Skip to main content
Glama

Project Christina:自主认知放大器

Python 3.11+ License: MIT Dependencies Tests FastMCP Compliant Code Style: Ponytail Ultra

Host: Google Antigravity Host: OpenCode Host: Claude Desktop Host: OpenAI Codex CLI

[快速开始](#- 1-command-zero-friction-installation) • 架构MCP 工具CLI 参考文档贡献指南


🌟 执行摘要:消除上下文腐化

现代 AI 编码智能体在大规模代码库($10\text{M}+$ tokens)上失败,原因不在于推理能力,而在于Context Rot(上下文腐化):注意力分散、未索引的提示词污染、上下文清空后架构约束丢失,以及不协调的集群冲突。

Project Christina 通过一套集成的高性能认知三位一体方案来解决这些问题:

  1. RLM(递归语言模型——上下文即变量):将大规模代码库移出对话提示词,放入沙箱化的堆变量(context)中。智能体执行有界子查询($D \le 2, N \le 20$)和带自动回滚的事务式写时复制(CoW)Python 控制循环。

  2. Graphify(确定性 CPG 与 AST 雷达):构建内存 SQLite3 WAL 调用图,实现 亚 0.3ms 递归 CTE 查询、传递性爆炸半径分析和中心性极高的 Node 节点排名,带来 71.5x 的 token 发现量缩减

  3. OKF(持久语义记忆与认知进化):亚微秒级正则 frontmatter 解析($6.72\ \mu\text{s}$/doc)、正式 AGM 信念修正、艾宾浩斯遗忘曲线,以及带 $\le 400$-token 自动压缩后记忆恢复锚点的 Mark-and-Sweep 语义垃圾回收。

  4. 跨项目认知蒸馏:将专有代码匿名化为数学原型,具备严格的零信息泄漏不变量($\mathcal{I} = 0$)、多进制 Shannon 熵秘密清洗机制,以及跨代码库的贝叶斯不变量聚合。

  5. 集群并发控制:使用 Kung-Robinson 乐观并发控制(OCC)、Tree-CRDT 三方 AST 合并以及 Linda 元组空间黑板机制,实现去中心化多智能体执行。


🏛️ 三支柱认知架构

                                  ┌─────────────────────────────────────────┐
                                  │           SUPERVISOR / AGENT            │
                                  │  (Antigravity / OpenCode / Claude / AI) │
                                  └────────────────────┬────────────────────┘
                                                       │ JSON-RPC 2.0 (stdio)
                                                       ▼
┌───────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐
│                                            PROJECT CHRISTINA FAST-MCP GATEWAY                                     │
├──────────────────────────────────────┬────────────────────────────────────┬───────────────────────────────────────┤
│          PILLAR 1: RLM ENGINE        │       PILLAR 2: GRAPHIFY CPG       │        PILLAR 3: OKF MEMORY           │
│         (Context as Variable)        │          (AST Code Radar)          │         (Semantic Evolution)          │
├──────────────────────────────────────┼────────────────────────────────────┼───────────────────────────────────────┤
│ • Out-of-core Heap Variables         │ • In-Memory SQLite3 WAL Graph      │ • Sub-microsecond OKF Regex Parser    │
│ • Transactional CoW Rollback         │ • Sub-0.3ms Transitive Blast Query │ • Formal AGM Belief Revision          │
│ • 3-Phase EGRI Invariant Linter      │ • Composite God-Node Centrality    │ • Ebbinghaus Forgetting & GC          │
│ • Dynamic Governor (D<=2, N<=20)     │ • Circular Dependency & Wave Sort  │ • Symbol-to-ADR Constraints           │
└──────────────────────────────────────┴────────────────────────────────────┴───────────────────────────────────────┘
                                                       │
                                                       ▼
┌───────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐
│                                        DECENTRALIZED SWARM & DISTILLERY                                           │
├───────────────────────────────────────────────────────────────────┬───────────────────────────────────────────────┤
│                    SWARM CONCURRENCY BLACKBOARD                   │         GLOBAL EPISTEMIC DISTILLERY           │
├───────────────────────────────────────────────────────────────────┼───────────────────────────────────────────────┤
│ • Kung-Robinson Optimistic Concurrency Control (OCC)              │ • Zero-Information Leakage (I = 0)           │
│ • Semantic Tree-CRDT 3-Way AST Merge Resolution                   │ • Multi-Base Shannon Entropy Secret Redaction │
│ • Linda Tuple Space (`out`, `rd`, `in`, `eval`, `digest`)         │ • Bayesian Invariant Distillation (0700 Fence)│
└───────────────────────────────────────────────────────────────────┴───────────────────────────────────────────────┘

