AI Engineering

Product Prioritization ranks requirements, features, or backlog items with RICE, ICE, MoSCoW, or Kano. Use it when you need a transparent priority matrix, impact/effort view, and sprint allocation proposal.

User Stories breaks an epic into independent user stories with Given-When-Then acceptance criteria, INVEST checks, and story point estimates. Use it to turn a large requirement into a story map and sprint plan.

BitRouter routes OpenAI- or Anthropic-shaped requests through a self-hosted local proxy on 127.0.0.1:4356. Use it to install, configure, launch, and troubleshoot provider routing for coding agents.

Evaluating BitRouter Routes classifies and submits evaluation results for BitRouter route decisions or Eval Exchange subjects. Use it when you need task-native, human, enterprise, agentic, or generic evaluators to judge a request, episode, or task outcome.

Project Cairn turns project work into reusable knowledge by keeping validated lessons, decisions, and notes in project files. Use it to initialize or maintain Cairn docs, audit drift, cite external knowledge, and prepare reusable experience for graduation.

Run BitRouter Benchmark guides Harbor benchmark runs through BitRouter, from choosing a dataset and agent to confirming routed providers and models. It also covers resume, audit, sharing, publication, and optional BitRouter OSS on AWS setup.

SLM Cache stores repeated file reads, search results, and tool output behind stable keys. Use it to check for a hit first, then fill on miss; it fails open on errors and never blocks the task.

SLM Governance defines role-based behavior for SuperLocalMemory in governed workspaces. It covers retention policies, audit trails, GDPR export and erasure, and when agents may read or write under admin, member, or viewer access.

Slm Graph indexes a codebase as a structural graph and answers questions about callers, callees, inheritance, and change impact. Use it to navigate unfamiliar code, assemble review context, and check what changed since the last index.

SLM Graph indexes a codebase as a structural graph and answers questions about callers, callees, inheritance, blast radius, and semantic code search. Use it to understand how code connects, what changes may break, and to assemble review context.

SLM Loop runs bounded, gate-verified iterations using SuperLocalMemory as a durable ledger. Use it for tasks with a checkable acceptance condition, and report the exact terminal status when the independent gate passes or a bound stops the run.

SLM Mesh lets multiple AI agent sessions on the same machine discover each other, share transient state, send messages, and lock files to avoid conflicts. Use it when coordinating parallel work across sessions via MCP.