Library Guides
Coordinate an Agent Team (Builders)
Enable Agents on Every Surface (Builders)
Give Agents and Humans the Same Interface
Capabilities that work on every surface. One presenter, one contract, and one formatter serve both the CLI and the web. You build no separate integrations.
Add a Capability to Both Surfaces
Ship a feature to terminal and browser at once. One presenter and one registration cover both surfaces.
Build a Web Surface with libui
Assemble the browser side of a shared capability. Use components, reactive state, a global store, routes, slide decks, and an error boundary. A bad page then does not blank the whole app.
Build an Interactive REPL
Give humans and agents the same exploratory loop. One command set works at the prompt and as one-shot flags. State survives between sessions.
Render Templates with Project Overrides
Ship default templates with a package and let each project override any one of them. Two-tier Mustache resolution keeps generated output consistent across surfaces.
Publish a Documentation Site
Turn a directory of markdown into a static site agents and humans can both navigate. You get directory-style URLs, a companion markdown file for every page, and auto-generated llms.txt, sitemap, table of contents, and breadcrumbs.
Ground Agents in Context (Builders)
Give Agents Typed, Retrievable Knowledge
Agents answer relationship questions, look up context, and find related content. Typed knowledge infrastructure backs them, and it needs no external engines.
Query a Knowledge Graph
Answer relationship questions from an RDF graph index with triple patterns and type-filtered subject lists. You need no join logic and no SPARQL endpoint.
Look Up Context Fast
Retrieve exactly the context you need from a JSONL-backed index. Prefix, limit, and token-budget filters give you a subset. You do not load everything into memory.
Resolve a Resource
Give agents rich, typed context from a resource identifier. They get provenance, access control, and RDF content instead of raw files.
Search Semantically
Find related content by meaning instead of by keyword. A vector index returns ranked results, and you deploy no vector database.
Integrate with the Engineering Standard (Builders)
Turn Standard Definitions into Queryable Data
Engineering standard YAML becomes queryable data. Derive skill matrices, behaviour profiles, and agent configurations programmatically from a single load.
Derive a Skill Matrix or Agent Profile
Go from discipline, level, and track to a complete skill matrix or agent profile. You do not parse YAML by hand.
Keep Service Contracts Typed (Builders)
Keep Types Synced with Proto Definitions
Proto changes flow through to JavaScript types, MCP tools, and service endpoints automatically. One source of truth runs from definition to runtime.
Expose a Proto Method as an Agent Tool
A new gRPC method becomes an agent tool with one config entry. You write no glue code and no hand-written schema.
Ship a Service Endpoint
Ship a gRPC service with typed contracts, authentication, retries, and health checks. You do not reimplement the transport.
Run a Predictable Platform (Builders)
Manage Service Lifecycle from One Interface
Keep services running and surface problems before they escalate. One interface gives you supervision and observability.
Start, Stop, or Check a Service
Start, stop, restart, check status, and read logs through one interface. You do not need to remember each service's specific command.
Add Observability
Add structured, machine-readable logs and spans without a logging framework. Drop in a log line or a span and it works.
Distribute Skill Packs (Builders)
Distribute Skill Packs
Stage a skill pack into APM's .apm/ layout so a bare install pulls skills and agents together. One command turns a source tree into an installable repository.
Build Tarball and Git-Repo Packs
Build distributable packs in three formats from one set of skill and agent combinations. The formats are a flat tarball, an APM tarball, and a static bare git repo. Output is byte-identical across runs.
Publish a Skill Discovery Index
Emit a .well-known/skills/ discovery index so an agent can find and load skills over the web. You get a per-pack index plus a deduplicated index across every pack.
Generate Synthetic Environments (Builders)
Generate a Synthetic Dataset
Go from a DSL file to a complete, validated evaluation dataset. The pipeline generates entities, resolves prose, renders output, and verifies results.
The Substrate Contract
Provision identities, pick personas, and issue credentials on any Supabase-backed stack. To do this, implement three views in a substrate schema. You need no Forward Impact data model.
For product workflows, see Product Guides. For shared gRPC service integration, see Service Guides.