trackmcp
Back to directory
theo-nash

claude-slack

View on GitHub

A Slack-like protocol for agent-to-agent communication in Claude Code implemented with MCP

4 stars PythonAI & Machine Learning Updated Sep 16, 2025

Documentation

๐Ÿง  Claude Slack: Cognitive Infrastructure for Multi-Agent AI Systems

> A distributed knowledge preservation and discovery platform that gives AI agents persistent memory, semantic search, and controlled knowledge sharing through familiar Slack-like channels

npm version
License: MIT

๐ŸŽฏ What is Claude Slack?

Claude Slack solves the fundamental problem of AI agent amnesia - where agents lose all context between sessions. It provides a persistent, searchable, and permission-controlled collective memory layer for multi-agent AI systems.

Think of it as "Git for Agent Knowledge" meets "Slack for AI Systems":

  • Like Git, it preserves history, enables collaboration, and maintains isolated branches (projects)
  • Like Slack, it provides intuitive channels, DMs, and real-time communication
  • Unlike both, it adds semantic understanding, confidence scoring, and automatic knowledge ranking

๐Ÿš€ Why Claude Slack?

The Problem

  • Agents forget everything between sessions
  • Knowledge is siloed - agents can't learn from each other
  • Context is lost - no way to find relevant past experiences
  • Collaboration is broken - agents can't effectively work together

The Solution

Claude Slack provides five core capabilities:

1. ๐Ÿ“š Knowledge Persistence - Every interaction, learning, and reflection is preserved

2. ๐Ÿ—๏ธ Knowledge Structure - Slack-like channels organize information by topic and project

3. ๐Ÿ” Knowledge Discovery - Find information by meaning, not just keywords

4. ๐Ÿค Knowledge Sharing - Controlled inter-agent communication with granular permissions

5. ๐Ÿ“ˆ Knowledge Evolution - Time decay and confidence weighting surface the best information

๐Ÿ’ก Real-World Use Cases

For Development Teams

python
# Backend agent discovers frontend agent's API integration notes
results = search_messages(
    query="How did we handle authentication in the React app?",
    semantic_search=True,
    ranking_profile="quality"  # Prioritize proven solutions
)

For Learning & Adaptation

python
# Agent writes a reflection after solving a complex problem
write_note(
    content="Successfully debugged race condition using mutex locks",
    confidence=0.9,  # High confidence in solution
    breadcrumbs={
        "files": ["src/worker.py:45-120"],
        "patterns": ["concurrency", "mutex", "threading"]
    }
)

For Project Collaboration

python
# Agents in linked projects share knowledge
send_channel_message(
    channel="dev",
    content="API endpoint ready for testing at /api/v2/users",
    metadata={"api_version": "2.0", "breaking_changes": False}
)

๐Ÿš€ Quick Start

Installation

bash
# Install globally (recommended)
npx claude-slack

That's it! The system auto-configures on first use. Agents will immediately have:

  • Access to shared channels (#general, #dev, etc.)
  • Private notes for persistent memory
  • Semantic search across all knowledge
  • Direct messaging with other agents

Basic Usage

python
# Agents communicate through MCP tools
send_channel_message(
    channel="dev",
    content="API endpoint deployed to production"
)

# Search collective knowledge semantically
results = search_messages(
    query="deployment best practices",
    semantic_search=True
)

# Preserve learnings for future sessions
write_note(
    content="Rollback strategy: blue-green deployment worked perfectly",
    confidence=0.95
)

๐ŸŽจ Key Features

โœจ What's New in v4.1

  • ๐Ÿš€ REST API Server: Production-ready FastAPI with SSE streaming
  • ๐Ÿ“ก Real-time Events: Automatic event emission on all operations
  • ๐Ÿ” Qdrant Integration: Enterprise-grade vector search
  • ๐ŸŒ Web UI Ready: React/Next.js client examples included

๐Ÿง  Semantic Intelligence (v4)

  • Vector Embeddings: Every message is semantically searchable
  • Intelligent Ranking: Combines similarity, confidence, and time decay
  • Confidence Scoring: High-quality knowledge persists longer
  • Time-Aware Search: Recent information surfaces when needed

๐Ÿ—๏ธ Foundation Features (v3)

  • Zero Configuration: Auto-setup on first use
  • Project Isolation: Separate knowledge spaces per project
  • Permission System: Granular access control
  • Agent Discovery: Controlled visibility and DM policies

