Friday

MCP文档知识

提供方 未标注

文档知识 未标注 未标注 社区 / 第三方 ClaudeCursorVS CodeWindsurf

自托管持久认知记忆基底,为AI编码代理提供零遗忘上下文层、爆炸半径遍历,以及可选libSQL无服务器存储。

一句话选型结论

按资料字段整理

Friday 属于文档知识类 MCP 服务器,传输方式未标注,鉴权方式未标注,可直接接入 Claude、Cursor、VS Code 等,没有现成安装命令,需按官方文档接入。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类文档知识 传输方式未标注 鉴权未标注 部署方式未标注
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

文档知识
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

记忆

安装与配置

未标注 未标注
上游未给出传输方式
  1. 1
    准备运行环境

    按官方文档确认运行环境(常见为 Node.js 或 Python),装好后再执行安装命令。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
文档检索问答

在你的文档库里按问题找答案。

知识库读写

把新资料写进知识库,随用随取。

内容整理

把零散资料归纳成结构化笔记。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 已适配 Claude、Cursor、VS Code,换客户端不用重新研究配置。

先想清楚的地方

  • 没有现成安装命令,需要按官方文档自己填启动命令和参数。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在文档知识场景里让模型直接调用外部能力的人。
  • 已经在用 Claude、Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Friday当前 未标注 未标注 未标注 无 未标注
dify 未标注 stdio · 本地进程 本地部署 有 2026-04-11
open-webui 未标注 stdio · 本地进程 本地部署 有 2026-04-11
JeecgBoot 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Cherry Studio 未标注 未标注 未标注 无 2026-05-17
mempalace 未标注 stdio · 本地进程 本地部署 有 2026-04-11

服务器档案

文档知识
字段来自项目仓库与公开索引,中文说明由本站标注
提供方未标注上游标注的维护方 未标注
分类文档知识本站按上游分类展示
连接方式未标注上游未给出传输方式
鉴权方式未标注远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型未标注上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

41.2 KB
来自项目仓库与上游目录的原文,未做删改

Friday

Self-hosted persistent cognitive memory layer for AI coding agents.

Persists architecture decisions, schemas, and constraints across sessions via the Model Context Protocol (MCP).

The Problem
Architecture
Dual-Engine
Memory Lifecycle
Quickstart
Python SDK
MCP Setup
Agent Rules
API Reference

Friday Neural Studio — Real-time 3D WebGL knowledge graph visualizer rendering service topologies, dynamic access heatmaps, and automated memory consolidation.


The Problem: Session Amnesia

Modern AI coding agents (Cursor, Claude Code, Antigravity, VS Code) excel at isolated code generation. However, in continuous engineering workflows, developers encounter a structural limitation: Session Amnesia.

Current workarounds fall into three deeply flawed patterns:```
┌─────────────────────────────────────────────────────────┐
│ WHY STANDARD APPROACHES BREAK DOWN │
└─────────────────────────────────────────────────────────┘

  1. Context Windows (RAM) 2. Static Rules Files 3. Standard Vector RAG
    ┌─────────────────────────┐ ┌─────────────────────────┐ ┌─────────────────────────┐
    │ • Ephemeral volatile │ │ • Linear token tax │ │ • Matches text phrasing,│
    │ memory (clears on │ │ (2,500 tokens burned │ │ NOT system topology │
    │ every new thread) │ │ on every trivial fix) │ │ • Blind to directed │
    │ • Lost-in-the-middle │ │ • Stale rules accumu- │ │ call graphs & schema │
    │ degradation on 50k+ │ │ late & conflict │ │ dependencies │
    │ token prompts │ │ • Zero cross-tool sync │ │ • Hallucinates blast │
    │ • High latency & cost │ │ (Cursor ≠ Claude CLI) │ │ radii of refactors │
    └─────────────────────────┘ └─────────────────────────┘ └─────────────────────────┘