Mermaid 流程图

flowchart TD
    Host[Host Agent Context] -->|JSON-RPC 2.0 stdio| MCP[Christina FastMCP Server]
    
    subgraph Trinity["Autonomous Cognitive Trinity"]
        MCP -->|cpg_query| CPG[Graphify CPG Radar<br/><i>sub-0.3ms SQLite WAL</i>]
        MCP -->|rlm_execute| RLM[RLM Sandbox<br/><i>Transactional CoW REPL</i>]
        MCP -->|memory_evolve| OKF[OKF Semantic Memory<br/><i>AGM Revision & Epistemic GC</i>]
    end
    
    subgraph SwarmDistill["Swarm & Cross-Project Substrate"]
        MCP -->|swarm_blackboard| OCC[Swarm Concurrency<br/><i>Kung-Robinson OCC + Tree-CRDT</i>]
        OKF -->|distill_global| Distill[Global Epistemic Distillery<br/><i>Anonymized Archetypes (I=0)</i>]
    end

    CPG -.->|Blast Radius & Waves| OCC
    RLM -.->|Isolated Sub-Calls| Host
    OKF -.->|ADR Anchor <=400 Tokens| Host

🚀 一条命令,零摩擦安装

Christina 可在数秒内完成安装,无需后台守护进程、本地编译或 root 权限:

cd christina
./install.sh

自动化诊断预检

./install.sh doctor
================================================================
 Christina Cognitive Amplifier Diagnostics (v1.0.0)
================================================================
✓ Python Version: 3.11+ (Requirement satisfied)
✓ SQLite3 in-memory WAL Engine: Ready
✓ OKF Semantic Memory Engine: Ready
✓ Google Antigravity Plugin: Registered
✓ OpenCode Plugin: Registered
✓ Global memory directory: ~/.config/christina/global_memory (0700 fenced)
================================================================
✅ All systems functional.

运行完整测试套件(62/62 通过,耗时小于 <1.2s)

./install.sh test
# Or with pytest directly:
pytest tests/ -v

🛠️ 标准 FastMCP 工具矩阵

Christina 提供 4 个统一 JSON-RPC 2.0 stdio 工具,兼容任何 MCP 主机:

工具

类别

关键能力与模式

性能上界

cpg_query

AST 代码雷达

blast_radius, def_use, cfg, vinterfaces, god_nodes, cycles, waves, info

内存遍历 <0.3ms

rlm_execute

沙箱化执行

子智能体 MapReduce、事务式 CoW REPL、三阶段 EGRI linting 检查、计算资源抑制器目标

递归边界 $D \le 2, N \le 20$

memory_evolve

语义记忆

search, persist, revise(AGM), gc(Ebbinghaus 标记-清除), distill_global, query_global

$6.72\ \mu\text{s}$/文档解析

swarm_blackboard

集群并发控制

out, rd, in, eval, occ_validate(Kung-Robinson OCC), tree_merge(Tree-CRDT), digest

