by hwfengcs · Agent Tool · ★ 50
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
SDYJ Multi Agents English | 中文 SDYJ Multi Agents 是一个基于 LangGraph 的多智能体研究框架。它把开放式研究任务拆成“意图识别 - 计划生成 - 人工审核 - 多源检索 - 综合报告”的可控工作流，并重点提供 Trace v2、deterministic replay、证据追踪和可作为 CI gate 的 benchmark。 为什么值得关注 多 Agent 工作流：Coordinator、Planner、Researcher、Rapporteur 分工协作。 Human-in-the-loop：执行研究前先展示计划，用户可批准或反馈修改。 多模型适配：支持 DeepSeek、OpenAI、Claude、Gemini，统一 LLM 抽象层。 多源检索：集成 Tavily、arXiv，并预留 MCP 工具适配接口。 证据驱动报告：检索结果会规范化为 证据项，自动去重并保留 URL、domain、query、发布时间和相关性分数。 Trace v2 可观测性：每次运行都会生成事件时间线，记录节点、LLM 调用、工具调用、routing decision、latency、错误、报告指标和 replay cache。 Deterministic Replay：可用已记录的 LLM/tool I/O 重放一次历史运行，复现失败路径，不调用真实 API。 实用 Benchmark：内置困难 Agent 场景，支持阈值 gate、summary compare、trace completeness 和离线确定性检查。 可复现工程：提供 Python 包配置、CLI 入口、单元测试、CI、示例输出和架构文档。 架构概览 更完整的设计说明见 [docs/architect
| Stars | 50 |
| Forks | 7 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 64.8855506615949/100 |
| Open Issues | 2 |
| Last Updated | 2026-05-28 |
| Created | 2025-10-04 |
| Platforms | python |
| Est. Tokens | ~42k |
These tools work well together with SDYJ_Multi_Agents for enhanced workflows:
Looking for a SDYJ_Multi_Agents alternative? If you're comparing SDYJ_Multi_Agents with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Structured Data Extractor for AI Agents. Search your documents or the web for specific data and get it back in
AI agent with multi-agent orchestration, autonomous cognitive systems, and a full management dashboard
Benchmarking the gap between AI agent hype and architecture. Three agent archetypes, 73-point performance spre
Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, Git
The Complete AI Development Toolkit for Claude Code — 113 skills, 37 agents, 212 hooks. Production-ready patte
A curated list of tools, papers, and datasets for applying AI to cybersecurity tasks. This list primarily focu
Explore other popular agent tool tools:
SDYJ_Multi_Agents is A LangGraph-powered multi-agent deep research system featuring task planning, human-in-the-loop review, multi-source retrieval, evidence-grounded report generation, full tracing and reproducible evalu. It is categorized as a Agent Tool with 50 GitHub stars.
SDYJ_Multi_Agents is primarily written in Python. It covers topics such as agent, agent-skills, agentic-workflow.
You can find installation instructions and usage details in the SDYJ_Multi_Agents GitHub repository at github.com/hwfengcs/SDYJ_Multi_Agents. The project has 50 stars and 7 forks, indicating an active community.
SDYJ_Multi_Agents is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to SDYJ_Multi_Agents on Agent Skills Hub include open-extract, captain-claw, ai-agents-reality-check. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.