Search

可复用的 Agent 框架库，支持中国大模型

AI Agent Skill for HODL.DANCE — memecoin launchpad on BSC

Transform AI agent instruction and skill files into searchable documentation portals

Domain-agnostic knowledge graph memory for AI agents. Zero-config, local-first, SQLite-powered. Works as OpenClaw skill (CLI) or plugin (auto-hook).

A fast, cross-platform package manager for AI agent skills

Multi-tier long-term memory for LLM agents. Install: pip install smolAmem. Import: import mneme.

Production-grade SEO setup skill for Claude Code, Cursor, Windsurf, Cline, Roo Code, GitHub Copilot, Aider, Continue.dev, and Zed. Analyzes your project first, asks before writing, then implements exactly what you confirmed.

OpenAI Agents SDK tracing bridge for Phionyx runtime evidence — every Trace and Span emitted by the SDK becomes a signed, hash-chained envelope entry.

Native LangChain + LangGraph adapters for Phionyx runtime evidence — every chain, tool call, and LLM invocation emits a signed, hash-chained envelope entry.

assistant-ui powered React UI for LangGraph-backed agents

Embed [Zuno](https://github.com/iarmankhan/zuno) — a typed AI agent harness with sandboxed tool execution and AI SDK v6 native streaming — directly into your Node app. **No service to deploy, no database to provision.**

Claude Agent Framework - Reusable framework for coordinating AI agents and humans in software projects

AI-powered CLI for Ketoy — scaffold, write, migrate, diagnose, and build .ktx bundles for Android. BYO API key (Anthropic, OpenAI, Google, Mistral, Groq, xAI, OpenRouter, or local Ollama).

A clone of Claude Code using Replicate and Ollama models

Evaluation framework for testing and scoring Agentium agents

Time-travel debugger for AI agents. Record any production run, replay any failure.

Multi-Agent Reinforcement Learning environments with very large numbers of agents.

SDK, contracts, and invoice agent helpers for Loka merchant payments on Celo.

Specification-Driven Development Extended - LLM-agnostic spec-first governance framework with role enforcement, telemetry, and GitHub integration

CLI for evaluating Claude Code skills and AI agents