RushDB is a graph + vector database and memory layer for AI agents. Push any JSON, get typed, searchable, relationship-aware records back — no schema, no migrations. Built on Neo4j.
This repository also configures its own agents. See what rushdb tells them →
Skill Claude CodeCodex
Operate RushDB as persistent agent memory across native OpenClaw or Hermes integrations, MCP tools, and custom SDK harnesses. Use when an agent must remember explicit facts, capture or recall prior turns, manage durable decisions and tasks, choose between native lifecycle memory and model-directed MCP, avoid duplicate…
Skill Claude CodeCodex
Model data in RushDB's property-centric LMPG graph. Use when designing or evolving schemas, choosing labels and properties, defining relationships, importing nested JSON, structuring a new use case, or modeling agent memory with EPISODE, MEMORYFACT, domain records, scope fields, semantic properties, and fact…
Skill Claude CodeCodex
Design a tailored RushDB schema for any use case through guided conversation. Use this skill when a user is starting a new project, unsure what labels to define, asking "what records should I create", or wants a scaffold for a known domain (e-commerce, healthcare, SaaS, CRM, agent memory, etc.). Interviews the user…
Skill Claude CodeCodex
Build faceted filter UIs on top of RushDB. Use this skill when generating code for filter sidebars, multi-select facets, range sliders, or any UI that lets users narrow a record set by property values. Covers the full flow: discover properties + types, enumerate distinct values, map each type to the right widget, and…
Skill Codex
Design, implement, review, or test native RushDB memory adapters for agent runtimes. Use when adding lifecycle-aware recall and persistence to a framework, mapping prompt/turn/compaction/session hooks, implementing AgentMemoryEvent v1, enforcing participant and sandbox scope, adding durable outbox delivery, or…
Skill Claude CodeCodex
Build RushDB queries, searches, filters, and aggregations. Use whenever an agent needs to list or filter records, count or group data, traverse relationships, run semantic/vector search, construct a findRecords call, discover live labels and properties, or recall canonical EPISODE and MEMORYFACT records with mandatory…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: