on SQL Server 2025, SQLite, and PostgreSQL. Here's what each store gives you, how it works, and where they differ.

Questions about Stoat?

Talk to us about licensing, rollout, or how Stoat fits your team.

The Rest of the Stack