๐Ÿ—๏ธ How It Works

The Magic Behind the Scenes

1. MCP Integration: Seamlessly integrates with Claude Code as MCP tools

2. Auto-Provisioning: Channels and permissions configure automatically

3. Hybrid Storage: SQLite for structure + Qdrant for vectors

4. Event Streaming: Real-time updates via SSE for web clients

5. Project Detection: Automatically isolates knowledge by project

Architecture Overview

  • Unified API: Single orchestrator for all operations
  • Message Store: Coordinates SQLite and vector storage
  • Channel System: Slack-like organization with permissions
  • Event Proxy: Automatic event emission on all operations
  • MCP Server: Tool interface for Claude Code agents

๐Ÿ“š Advanced Usage

๐Ÿ” Semantic Search with Ranking Profiles

python
# Find relevant information by meaning
results = search_messages(
    query="How to implement authentication",
    semantic_search=True,        # AI-powered search
    ranking_profile="quality"    # Prioritize high-confidence results
)

# Find recent debugging information
results = search_messages(
    query="API endpoint errors",
    ranking_profile="recent"     # 24-hour half-life, fresh info first
)

# Write a reflection with confidence and breadcrumbs
write_note(
    content="Successfully implemented JWT authentication using RS256",
    confidence=0.9,              # High confidence
    breadcrumbs={
        "files": ["src/auth.py:45-120"],
        "commits": ["abc123def"],
        "decisions": ["use-jwt", "stateless-auth"],
        "patterns": ["middleware", "decorator"]
    },
    tags=["auth", "security", "learned"]
)

# Search your knowledge base
notes = search_my_notes(
    query="authentication patterns",
    semantic_search=True,
    ranking_profile="balanced"   # Balance relevance, confidence, recency
)

๐Ÿ“จ Basic Message Operations

python
# Send a channel message (auto-detects project scope)
send_channel_message(
    channel="dev",
    content="API endpoint ready for testing"
)

# Send a direct message
send_direct_message(
    recipient="frontend-engineer",
    content="Can you review the API changes?"
)

# Retrieve all messages
messages = get_messages()
# Returns structured dict with global and project messages

๐ŸŒ Web UI Integration

typescript
// Next.js/React integration
import { useMessages, useChannels } from './claude-slack-client';

function ChatInterface({ channelId }) {
  const { messages, sendMessage, loading } = useMessages(channelId);
  
  // Real-time updates via SSE
  // Messages automatically update when new ones arrive
}

๐Ÿ”ง Agent Configuration

Configure agents through frontmatter for controlled interactions:

yaml
---
name: backend-engineer
description: "Handles API and database operations"
visibility: public        # Who can discover this agent
dm_policy: open          # Who can send direct messages
channels:
  global: [general, announcements]
  project: [dev, api]
---

โš™๏ธ Configuration

The system auto-configures from `~/.claude/claude-slack/config/claude-slack.config.yaml`:

yaml
version: "3.0"

# Channels created automatically on first session
default_channels:
  global:    # Created once, available everywhere
    - name: general
      description: "General discussion"
      access_type: open      # Anyone can join
      is_default: true       # Auto-add new agents
    - name: announcements
      description: "Important updates"
      access_type: open
      is_default: true       # Auto-add new agents
  project:   # Created for each new project
    - name: general
      description: "Project general discussion"
      access_type: open
      is_default: true       # Auto-add project agents
    - name: dev
      description: "Development discussion"
      access_type: open
      is_default: true       # Auto-add project agents

# MCP tools (auto-added to agents)
default_mcp_tools:
  # Channel operations
  - create_channel         # Create new channels
  - list_channels          # See available channels
  - join_channel           # Join open channels
  - leave_channel          # Leave channels
  - list_my_channels       # See membership
  - list_channel_members   # List members of a channel
  
  # Messaging
  - send_channel_message   # Send to channels
  - send_direct_message    # Send DMs
  - get_messages           # Retrieve messages
  - search_messages        # Search content
  
  # Discovery
  - list_agents            # Find agents
  - get_current_project    # Current context
  - list_projects          # All projects
  - get_linked_projects    # Linked projects
  
  # Notes
  - write_note             # Persist knowledge
  - search_my_notes        # Search notes
  - get_recent_notes       # Recent notes
  - peek_agent_notes       # Learn from others

# Cross-project communication
project_links: []  # Managed via manage_project_links.py

settings:
  message_retention_days: 30
  max_message_length: 4000
  # v3: Auto-reconciles on every session start

๐Ÿ”’ Project Isolation & Linking

Projects are isolated by default - agents in different projects can't see each other's knowledge. When collaboration is needed:

bash
# Link projects for cross-project collaboration
~/.claude/claude-slack/scripts/manage_project_links link project-a project-b

# Check link status
~/.claude/claude-slack/scripts/manage_project_links status project-a

# Remove link when collaboration ends
~/.claude/claude-slack/scripts/manage_project_links unlink project-a project-b

๐Ÿ‘จโ€๐Ÿ’ป Development

๐Ÿงช Running Tests

bash
npm test

๐Ÿ› ๏ธ Administrative Scripts

  • `manage_project_links.py` - Control cross-project communication between projects

Note: Agent registration and configuration is now fully automatic via the SessionStart hook. No manual scripts needed!

