Search

Chain Pi prompt templates and skills into a single prompt

A modern, offline-first content management platform built with Nuxt 4, featuring page and email builder, file and data management, and AI-powered document processing

Repo-issue–driven autopilot runner

Command-line interface for TypeSafe AI's Jev evaluation model — evaluate typed questions against shared state and get structured JSON back

Typed, policy-driven decision workflows on top of the TypeSafe AI Jev SDK

Troubleshooting knowledge base for ops mode — distilled postmortem cases stored in the access hub, searched before diagnosing and recorded after resolving.

empty

Thinking-level fallback for dsh: wraps the llm/stream waterfall and re-issues an auxiliary model call the provider rejected for naming an unsupported thinking level (e.g. Google: "Thinking level MINIMAL is not supported for this model"). On that provider

Local-first personal knowledge base with RAG: import PDFs, notes and email, hybrid vector + keyword search, and cited Q&A over your own documents. Runs entirely on your machine.

Cost budget for dsh web_search: bounds the number of billable provider search requests a `web_search` call may initiate (per call / per turn / per session / whole subagent tree) and denies the call with an actionable error once the budget is exhausted. Ex

Agent long-term-memory layer for the Vercel AI SDK, backed by the typesafe-ai/jev evaluation model. Write/retrieve/evict gates are all selection decisions -- memories are stored, retrieved and evicted verbatim, never summarized or rewritten.

Rubric-based eval harness for LLM/agent outputs, backed by the typesafe-ai/jev evaluation model via Vercel AI Gateway. Cheap enough (~$0.04/1M input tokens, one round trip per case) to run on every PR.

Separate real LLM failures from flaky ones, with confidence intervals.

Blockchain Commons Provenance Mark for TypeScript - A cryptographically-secured system for establishing and verifying the authenticity of works

Verified intake for Ring Partner API webhooks: HMAC SHA-256 signature verification, typed event payloads, and idempotent deduplication. Framework-agnostic, zero dependencies.

I-Lang protocol specification: AI-native communication protocol for structured human-to-AI and AI-to-AI workflows, with reference validators

Drizzle (mssql) adapter for @aiquants/authz-core: defineAuthzSchema factory, getEffectivePermissions, and row/column scope application helpers.

Attestia scripts: session open, session close, nightly close, hours, scheduler. Plain Node, no dependencies.

Native i18next catalog tooling for the TransLocale cloud service.

SvelteKit tooling and request-isolated i18next context for TransLocale cloud catalogs.