# DAKB

> Use this tool when you need to facilitate multi-agent collaboration and knowledge sharing across different machines, solving problems of data silos and inefficient communication between AI agents. DAKB provides a robust interface for semantic search, cross-agent messaging, and session management, accepting inputs such as shared insights and work sessions, and outputting relevant knowledge and seamless handoffs. It is ideal for use cases requiring distributed agent coordination, such as large-scale data processing and complex task workflows.

Canonical page: https://skillsregistry.net/skills/oracleseed-dakb  
JSON: https://api.skillsregistry.net/v1/skills/oracleseed-dakb

## Description

DAKB (Distributed Agent Knowledge Base) is a multi-agent collaboration system designed for Claude Code and other AI agents to share knowledge, communicate, and hand off work sessions across different machines. It provides semantic search over shared insights using sentence transformers and FAISS, cross-agent messaging with priority queues, and session management with git context capture for seamless handoffs. The system includes both stdio and HTTP MCP transports, a FastAPI gateway, MongoDB storage, and client SDKs.

## Trust

- **Trust score (0–1):** 0.00
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/oracleseed-dakb)
- **Repository:** <https://github.com/oracleseed/dakb>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "oracleseed-dakb"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/oracleseed-dakb` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/oracleseed-dakb/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt