ContextGraph

概述

ContextGraph 为编码代理和多代理团队提供持久的内存后端，具有受控共享内存、上下文编译和响应式增量压缩功能。它使代理能够通过结构化检查点在上下文压力下保持状态，并在存储库本地目录中维护可见状态。该服务器通过 MCP 协议实现这些内存管理功能。

试试问 AI

装完之后，这里有 5 个你可以让 AI 做的事：

• contextgraph_compile_context

  Compile a governed, token-budgeted context pack from mixed agent memory

  试试:Compile context for payment service issues with 1000 tokens试试:Create a context pack about project status for me
• contextgraph_store

  Store a claim in agent memory with provenance and access controls

  试试:Store that payment service is migrating from REST to gRPC for Q2试试:Remember that we had an incident with connection pool exhaustion
• contextgraph_recall

  Retrieve memories matching a query with relevance scoring

  试试:Recall information about payment service latency issues试试:What do we know about the API migration project?
• contextgraph_register_agent

  Register a new agent with the memory system

  试试:Register a new agent named 'ops-bot' for operations team试试:Create an agent called 'research-assistant' for the research department
• contextgraph_create_session

  Create a new session for an agent to record events

  试试:Start a session for the payments refactor project试试:Create a new coding session for API migration
• contextgraph_record_session_event

  Record an event (decision, constraint, task, etc.) in a session

  试试:Record a decision to keep the REST API stable试试:Note that we need to add migration tests
• contextgraph_checkpoint_session

  Create a checkpoint from a session to save its current state

  试试:Checkpoint the current session before making major changes试试:Save the current state of the coding session
• contextgraph_fork_session

  Create a new session that inherits from an existing checkpoint

  试试:Fork the current session to experiment with gRPC implementation试试:Create a branch from the last checkpoint to try a different approach
• contextgraph_sync_memory_directory

  Sync session state to a local .contextgraph/ directory

  试试:Sync the current session state to my workspace试试:Update the memory directory with the latest changes
• contextgraph_get_context_pack

  Retrieve a previously compiled context pack

  试试:Get the context pack I compiled earlier about payment issues试试:Retrieve the project status context pack
• contextgraph_explain_context_pack

  Get explanations for why claims were included or excluded in a context pack

  试试:Explain why some claims were excluded from the payment service pack试试:Show me why claims conflicted in the last compilation

可对比工具

安装

pip install contextgraph

{
  "mcpServers": {
    "contextgraph": {
      "command": "python",
      "args": ["-m", "contextgraph.server"],
      "env": {}
    }
  }
}

FAQ

ContextGraph 与向量内存有什么不同？

ContextGraph 提供结构化内存，具有来源证明、新鲜度、访问控制和可解释检索功能，而不仅仅是原始文本存储。

响应式增量压缩如何工作？

它将事件记录为结构化检查点，编译增量包，保留决策、任务和状态，而不是将会话折叠为摘要，从而在上下文边界之间保持状态。

ContextGraph 对比