1. **Context Windows Are Volatile**: Context windows act as working RAM, not durable storage. Clearing a thread or restarting an agent resets state. Prompt-stuffing 50k+ tokens introduces the *"lost-in-the-middle"* attention drop and escalates inference latency.
2. **Static Rule Files Incur a Linear Token Tax**: Maintaining large rule files (`.cursorrules`, `AGENTS.md`) forces the model to re-read thousands of lines on every keystroke, leading to contradictory instructions and cross-editor fragmentation.
3. **Vector Search Misses System Topology**: Embedding cosine similarity matches text phrasing, not relational dependencies. Vector search cannot traverse directed graphs:
   $$\text{Table: accounts} \longrightarrow \text{FK: subscriptions} \longrightarrow \text{Service: BillingService} \longrightarrow \text{Worker: InvoicePoller}$$

---

## Architecture: Multi-Layer Cognitive Substrate

Friday runs as a self-hosted background service providing a structured, four-tier memory substrate accessed via the Model Context Protocol (MCP):```
┌────────────────────────────────────────────────────────────────────────────────────────┐
│               AI CODING CLIENTS (Cursor / Claude Code / Antigravity / VS Code)         │
└───────────────────────────────────────────┬────────────────────────────────────────────┘
                                            │
                                7 MCP Tools (stdio / HTTP)
                                ├── add_memory       (persist decisions & rationale)
                                ├── add_fact         (versioned immutable truths)
                                ├── memory_search    (targeted semantic recall)
                                ├── get_context      (compiled multi-layer prompt)
                                ├── get_blast_radius (graph dependency traversal)
                                ├── delete_memory    (evict obsolete episodic memories)
                                └── revoke_fact      (prune conflicting/invalid truths)
                                            │
                                            ▼
┌────────────────────────────────────────────────────────────────────────────────────────┐
│                                 FRIDAY COGNITIVE ENGINE                                │
│                                                                                        │
│   Layer 1: Facts Ledger         Layer 2: Episodic Memory       Layer 3: Graph Topology │
│  ┌─────────────────────────┐   ┌───────────────────────────┐  ┌──────────────────────┐ │
│  │ Versioned Facts Ledger  │   │ Mem0 Conversational       │  │ Neo4j Property Graph │ │
│  │ • Deterministic truths  │   │ • Semantic decisions      │  │ • Directed call-trees│ │
│  │ • Conflict detection    │   │ • User preferences        │  │ • Schema blast-radius│ │
│  │ • Zero prompt overhead  │   │ • Sub-100ms retrieval     │  │ • Entity dependencies│ │
│  └─────────────────────────┘   └───────────────────────────┘  └──────────────────────┘ │
│                                                                                        │
│   Layer 4: Cognitive Dynamics Engine                                                   │
│   • Synaptic Energy Decay: E(t) = E₀ · 2^(-Δt / 14d) automatically evicts stale clutter│
│   • Nightly Dream Cycle (03:00 UTC): Prunes noise, crystallizes graph insights & backups│
│   • Empathy State Tracking: Adapts agent brevity and tone to developer urgency & mood  │
│   • Neural Studio: WebGL-based 3D graph visualizer for human and agent state auditing. │
│   • Persona Synchronization: /export/persona compiles canonical rules on-demand.       │
└────────────────────────────────────────────────────────────────────────────────────────┘

The 4 Memory Layers Explained:

Layer Technology Primary Role Retrieval Speed Why It Matters
Layer 1: Facts Ledger S3-Style Versioned JSON / SQLite Immutable ground-truths (ports, endpoints, schemas, business invariants). < 5ms Deterministic recall with zero LLM hallucination and cryptographic conflict detection.
Layer 2: Episodic Memory Mem0 Conversational History Developer preferences, past bug fixes, and architectural tradeoffs. < 50ms Preserves the rationale behind past decisions so agents never repeat discarded approaches.
Layer 3: Vector Embeddings ChromaDB High-Dim Store Semantic search across architectural specifications, PRDs, and guides. < 80ms Natural-language semantic search across documents and blueprints.
Layer 4: Relational Graph Neo4j 5.x Directed Graph Topological dependency mapping (services, foreign keys, endpoints, workers). < 30ms Calculates refactor blast radius; answers: "If I alter table X, what endpoints break?"

