Search

OpenBox governance SDK for DeepAgents (langchain-ai/deepagents)

Multi-agent AI system built on AutoGen for autonomous task execution

Multi-agent text handoffs discard KV-cache and attention state. AVP transfers that state directly — 51-78% fewer tokens, 1.5-5x faster.

CLI tool for tracking claims and contradictions across multi-agent LLM systems

AI model: DataManagement-AI/Agentic-Data-1

AI model: yangzhch6/mcpfactory-qwen3-8b-newreward-step340

AI model: yangzhch6/mcpfactory-qwen3-8b-newreward-step300

AI model: yangzhch6/mcpfactory-qwen3-1.7b-newreward-step340

AI model: yangzhch6/mcpfactory-qwen3-1.7b-newreward-step300

AI-powered geospatial analysis platform built on Google ADK. 21/21 agentic design patterns, AgentOps 3.9/5 maturity (Google P2P 78%), 3-phase CI/CD, StorageManager data lake (s3://+postgis://), 34 toolsets (200+ tools), 21 Skills, 170+ REST APIs, USD cost guard, HITL approval, Feature Flags, Terraform IaC. v15.1

🏃 Sovereign Agent Evaluation Framework - Zero cloud dependencies. Local-only, cryptographically signed benchmarks for AI agents. npm run demo = instant evals.

Scoped, time-bound, cryptographically-signed capabilities for AI agents. Zero dependencies. Sovereign by design.

Turn a single Claude Code session into a full Web3 website development studio. 36 agents. 37 workflows. 25 design styles. Build official websites, DApps, token pages, and NFT projects on BNB Chain.

Self-spawning AI agents born from tasks. Zero pre-built agents. Distributed memory. 4-layer guardrails. Fossil record. Groq + LLaMA.

Replay Debugger for AI Agents

📺 视频学习助手: 自动生成 B站/YouTube/本地视频思维导图、笔记与总结。AI Video Learning Assistant: Auto-generate Mind Maps, Notes & Summaries. 支持播客分析与视频索引，开源平替。 (Bilibili/YouTube/Local/Podcast)

An AI-driven character content generation system that implements a complete workflow from character creation, schedule planning, event planning, director output to video performance generation.

AI Skill設計・作成・改善ツールキット（skill-creator-pro + skill-creator + skill-refiner）をプロジェクトにインストールするCLI

Self-evolving skill ecosystem for AI agents. Skills and projects co-evolve through multi-judge evaluation and a Pareto frontier.

UrsaMU development skill installer for Claude Code, Gemini CLI, Cursor, Codex, Antigravity, and OpenCode.