{"repo":"caura-ai/caura-build-fleet","free":true,"listed":false,"github":"https://github.com/caura-ai/caura-build-fleet","clone":"git clone https://github.com/caura-ai/caura-build-fleet.git","description":"A runnable reference implementation of multi-agent constraint propagation using MemClaw. 5 specialists share memory via MCP so decisions made upstream automatically govern downstream agents.","language":"Python","stars":28,"topics":["agent-fleet","agent-memory","ai-agents","ai-pipeline","constraint-propagation","llm","mcp","model-context-protocol","multi-agent","python"],"license":"Apache-2.0","category":"ai-agents","readme_excerpt":"MemClaw Fleet: 5-Agent Pipeline with Shared Memory A runnable reference implementation of multi-agent constraint propagation using MemClaw. Each agent recalls what the previous one decided before acting. Clone it, run it, adapt it to any domain. What is MemClaw? · Why Multi-Agent? · Quickstart · New Fleet · Query Memories · Add an Agent --- What Is MemClaw? MemClaw is a governed shared memory platform built for AI agent fleets. It's not a vector database bolted onto your pipeline; it's a memory layer designed from the ground up for multi-agent coordination. New to MCP? MCP (Model Context Protocol) is an open standard that lets LLMs call external tools via a consistent interface. MemClaw exposes its memory operations as MCP tools, so any MCP-compatible agent or IDE (Claude Code, Cursor, OpenClaw) can read and write fleet memory without custom integration code. Learn more → Core Features Feature What it means in practice :--- :--- Hybrid recall Vector similarity + keyword match + knowledge graph traversal in one call. Agents find relevant memories even when they paraphrase the original query. Fleet namespacing Every memory is scoped to a fleet id . Multiple fleets share one tenant without bleeding into each other. Row-level security scope agent flag makes a memory readable only by the writing agent. Per-row ACL enforced at the storage layer. Contradiction detection memclaw insights scans the fleet for conflicting rules across stored memories and surfaces them post-commit for ag","default_branch":null,"files":null,"tree":[],"storefront":"/r/caura-ai","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/caura-ai/caura-build-fleet/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}