Architectural Comparison Matrix

Capability Static Prompts (.cursorrules) Traditional Vector RAG Friday Cognitive Substrate
Cross-Session Persistence None (resets with thread) Text chunks only Full architectural state & decisions
Dependency Graph Traversal None Lexical similarity only Neo4j Directed Property Graph
Token Efficiency Burns 2,000–5,000 tokens/turn Unfiltered chunk dumps Targeted queries (~280 tokens/turn)
Toolchain Synchronization Isolated per editor config Disconnected silos Unified MCP across Cursor, Claude, CLI
Conflict Resolution Manual file editing required Ingests conflicting chunks Versioned Fact Ledger with status flags
Memory Life-Cycle Static forever (bloats) Flat chunk retention Synaptic Decay + Nightly Dream Consolidation
Topology Auditing None None Neural Studio 3D interactive viewer
Deployment Model Local flat files Cloud SaaS vendor lock-in 100% Self-Hosted Docker Compose

Dual-Engine Architecture: Decoupled Background Processing

A foundational architectural decision in Friday is:
> "Why does Friday maintain a background worker LLM (such as Groq, DeepSeek, or local Ollama) on the server, completely separate from the frontier model running in Cursor, Claude Code, or Antigravity?"

Interactive coding agents require low latency, while knowledge graph maintenance requires continuous data extraction and synthesis. Friday enforces a Dual-Engine Architecture that cleanly decouples frontline developer workflows from background data pipelines:```
┌────────────────────────────────────────────────────────────────────────────────────────┐
│ THE DUAL-ENGINE ARCHITECTURE MODEL │
├────────────────────────────────────────────────────────────────────────────────────────┤
│ │
│ INTERACTIVE AGENT (Frontline Client) BACKGROUND WORKER (Async Engine) │
│ ┌─────────────────────────────────────┐ ┌─────────────────────────────────────┐ │
│ │ Client: Cursor / Claude / Antigravity│ │ Engine: Self-Hosted Friday Server │ │
│ │ Model: Frontier (Claude 3.5 / GPT-4o)│ │ Model: Fast Worker (Groq / Ollama) │ │
│ │ Role: Complex code generation │ │ Role: Async graph extraction │ │
│ │ Context: Lean, task-specific prompt │ │ Role: Conflict pruning & decay │ │
│ │ State: Ephemeral session lifetime │ │ State: 24/7 background persistent │ │
│ └──────────────────┬──────────────────┘ └──────────────────▲──────────────────┘ │
│ │ │ │
│ │ 1. MCP Tools (memory_search, add_memory) │ 2. Microsecond │
│ ▼ │ Async Parsing │
│ ┌──────────────────────────────────────────────────────────────┴──────────────────┐ │
│ │ FRIDAY PERSISTENT MEMORY ARCHITECTURE │ │
│ │ │ │
│ │ Layer 1: Facts Ledger (Deterministic S3-style Hash Table) │ │
│ │ Layer 2: Episodic Memory (Mem0 Conversational Thread History) │ │
│ │ Layer 3: Vector Embeddings (ChromaDB Semantic Chunks) │ │
│ │ Layer 4: Property Knowledge Graph (Neo4j Directed Topology) │ │
│ │ Memory Lifecycle: Dynamic Decay (E(t)) & Nightly Dream Cycle (03:00 UTC) │ │
│ └─────────────────────────────────────────────────────────────────────────────────┘ │
└────────────────────────────────────────────────────────────────────────────────────────┘


### Why Decoupling Background Processing is Essential:

#### 1. ⚡ Zero-Latency IDE Execution (Non-Blocking Decoupling)
When you type in Cursor or Claude Code and an agent records a major decision via `add_memory`, the Conscious model cannot pause for 4–6 seconds while an LLM parses semantic entities, identifies foreign keys, and runs Cypher mutations.
- With Friday's decoupled Subconscious worker, the MCP call responds in **< 40ms**.
- The Subconscious engine (e.g. Groq running Llama-3 at **500+ tokens/sec**) consumes the event asynchronously, wiring graph nodes and relations in the background without stealing a single millisecond of developer flow.

