Search

Claude Code skill that orchestrates large projects using Architect/Developer/QA subagents with persistent state

Reusable Claude Code skills and hooks for Semantu projects

Track OpenAI, Claude, Gemini and OpenAI-compatible models then give solutions to improve your agent system.

Unified TypeScript SDK for AI providers (OpenAI, Anthropic, Gemini, Ollama) with 72 built-in tools, workflow engine, and mode system for building AI-powered applications

The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools

CFSA Pipeline — Constraint-First Specification Architecture for AI agents. Production-grade from line one.

`contextqmd` is a standalone CLI for ContextQMD. It talks to the registry API directly and manages a local docs cache and search index powered by QMD (SQLite + BM25 + vector search).

Official Python SDK for Tilde: an agent-native data platform that combines versioned object storage with sandboxed compute

AI-Agent-friendly database CLI for seekdb / OceanBase

AI-powered literature reading assistant with multi-agent orchestration and hybrid RAG

Agora Agent Client Toolkit — real-time voice agent integration for web

Long Life Memory for LLMs — structured project knowledge for AI agents and humans

Matrx AI Engine — unified AI orchestration backend with multi-provider LLM support, streaming, tool execution, and conversation persistence.

No description available

🛡️ Security scanner for AI agents, MCP servers & plugins — 30 rules, AST taint tracking, cross-file analysis, kill chain detection. Free & open source alternative to Snyk Agent Scan.

Agent core of Proj.Amrita

A multi-agent, event-driven payment automation platform built with .NET 10 and Aspire 13. Users create "watch requests" for products; autonomous agents monitor prices, request human approval via A2P messaging, and execute payments.

AI Agent 驱动的投资分析框架：策略配置 → 量化筛选 → LLM 多章深度分析 → 多基准回测验证

PIXELANIM8 8-битный генератор GIF

Runtime containment kernel for LLM agents. Enforces budget, step, retry, and circuit-breaker limits before the model call.