Awesome GitHub RepositoriesSession State Summarizers

rrweb is a DOM session recording library and serialization framework used to record and replay web sessions. It converts the state of a web page into a serializable JSON data structure and tracks mutations to reconstruct user interactions within a replay engine. The system distinguishes itself by using a sandboxed iframe for reconstruction to isolate replayed content, preventing script execution and form submissions. It ensures visual consistency through CSS inline-style flattening and provides sensitive data masking to prevent private information from being captured. The project covers a br

This project provides a system for managing agent context and session memory, featuring an agent context compactor, an AI session memory manager, and a tool output sandbox. It functions as a middleware layer and server extension for the Model Context Protocol to optimize context windows and reduce token usage. The system optimizes agent performance by sandboxing tool outputs and externalizing large data sets, replacing raw I/O with pointers and concise summaries. It employs a persistent knowledge base that indexes session history and tool outputs for retrieval via full-text search, ensuring s

Memori is an AI agent memory middleware platform designed to provide persistent, context-aware recall for language models. It functions as a non-intrusive layer that intercepts outbound model requests to automatically capture interaction history and execution traces, ensuring that agents maintain continuity across sessions without requiring modifications to existing application logic. The platform distinguishes itself through a dual-model storage architecture that maintains information as both structured relational primitives for precise fact retrieval and rolling narrative summaries for situ

jcode 是一个用于开发自主 AI 编码代理的框架，这些代理可自动化软件开发任务。它作为一个代理编排器、工具运行时和语义记忆引擎，支持创建能够修改代码、运行测试并迭代自身功能的代理。 该项目以其递归代理群集（Swarming）而著称，其中协作代理的层级结构可以生成子代理来分解复杂任务。它实现了一个语义记忆系统，结合了基于向量的检索和基于图的关系映射，以在会话间保持上下文。为了管理风险，该系统使用分级操作治理，要求人工批准敏感操作，并将代理活动隔离在单独的 Git 工作树中。 该框架包含一个全面的浏览器自动化工具包，用于与网页交互、提取 DOM 快照和捕获截图。它还实现了模型上下文协议（MCP）以集成外部工具和数据，并支持二进制热重载以在不丢失活动网络连接的情况下更新服务器。 该系统提供用于管理代理记忆的命令行界面，并包括用于跟踪计划进度和可视化代理群集拓扑的审计工具。

OpenSquilla 是一个 LLM 智能体编排框架，旨在利用有向无环图协调多步 AI 工作流和工具执行。它作为一个集中式系统，用于管理专门的技能包并执行复杂的推理序列。 该项目通过一个路由网关脱颖而出，该网关根据复杂性、成本和性能将任务定向到不同的 AI 提供商。它利用多层 AI 记忆系统，通过本地嵌入和 SQLite 组织工作、情景和语义知识，并配有一个安全执行沙盒，通过基于风险的权限配置文件隔离智能体生成的代码。 该平台涵盖了广泛的功能，包括多渠道部署到 Web 和消息平台、通过 cron 进行自动任务调度，以及用于连接外部工具的 Model Context Protocol 网桥。它还提供全面的监控和可观测性工具，用于跟踪 Token 成本、审计运行时决策以及管理可重用技能目录。 该系统包括用于工作区初始化和技能生命周期管理的命令行工具。

This project is a Git-based AI session tracker and context manager designed to record AI agent interactions, transcripts, and tool usage directly into Git repositories. It functions as a system for capturing and indexing the reasoning behind code changes, linking AI prompts and responses to specific code commits to preserve developer intent. The tool distinguishes itself by using Git as a primary storage layer for session metadata, utilizing shadow branches and checkpoints to track agent state without polluting the main commit log. It includes specialized capabilities for auditing AI contribu

Kimi-code is a command-line interface and orchestration framework designed to integrate autonomous AI agents into software development workflows. It functions as a terminal-based assistant that manages multi-step coding tasks, including planning, file system modifications, shell command execution, and test running, all while maintaining conversational context within a local development environment. The project distinguishes itself through a focus on secure, autonomous agent orchestration and granular control over AI interactions. It enforces strict security by requiring explicit user approval

This project is a research-focused toolkit designed for building autonomous agent systems, multi-agent workflows, and security governance frameworks. It provides a platform for coordinating specialized sub-agents through structured communication protocols and phased task delegation to complete complex technical objectives. The framework distinguishes itself by integrating a dedicated security policy engine that validates autonomous tool execution against user-defined permissions and safety rules. It also features a research-oriented approach to prompt engineering, enabling the dynamic assembl

这是一个由 AI 驱动的开发工作流编排器，可将自主编码智能体直接集成到代码编辑器中。它作为一个管理多智能体系统的框架，使开发者能够自动化处理代码重构、内联补全和多阶段软件开发工作流等复杂任务。通过标准化的通信协议，它架起了本地开发环境与大语言模型之间的桥梁。 该系统的核心优势在于其对基于智能体的任务编排和细粒度配置的专注。用户可以定义具有不同行为、工具和系统提示词的多个智能体，从而实现高度定制化的自动化，并确保符合项目特定的编码标准。它支持复杂的上下文管理，包括将代码库细节、工作区状态和诊断信息注入提示词，以提高生成代码和方案的准确性。 除了核心编排功能外，该平台还提供了全面的可观测性和会话管理工具。它包含监控 Token 使用量、跟踪后台任务状态以及在会话间持久化对话历史的功能。其架构依赖于标准输入输出流以实现可靠通信，并集成了安全凭证管理，可在不暴露敏感密钥的情况下处理身份验证。