#### 2. 💰 95%+ Token Cost Optimization
Frontier reasoning models (Claude 3.5 Sonnet, GPT-4o) cost **$3.00 to $15.00 per million tokens**. Using these expensive models for routine structural maintenance—such as extracting triples (`Entity A` $\longrightarrow$ `RELATION` $\longrightarrow$ `Entity B`), verifying fact hashes, or applying synaptic decay—wastes massive token budgets.
- Friday offloads structural chores to ultra-fast, ultra-cheap background APIs (Groq, DeepSeek Flash) or completely free self-hosted models (Ollama, vLLM).
- Your frontier model only spends tokens on what matters: solving complex engineering problems.

#### 3. 🌙 Autonomous Background Consolidation (The Dream Cycle)
Your coding session ends when you close your IDE or put your laptop to sleep. But memory evolution cannot stop when the laptop closes:
- Friday's Subconscious engine lives on your cloud or local server 24/7.
- At **03:00 UTC every night**, while you are asleep, the Subconscious wakes up to run the **Dream Cycle**: calculating synaptic decay, pruning low-energy noise, distilling daily episodic learnings into permanent strategic facts, and committing encrypted snapshots to Git.

#### 4. 🛡️ Hallucination & Context Pollution Defense
Dumping a monolithic 500-node graph or 100 historical decisions directly into your editor's prompt causes **Instruction Dilution**: the LLM becomes confused, forgets recent constraints, and hallucinates outdated patterns.
- The Subconscious acts as an intelligent firewall.
- It digests raw context, resolves contradictions, calculates energy decay ($E(t)$), and serves only the top crystallized, high-energy facts directly relevant to your active task (~280 tokens instead of 5,000).

---

## Memory Lifecycle Management: Decay, Consolidation & Calibration

Friday implements active memory lifecycle management to ensure AI agents retain critical constraints without context bloat or stale instruction interference:```
┌────────────────────────────────────────────────────────────────────────────────────────┐
│                          FRIDAY MEMORY LIFECYCLE ENGINE                                │
├────────────────────────────────────────────────────────────────────────────────────────┤
│                                                                                        │
│  🔥 Dynamic Memory Heat & Decay           🌙 The Dream Cycle (Nightly 03:00 UTC)      │
│  ┌───────────────────────────────────┐    ┌────────────────────────────────────────┐   │
│  │ Exponential Synaptic Decay        │    │ 1. Synaptic Pruning (Evaporates noise) │   │
│  │ • E(t) = E₀ · 2^(-Δt / T_half)    │───>│ 2. Episodic Synthesis (Distills gems)  │   │
│  │ • Recall Potentiation (+0.25)     │    │ 3. Neo4j Crystallization (Graph edges) │   │
│  │ • Soft Archive if E < 0.25        │    │ 4. Autonomous Backup to Git            │   │
│  └───────────────────────────────────┘    └────────────────────────────────────────┘   │
│                                                                                        │
│  🤍 Adaptive Context & Persona Calibration                                             │
│  ┌──────────────────────────────────────────────────────────────────────────────────┐  │
│  │ Multi-Dimensional Response Calibration                                           │  │
│  │ • Interaction Modes: tactical_sprint | deep_architecture | casual_brainstorm     │  │
│  │ • Task Context & Urgency Detection (0.0 to 1.0)                                  │  │
│  │ • Dynamic Response Calibration: Brevity (high/med/low) & Tone Tuning             │  │
│  └──────────────────────────────────────────────────────────────────────────────────┘  │
└────────────────────────────────────────────────────────────────────────────────────────┘