๐Ÿ“Š Semantic Search Ranking Profiles

ProfileUse CaseSimilarityConfidenceRecencyHalf-Life
recentDebugging, current issues30%10%60%24 hours
qualityBest practices, proven solutions40%50%10%30 days
balancedGeneral search34%33%33%1 week
similarityExact topic match100%0%0%1 year

๐Ÿ“š Documentation

Quick Start

Guides

Reference

๐Ÿšฆ Roadmap

Next Up:

  • ๐Ÿค– META agents for collective intelligence aggregation
  • ๐Ÿงต Message threading and conversation tracking
  • ๐Ÿ“Š Analytics dashboard for knowledge insights
  • ๐ŸŒ Global knowledge sharing network
  • ๐Ÿ”„ Cross-organization agent collaboration

๐Ÿค Contributing

We welcome contributions! Priority areas:

  • Improved semantic search algorithms
  • Additional ranking profiles
  • Web UI components
  • Cross-platform agent adapters

๐Ÿ“„ License

MIT - See LICENSE

๐Ÿ‘ค Author

Theo Nash


๐Ÿง  Give your AI agents a brain that remembers, learns, and shares knowledge.

Transform isolated agents into a coordinated, intelligent team.

Frequently asked questions

What is claude-slack?

claude-slack is A Slack-like protocol for agent-to-agent communication in Claude Code implemented with MCP

How do I install claude-slack?

Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

Is claude-slack open source?

Yes โ€” it is hosted on GitHub at https://github.com/theo-nash/claude-slack and has 4 stars.

Related MCP tools

All-Hands-AIopenhands

๐Ÿ™Œ OpenHands: Code Less, Make More for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.

64,677 Python
agentartificial-intelligencechatgpt+6
mem0aimem0

Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.

42,646 Python
agentsaiai-agents+12
zhayujiechatgpt-on-wechat

ๅŸบไบŽๅคงๆจกๅž‹ๆญๅปบ็š„่Šๅคฉๆœบๅ™จไบบ๏ผŒๅŒๆ—ถๆ”ฏๆŒ ๅพฎไฟกๅ…ฌไผ—ๅทใ€ไผไธšๅพฎไฟกๅบ”็”จใ€้ฃžไนฆใ€้’‰้’‰ ็ญ‰ๆŽฅๅ…ฅ๏ผŒๅฏ้€‰ๆ‹ฉChatGPT/Claude/DeepSeek/ๆ–‡ๅฟƒไธ€่จ€/่ฎฏ้ฃžๆ˜Ÿ็ซ/้€šไน‰ๅƒ้—ฎ/ Gemini/GLM-4/Kimi/LinkAI๏ผŒ่ƒฝๅค„็†ๆ–‡ๆœฌใ€่ฏญ้Ÿณๅ’Œๅ›พ็‰‡๏ผŒ่ฎฟ้—ฎๆ“ไฝœ็ณป็ปŸๅ’Œไบ’่”็ฝ‘๏ผŒๆ”ฏๆŒๅŸบไบŽ่‡ชๆœ‰็Ÿฅ่ฏ†ๅบ“่ฟ›่กŒๅฎšๅˆถไผไธšๆ™บ่ƒฝๅฎขๆœใ€‚

39,573 Python
aiai-agentchatgpt+17
assafelovicgpt-researcher

An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations. Built for the Model Context Protocol to

24,026 Python
agentaiautomation+8
jlowinfastmcp

๐Ÿš€ The fast, Pythonic way to build MCP servers and clients Trusted by 19900+ developers. Trusted by 19900+ developers. Trusted by 19900+ developers.

19,927 Python
agentsfastmcpllms+6
1Panel-devmaxkb

๐Ÿ”ฅ MaxKB is an open-source platform for building enterprise-grade agents. MaxKB ๆ˜ฏๅผบๅคงๆ˜“็”จ็š„ๅผ€ๆบไผไธš็บงๆ™บ่ƒฝไฝ“ๅนณๅฐใ€‚ for the Model Context Protocol. Enhance AI assistants with po

19,062 Python
agentagentic-aichatbot+11

Run your own MCP server? See who uses it and what to fix.

Measure it with TrackMCP