Independent software / In development

Small tools.
Ambitious possibilities.

A collection of focused AI agent and infrastructure products. Each starts with one engineering problem worth solving.

RelaymossPrivate preview

Give every agent task a way forward.

A task queue designed for AI workflows: visible handoffs, deliberate retries, and a clear place to resume when a run needs another try.

Agent task orchestration
GategrainPrivate preview

Keep people in the important decisions.

An approval inbox for agent actions. Put the proposed change, supporting context, and next step in front of a person before your workflow continues.

Human approvals for agents
ToolfernPrivate preview

Catch tool mismatches before the next run.

A proposed contract-checking layer for agent tools. Compare schemas, inspect inputs, and make interface changes visible before they surprise your workflow.

Agent tool contract checks
MembrayPrivate preview

Know what your agent remembers. And why.

A memory workspace designed to keep agent context readable, versioned, and reviewable. Trace a saved fact back to its source before carrying it into the next task.

Versioned agent memory
TracegrovePrivate preview

Turn a tangled run into a clear story.

A timeline for understanding agent work. Bring tool calls, intermediate outputs, and handoffs into one readable view so you can see how a run reached its result.

Agent run observability
EvalwickPrivate preview

Give your next prompt change a fair test.

A workspace for small, repeatable agent evaluations. Keep test cases, expected behavior, and review notes together so a change can be assessed against the same examples.

Agent evaluation workflows
FetchhollowPrivate preview

Find stale context before your agents do.

A freshness monitor concept for retrieval pipelines. Track source changes, indexing checkpoints, and unresolved gaps so your team can see which knowledge needs another pass.

Retrieval source freshness
BudgetreedPrivate preview

Know where the next agent call fits.

A usage workspace for teams building with agents. Group model and tool activity by workflow, review budget thresholds, and spot runs that need a closer look.

Agent usage visibility
DriftparcelPrivate preview

Make API changes easier to act on.

A review inbox for changing API contracts. Compare snapshots, collect relevant differences, and give the engineer responsible a useful starting point for the update.

API change review
SessionloomPrivate preview

Pick up browser workflows with better context.

A checkpoint workspace for browser-based agents. Capture progress, record what needs attention, and make the next handoff understandable when a workflow pauses.

Browser workflow checkpoints