无锁乐观并发验证验证

MCP 工具调用

1. 爆炸半径分析(cpg_query

{
  "name": "cpg_query",
  "arguments": {
    "symbol": "PaymentGateway",
    "mode": "blast_radius",
    "depth": 3
  }
}

2. 事务式子查询执行(rlm_execute

{
  "name": "rlm_execute",
  "arguments": {
    "query": "Audit error recovery handling in database connection pool",
    "scope_paths": ["src/db/", "src/pools/"]
  }
}

3. 带符号约束的语义记忆搜索(memory_evolve

{
  "name": "memory_evolve",
  "arguments": {
    "action": "search",
    "query": "zero-trust authentication policy",
    "linked_symbols": ["AuthMiddleware"]
  }
}

4. 集群 OCC 冲突校验(swarm_blackboard

{
  "name": "swarm_blackboard",
  "arguments": {
    "action": "occ_validate",
    "worker_id": "worker_security_audit",
    "read_version": 4,
    "read_set": ["AuthMiddleware", "SessionToken"],
    "write_set": ["AuthMiddleware"]
  }
}

⚡ CLI 快速参考

# 1. Scan codebase and index AST knowledge graph into in-memory SQLite3 WAL
python3 -m christina.cli scan .

# 2. Calculate static blast radius for a target symbol
python3 -m christina.cli blast AuthService --depth 3

# 3. List top God Nodes ranked by composite degree centrality
python3 -m christina.cli god-nodes --limit 10

# 4. Search OKF institutional memory, ADRs, and symbol constraints
python3 -m christina.cli memory "connection pool timeout" --symbol DatabasePool

# 5. Run FastMCP JSON-RPC 2.0 stdio server
python3 -m christina.cli serve

# 6. Execute system diagnostics
python3 -m christina.cli doctor

🔌 多主机兼容与配置

1. Google Antigravity CLI(agy

自动符号链接到 ~/.gemini/antigravity-cli/plugins/christina,并注册到 ~/.gemini/antigravity-cli/mcp_config.json

2. OpenCode

自动注册到 ~/.config/opencode/plugins/christina 以及 ~/.config/opencode/opencode.json

3. Claude Desktop

自动配置到 ~/.claude/claude_desktop_config.json(macOS 上为 ~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "christina": {
      "command": "python3",
      "args": ["-m", "christina.bridge.mcp_server"],
      "env": {
        "PYTHONPATH": "/path/to/christina"
      }
    }
  }
}

4. OpenAI Codex CLI

自动注册到 ~/.config/codex/config.json


🪮 Ponytail Ultra:零依赖保证

Project Christina 严格遵循 Ponytail Ultra 规范设计:

  • 零外部运行时依赖:仅使用标准 Python 库(ast, sqlite3, re, json, hashlib, fcntl, math, pathlib, typing)。

  • 零重型守护进程:不依赖 Docker、Neo4j、ChromaDB 或 Redis。内存 SQLite3 WAL 和 POSIX 文件锁可提供亚毫秒级执行,空闲后台内存占用为 $0\text{MB}$。

  • 严格代码精简:每个模块精简(不足 250 行代码)、内聚且自包含。


📚 文档与指南

文档

描述

入门指南

分步安装、验证和首个 Agent 工作流。

技能分类

渐进式揭示的技能定义(cpg, rlm, memory, swarm)。

Contributing 指南

Ponytail Ultra 开发规范、Nix 环境、测试套件和 ADR 工作流说明。

安全策略

零信息泄漏不变量($\mathcal{I} = 0$)、Shannon 熵敏感信息净化与隔离机制。

更新日志

详细的发布说明与版本历史。


📜 许可证

Project Christina 以开源 MIT 许可证 形式分发。

© 2026 Christina Engineering Swarm 与贡献者。

-
license - not tested
Not graded
quality - not tested
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
1Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

  • Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.

  • Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.

  • Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/amadeus-ex-machina/christina'

If you have feedback or need assistance with the MCP directory API, please join our Discord server