Search

Reusable AI agent skills, project playbook templates, and a small operator-controlled runtime harness.

Interactive agent + git commit orchestration. Requires git and a backend CLI (Claude Code or OpenCode); the GitHub CLI (gh) is optional, used for the dashboard's GitHub-ID committer view.

Drop-in replacement for @anthropic-ai/claude-agent-sdk that adds OpenTelemetry instrumentation for Astro deployments.

High-performance unified Docker and Podman container management library

A developer-first AI observability, security, and reliability toolkit for LLM applications and AI agents.

Run Claude Code or Codex on your machine against your Spryng board (the Spryng Local Agent / claude-code-runner).

SAIDEX — Structured AI Data EXtraction: validated Pydantic models from LLM responses with automatic retry, fallback, and an agentic tool loop

Autonomous, DSL-fluent coding agent built on the Claude Agent SDK — point it at any DSL directory and it plans, codes, debugs, verifies, and self-extends.

Static budget certificates for LLM-agent workflows (LangGraph / CrewAI / OpenAI Agents SDK). Backed by a machine-checked (Lean 4) cost-soundness theorem.

Scaffold a new agentic AI application with Next.js, Better Auth, and AI SDK

Verigent trust verification for LangChain agents, chains, and tools

Verigent trust verification for CrewAI agent delegation

Local-first agent memory: an Obsidian markdown vault as source of truth, with a rebuildable DuckDB index.

Turn any SKILL.md into a runnable AI Agent

Agentopolis — Habbo-style visualization of Claude Code agents building your repo as a city

LangChain governance middleware for Aegis ACP

Terminal orchestration for Open Code and Claude Code agents

Enhanced tool output rendering with syntax highlighting, file icons, tree views, FFF search, and paste chip formatting

The repo map your coding agent is forced to use — ~98% fewer tokens (up to 99.9% per task) to understand a TS/JS codebase. A queryable, ranked ts-morph code-relationship map: PageRank hubs, Aider-style symbol ranking, a token-budgeted digest, and a single

TripleS software engineering agent orchestrator — skill plugin for Claude Code, Cursor, Copilot, Codex, and Windsurf