Усі репозиторії публічного реєстру з цим тегом — із тем GitHub або ключових слів, які публікують їхні реєстри пакетів. Здоров'я вимірюється за тією ж версіонованою методологією, що й решта реєстру.
Agent skill — find & plug in free, ready-made StoryKit design blocks (charts, widgets, illustrations, themes) over the public StoryKit asset API (storykit.space).
Charts & dashboards for AI agents — 47 deterministic chart types + dashboard tiling, as an MCP server and pure-SVG engine. Tiny specs in, retina charts out, 100% local.
Production-grade Harness Engineering Framework for multi-developer AI coding agents — guardrails, state persistence, direction alignment, and self-correction across 6 IDEs. Zero dependencies.
Local research agent — one command, a cited answer with its trust signals: source-authority mix, lexical citation verification, confidence, cost. CLI + MCP server. Runs on your own LLM router; nightly public report card. Zero hosted dependencies.
JavaScript · TypeScript★ 2↓ 360/міс14 вер. 2026 р.
Enhanced fork of OpenWolf — a token-conscious second brain for Claude Code, with bounded storage, self-maintenance (openwolf doctor), .wolfignore scoping, and tunable retention. AGPL-3.0.
TypeScript · JavaScript★ 6↓ 2 762/міс14 вер. 2026 р.
Fluent, chainable TypeScript SDK: configure models, enable tools, stream events, then fetch text, JSON, run details or token stats in one call via .asText() or .allowTools('Read', 'Write'). Multi-level logging plus live onMessage/onToolUse callbacks give deep, CLI-compatible observability.
Shared, persistent memory for AI coding agents — Claude Code & Codex share one local-first, event-sourced project brain that survives sessions and syncs across machines. No server, no API key required.
Vendor-neutral control plane for AI coding agents. Deterministic CLI surface for context fetch, verify, and progress. Stable in v1.0 for claude-code / codex / generic; cursor / gemini-cli experimental.