Plasmod 为智能体提供跨会话的持久记忆和结构化上下文，统一保存状态、事件、证据、关系与可复用知识，使长期运行的系统能够在需要时找回正确的信息。Plasmod gives agents persistent memory and structured context across sessions. It preserves state, events, evidence, relationships and reusable knowledge so long-running systems can retrieve the right information when needed.

适合Best for需要持久状态、可追溯证据和可复用上下文的长期运行智能体。Long-running agents that need persistent state, traceable evidence and reusable context.

Hypha 是用于构建和运行智能体系统、工作流与工具链的模块化框架。它在统一运行时中连接智能体、模型、工具、记忆和执行逻辑，让系统更容易组合、观察与扩展。Hypha is a modular framework for building and running agent systems, workflows and toolchains. It connects agents, models, tools, memory and execution logic in one observable, extensible runtime.

适合Best for需要整合模型、工具和记忆，并保持执行过程可追踪的开发团队。Teams that need to connect models, tools and memory while keeping execution traceable.

AgentInfer Kit 将推理、评估、基准测试和训练连接为持续改进流程，帮助团队比较模型与策略、理解智能体行为，并将评估结果转化为后续性能提升。AgentInfer Kit links reasoning, evaluation, benchmarking and training into a continuous improvement loop, helping teams compare models and strategies and turn evaluation results into measurable gains.

适合Best for希望从评估走向模型、策略和工作流持续优化的智能体研发团队。Agent R&D teams moving from evaluation to continuous model, policy and workflow improvement.

BEAM 面向多智能体系统中的通信与协调问题，帮助智能体交换真正需要的信息，减少冗余消息、重复推理、Token 消耗与通信延迟。BEAM addresses communication and coordination in multi-agent systems, helping agents exchange only the information they need while reducing redundant messages, repeated reasoning, token use and latency.

适合Best for关注通信成本、响应延迟和协作质量的分布式多智能体系统。Distributed multi-agent systems focused on communication cost, latency and coordination quality.

THETA 面向社会科学与知识密集型研究的结构化文本分析，支持处理大规模文本、识别主题与关系、追踪变化，并将结论连接到代表性证据。THETA provides structured text analysis for social science and knowledge-intensive research, supporting large corpora, topic and relationship discovery, change tracking and evidence-linked findings.

适合Best for处理复杂文本集合并重视证据链的研究人员与分析团队。Researchers and analysis teams working with complex text collections and evidence chains.

宽窄·orbit 是用于情绪复盘、自我观察和持续回顾的 AI 产品。它借助易经的语言与结构，帮助用户整理想法、观察情绪模式，并在长期使用中重新理解过往记录。KuanZhai · orbit is an AI product for emotional reflection, self-observation and ongoing review. It uses the language and structure of the I Ching to help people organize thoughts and revisit patterns over time.

适合Best for希望建立结构化复盘空间并持续理解自身状态的用户。People who want a structured reflection space and a longer-term view of their own state.

OpenLab 将问题和想法转化为可执行的 AI 辅助实验，帮助用户规划流程、运行分析、生成图表与表格，并将结果整理为结构化报告。OpenLab turns questions and ideas into executable AI-assisted experiments, helping users plan workflows, run analyses, generate charts and tables, and assemble structured reports.

适合Best for希望从研究问题快速走向可重复实验的研究人员与知识工作者。Researchers and knowledge workers moving quickly from a research question to a reproducible experiment.