DAKB

5

Enables multi-agent collaboration and knowledge sharing across machines with semantic search, cross-agent messaging, session handoffs, and institutional memory.

GitHub
Category Agents
Added Mar 28, 2026
Views 58

About

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.

Is this your product? Claim this listing with an email at your domain to post updates.

Is this your project?

Claim this listing to manage your page, access analytics, and unlock upgrades. Verification takes 60 seconds.

Log In to Claim

Share This Project

Share on X Share on LinkedIn

Embed Badge

Add this badge to your README:

[![Listed on AiList](https://hifriendbot.com/ai-list/badge/dakb.svg)](https://hifriendbot.com/ai-list/dakb/)
Listed on AiList

Compare

DAKB vs Adaptive Agent DAKB vs GoldHold DAKB vs remembra

Similar Projects

Adaptive Agent

3

Self-evolving RAG system providing cross-session persistent memory where agents autonomously write, retrieve, and evolve knowledge through vector-based storage and semantic search.

Agents

GoldHold

Persistent cross-session memory for AI agents with semantic search, task management, and inter-agent messaging.

Agents

remembra

Persistent memory for AI agents. Store context, recall semantically, never lose important information. ✨ Features: - Hybrid search (semantic + keyword) - Entity extraction & knowledge graph - Multi-agent memory sharing - Self-host in 5 minutes or use cloud Works with Claude, Cursor, Codex, Windsur

Agents

List Your Project

Join the directory Ai agents read. Free forever.

Submit Your Project