Search

AI Agent Token Saver - 减少多 Agent 平台 token 消耗的综合工具（支持 Claude Code, Codex, OpenClaw, Cursor, Aider, Continue, Windsurf）

The package manager for AI agent skills — install, compose, and publish skills for Claude Code, Cursor, Codex, and Gemini CLI

Morphy — universal autonomous AI agent with multi-agent swarm execution

Agentic AI Security & Multi Agent Management: Agent Agnostic Platform. Offers Protection against Prompt Injection via Granular Action Scope & Cryptographically Protected Instruction Channel

Noeta runtime engine: the kernel (protocols / core / runtime / storage / guards / observers / read_models) plus the agent materials (policies / tools / providers / context), the execution machinery, the agent identity layer (spec / registry) and the official presets — everything needed to run an agent in-process.

See what your AI agents are doing. Two lines of code.

Kairo Code — AI coding agent in your terminal, powered by FreeModel and 20+ providers

LangChain chat model wrapper for the Claude Code Agent SDK — Mimir distribution of langchain-claude-code with bundled adapter fixes (upstream PRs #2/#4/#6, unmerged). Import package remains ``langchain_claude_code``.

Python SDK for the RuoYi AI engine (OpenAI-compatible chat, embeddings, rerank, agent forward, traces, providers).

Pi extension: Claude Code-style subagents. Delegate tasks to isolated, per-agent provider/model-configurable specialists (general-purpose, explore, plan) defined as Markdown files, driven entirely through tools (no TUI required).

CrewAI tool for SibFly — measured ground motion (subsidence & uplift) per US address, from NASA Sentinel-1 InSAR

Reserved for Omnigent community use and to prevent malicious use.

LangChain-native equivalent of Google ADK's RemoteA2aAgent — invoke remote A2A agents as LangChain Runnables and tools

Shared AgentOps contracts, validators, and GoalOps primitives.

A lightweight image generation connector for AI agents.

A multi-agent teams implementation using LangGraph (Blackboard & Mailbox architecture)

Persistent typed memory for AI coding agents — install & forget: auto-inject context via git hooks, 13 memory types, confidence tracking, conflict detection, grounded QA, codebase graphs

A coding agent built on LLM

Lightweight multi-agent AI pipeline framework with parallel DAG execution, tool calling, and cost tracking

Runtime security firewall for LLM agents — four-checkpoint scan engine, local-first with an optional hosted cloud tier