1. 🔥 Dynamic Memory Heat & Decay

Memories and verified facts are not static text—they have energy. Active, frequently recalled directives remain bright ($E > 1.0$). Irrelevant or outdated details experience exponential half-life decay ($T_{half} = 14\text{ days}$):
$$E(t) = E_0 \times 2^{-\frac{\Delta t}{T_{half}}}$$
When a memory is queried during coding, it receives a recall potentiation boost ($+0.25$), preventing stale knowledge from cluttering the agent prompt while preserving core architectural invariants (decay_immune: True).

2. 🌙 The Dream Cycle

Every night at 03:00 UTC (or on-demand via client.run_dream_cycle()), Friday enters the Dream Cycle:
- Synaptic Pruning: Identifies cold/stale facts and transitions them to archived storage.
- Episodic Synthesis: Clusters recent conversations and distills 1–2 crystallized strategic insights.
- Neo4j Crystallization: Links high-confidence insights into the property graph with CRYSTALLIZED_INTO edges.
- Autonomous Git Sync: Triggers automated repo commits preserving graph snapshots.

3. 🤍 Adaptive Context & Persona Calibration

Friday monitors the developer interaction context (urgent bug-fix sprint, late-night architecture exploration, or casual brainstorming). The engine dynamically adjusts agent response characteristics:
- Brevity Calibration: high (zero fluff, code-first) vs. detailed (system-wide breakdown).
- Tone Calibration: technical_concise (code-first, direct) vs. architectural_detailed (system-wide breakdown).
- Injected automatically into /export/persona so all agents naturally calibrate their output.


DeepEval Benchmarks

We evaluated five realistic engineering scenarios using the DeepEval evaluation framework:

  1. Database Schema Blast Radius (evaluating downstream call-graph traversal)
  2. Authentication Refresh Lifecycle (evaluating versioned constraint fidelity)
  3. Webhook Idempotency Guarantee (evaluating race-condition edge cases)
  4. Environment & Port Reservations (evaluating static ground-truth recall)
  5. Multi-Agent Toolchain Consistency (evaluating cross-tool synchronization between Cursor and Claude CLI)
Memory Architecture Contextual Precision Contextual Recall Faithfulness Prompt Tokens / Turn Session Retention
Static Prompts (.cursorrules) 38.0% 44.0% 62.0% 3,150 tokens 15.0% (resets)
Naive Vector RAG (Vector Only) 64.0% 58.0% 74.0% 1,820 tokens 55.0%
Friday Cognitive Substrate 95.0% 93.0% 99.0% 280 tokens 100.0%

Reproducing Benchmarks Locally```bash

python benchmarks/benchmark_deepeval.py


---

## Quickstart

### Option A: One-Command Installation (Recommended)

Run the self-contained installation script:```bash
curl -fsSL https://raw.githubusercontent.com/friday-memory/friday/main/install.sh | bash

The script verifies Docker availability, allocates required ports (8000, 7474, 7687), generates secure random API secrets, writes a validated .env, and launches Friday via Docker Compose.

Option B: Manual Setup via Docker Compose

  1. Clone the Repository:bash git clone https://github.com/friday-memory/friday.git cd friday

  2. Configure Environment (.env):```bash
    cp .env.example .env
    ``````ini
    # Master API key for endpoint security
    BRAIN_API_KEY=choose_a_strong_secret_key

# Fast Subconscious LLM provider (Groq or DeepSeek)
DEEPSEEK_API_KEY=your_key_here
DEEPSEEK_BASE_URL=https://api.deepseek.com
DEEPSEEK_MODEL=deepseek-chat

# Mem0 key for vector memory (optional)
MEM0_API_KEY=your_mem0_key_here

# Neo4j database credentials
NEO4J_URI=bolt://neo4j:7687
NEO4J_USER=neo4j
NEO4J_PASSWORD=choose_a_strong_password
```

  1. Start the Stack:bash make up # or: docker compose up -d

  2. Verify Health:bash curl http://localhost:8000/health ``````json { "status": "healthy", "service": "friday-cognitive-substrate", "version": "1.4.4", "layers": { "L1_core": "healthy", "L2_mem0": "healthy", "L3_chromadb": "healthy", "L4_neo4j": "healthy" } }


Python SDK (friday-memory)

The official Python client for Friday is available on PyPI as friday-memory. Connect your agentic workflows, LangChain pipelines, or autonomous scripts directly to Friday with zero boilerplate:```bash
pip install --upgrade friday-memory


### Synchronous Client```python
from friday import Friday

# Automatically resolves FRIDAY_URL and FRIDAY_API_KEY from environment
with Friday(api_key="your_secret_key", base_url="http://localhost:8000") as client:
    # 1. Health check
    status = client.health()
    print("Friday Status:", status["status"])

    # 2. Store architectural decision
    client.add_memory(
        "PostgreSQL 16 selected with pgvector for hybrid retrieval",
        project="backend-api",
    )

    # 3. Commit scoped ground-truth fact with auto-conflict resolution
    client.add_fact("Production database endpoint is db.internal.net:5432", project="backend-api")

    # 4. Query multi-hop dependency blast radius before refactoring
    blast = client.get_blast_radius(entity="OrdersTable", depth=2, project="backend-api")
    print(
        f"Impacted components ({blast['total_impacted']}):",
        [n["name"] for n in blast["impacted_nodes"]],
    )

    # 5. Multi-layer search (L2 Facts + L3 ChromaDB + L4 Knowledge Graph)
    context = client.search("database connection configuration", project="backend-api")
    print(context["results"])

    # 5. Cognitive State & Dynamic Response Calibration
    state = client.get_cognitive_state()
    print("Active Mode:", state["current_mode"])  # tactical_sprint, deep_architecture, etc.

    # 6. Trigger Nightly Dream Cycle Consolidation (Consolidates & Prunes)
    dream_report = client.run_dream_cycle(half_life_days=14.0)
    print("Crystallized Insights:", dream_report["crystallized_insights"])

    # 7. Apply Synaptic Decay
    decay_report = client.apply_decay(half_life_days=14.0)
    print("Active Facts Remaining:", decay_report["active_facts_count"])

Asynchronous Client (FastAPI / Agent Workers)```python

import asyncio
from friday import AsyncFriday

async def main():
async with AsyncFriday(api_key="your_secret_key") as client:
# Commit context concurrently
await client.add_memory("Redis cluster deployed for token bucket rate limiting")
facts = await client.get_facts(min_energy=0.5)
print(f"Verified high-energy facts: {len(facts)}")

asyncio.run(main())


### LangChain Integration (`FridayRetriever`)```bash
pip install "friday-memory[langchain]"
``````python
from friday.integrations.langchain import FridayRetriever
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI

retriever = FridayRetriever(
    api_key="your_secret_key",
    base_url="http://localhost:8000",
    project="reeldm",
)

# Connect directly to LCEL chains
prompt = ChatPromptTemplate.from_template(
    "Answer using verified system memory:\n{context}\n\nQuestion: {question}"
)

chain = {"context": retriever, "question": RunnablePassthrough()} | prompt | ChatOpenAI()

Client Setup (MCP)

Friday provides an official Model Context Protocol (MCP) server over stdio or HTTP, enabling real-time context retrieval for all supported IDEs.```
┌───────────────────────┐
│ Cursor (Desktop) │──┐
└───────────────────────┘ │
┌───────────────────────┐ │
│ Claude Code CLI │──┼── MCP Protocol (stdio transport)
└───────────────────────┘ │ FRIDAY_URL="http://127.0.0.1:8000"
┌───────────────────────┐ │ BRAIN_API_KEY="your_secret_key"
│ Antigravity IDE │──┤
└───────────────────────┘ │
┌───────────────────────┐ │
│ Windsurf / VS Code │──┤
└───────────────────────┘ │
┌───────────────────────┐ │
│ Codex CLI │──┘
└───────────────────────┘
▼
┌──────────────────────────────┐
│ FRIDAY CENTRAL BRAIN │
│ (Localhost or Remote VM) │
│ FastAPI + Mem0 + Neo4j │
└──────────────────────────────┘


1. Cursor (Local or Remote)

Add to `.cursor/mcp.json` in your project or globally in **Cursor Settings → MCP**:

**Local Docker Setup:**```json
{
  "mcpServers": {
    "friday": {
      "command": "python",
      "args": ["-m", "mcp.server"],
      "cwd": "/path/to/friday",
      "env": {
        "FRIDAY_URL": "http://localhost:8000",
        "BRAIN_API_KEY": "your_secret_key"
      }
    }
  }
}

Remote Cloud VM Setup (via SSH Tunnel):```json
{
"mcpServers": {
"friday": {
"command": "ssh",
"args": [
"-i", "/path/to/ssh_key.pem",
"-o", "StrictHostKeyChecking=no",
"ubuntu@YOUR_SERVER_IP",
"docker exec -i fridays-brain-app python /app/mcp_server/server.py"
]
}
}
}


2. Claude Code CLI

Register Friday directly via CLI:```bash
claude mcp add friday \
  -e FRIDAY_URL="http://localhost:8000" \
  -e BRAIN_API_KEY="your_secret_key" \
  -- python -m mcp.server
  1. Antigravity IDE

Add to ~/.gemini/config/mcp_config.json:```json
{
"mcpServers": {
"friday": {
"command": "python",
"args": ["-m", "mcp.server"],
"cwd": "/path/to/friday",
"env": {
"FRIDAY_URL": "http://localhost:8000",
"BRAIN_API_KEY": "your_secret_key"
}
}
}
}


4. Codex CLI

Add to `~/.codex/config.toml`:```toml
[mcp.servers.friday]
command = "python"
args = ["-m", "mcp.server"]
cwd = "/path/to/friday"

[mcp.servers.friday.env]
FRIDAY_URL = "http://localhost:8000"
BRAIN_API_KEY = "your_secret_key"
  1. VS Code (Cline / Roo Code / Continue)

Add to your VS Code MCP configuration:```json
{
"cline.mcpServers": {
"friday": {
"command": "python",
"args": ["-m", "mcp.server"],
"cwd": "/path/to/friday",
"env": {
"FRIDAY_URL": "http://localhost:8000",
"BRAIN_API_KEY": "your_secret_key"
}
}
}
}


---

## Tool Reference

Connected agents automatically access four core MCP primitives:

| Primitive | Purpose | Trigger Phase |
| :--- | :--- | :--- |
| `get_context` | Ingests active verified facts and recent context filtered by project namespace. | Session initialization. |
| `memory_search` | Queries vector and graph indices for architectural decisions and system dependencies. | Prior to answering technical questions or planning refactors. |
| `get_blast_radius`| Computes multi-hop transitive dependency blast radius for a service or entity. | Prior to refactoring schemas or modifying critical APIs. |
| `add_memory` | Records implementation details, rationale, and tradeoffs; triggers background graph extraction. | Post-implementation or bug resolution. |
| `add_fact` | Commits versioned ground truths with automatic key conflict resolution and project isolation. | Architectural declarations or configuration changes. |
| `delete_memory` | Evicts obsolete or invalid episodic memory entries by ID. | Memory hygiene and state cleanup. |
| `revoke_fact` | Revokes and supersedes conflicting, obsolete, or invalid ground truths. | Architectural migrations or rule deprecations. |

---

## Environment Variables Reference

| Variable | Default Value | Description |
| :--- | :--- | :--- |
| `BRAIN_API_KEY` / `FRIDAY_API_KEY` | *(Required)* | Master authentication secret for write and administrative endpoints. |
| `FACTS_PATH` | `/app/facts/facts.json` | Local filesystem path to the versioned JSON facts ledger. |
| `NEO4J_URI` | `bolt://neo4j:7687` | Bolt connection URI for the Layer 4 Neo4j instance. |
| `NEO4J_USER` | `neo4j` | Neo4j database username. |
| `NEO4J_PASSWORD` | *(Required)* | Neo4j database password. |
| `DEEPSEEK_API_KEY` / `GROQ_API_KEY` | `""` | API key for the Subconscious background LLM parser. |
| `DEEPSEEK_BASE_URL` | `https://api.deepseek.com` | Base URL for the OpenAI-compatible Subconscious provider. |
| `DEEPSEEK_MODEL` | `deepseek-chat` | Model name for automated graph extraction and conflict detection. |
| `MEM0_API_KEY` | `""` | Optional API key for Mem0 managed episodic memory layer. |
| `COGNITIVE_STATE_PATH` | `/app/core/cognitive_state.json` | Path to persistent developer cognitive and emotional calibration state. |

---

## Dynamic Directives Export (`/export/persona`)

Friday can compile stored facts and architectural constraints into synchronized markdown directives on-demand, preventing rules drift across teams:```bash
# Export canonical AGENTS.md
curl -s "http://localhost:8000/export/persona?target=agents" \
  -H "X-Brain-Key: your_key" > AGENTS.md

# Export Cursor .cursorrules
curl -s "http://localhost:8000/export/persona?target=cursor" \
  -H "X-Brain-Key: your_key" > .cursorrules

Universal Agent Directive Engine (Multi-Agent Rules)

Different AI coding assistants rely on different workspace instruction formats. Friday includes a built-in CLI engine that generates standardized, bidirectional memory directives for any editor or autonomous agent runner:

Target Environment Generated File Default Location
Universal Agent Standard AGENTS.md Repository root
Claude Code CLAUDE.md Repository root
Cursor IDE .cursorrules Repository root
Google Gemini & Antigravity GEMINI.md Repository root
GitHub Copilot copilot-instructions.md .github/
Windsurf & Cascade .windsurfrules Repository root
Continue.dev rules.md .continue/
Aider CONVENTIONS.md Repository root

1. List Supported Targets```bash

friday rules list


### 2. Generate Rules for Your Toolchain
Generate an optimized rule file for a specific agent:```bash
friday rules generate --target claude
friday rules generate --target cursor
friday rules generate --target gemini

Or generate standardized rule files for all supported tools at once:```bash
friday rules generate --all


### 3. Extensible Custom Agent Adapters
For proprietary agents, internal corporate tooling, or newly released frameworks, register and output custom adapted rule files:```bash
friday rules custom \
  --key myagent \
  --name "Internal SRE Agent" \
  --file ".myagent/rules.md"

Each generated rule file enforces the Two-Way Zero-Amnesia Protocol:

…(正文过长,页面只展示前面部分,完整内容见仓库)

常见问题

6 问
答案由本站依据条目字段整理,不引用上游原文
Friday 怎么安装?

资料没有给出安装命令,请到官方仓库或文档按说明接入;这类条目多数是生态应用,或尚未发布可安装包。

Friday 怎么在 Claude、Cursor、VS Code 里配置?

它的传输方式未标注,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Friday 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Friday 需要 API Key 吗?

资料没有标注鉴权方式,是否需要密钥取决于服务本身,接入前按官方文档确认。

Friday 支持哪些客户端?

资料标注支持 Claude、Cursor、VS Code、Windsurf、Cline、Gemini CLI;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Friday 能提供哪些能力?

资料显示能力标签包括 记忆。具体工具清单以官方文档为准。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。