Databases for AI agents
100 security-reviewed databases listings, skills, MCP servers, and toolkits you can install into Claude Code, Cursor, and other agents with one command.
Vlm Code Context Mcp
MCP server that indexes codebases into a SQLite database, exposing file metadata, exports, dependency graphs, and per-file change tracking.
Zalo Agent
Self-hosted AI agent living inside Zalo (personal account). Multi-account, 15 tools + external MCP servers, web dashboard, scheduler, durable memory, rich-text messages. Provider-agnostic: any OpenAI-compatible endpoint or Anthropic. TypeScript + SQLite. MIT.
Docker Compose Patterns
Use this skill when creating, modifying, or debugging Docker Compose configurations, even if the user just says they need to wire services together, add a database to their stack, or set up a local development environment with multiple containers. Covers service definitions, health checks, dependency ordering, volumes, networks, environment variables, and development overrides.
Docker Project Foundations
Use this skill when setting up, initializing, or Dockerizing a project, even if the user doesn't explicitly mention Docker but describes a need for containerized local development, adding a database or cache dependency, or running services without host-level installs. Covers Dockerfile, compose.yaml, and .dockerignore creation with Docker best practices.
Supabase Postgres Best Practices
>-
Kry System
Act 3 — Dữ liệu + Kiến trúc (cửa 1 chiều). Trigger khi user gõ /kry-system, hoặc nói 'thiết kế data model', 'schema cho app', 'kiến trúc hệ thống', 'dựng nền kỹ thuật', 'chốt stack + database', 'auth thế nào', sau khi đã có UX spec từ /kry-ux. Skill define TƯƠI cho app này: entity→bảng→field→ràng buộc + state machine + boundary/contract + auth/role (RLS) + stack + host. Spawn agent challenger-sys…
Ls Context Index
Use when building, querying, or refreshing the LocalSetup context index with hybrid SQLite retrieval, deterministic freshness/worklist surfaces, and agent-preflight checks.
Secaiq Watch
Local, read-only monitor for the AI tools on your computer: network activity, permissions, findings, token usage. macOS, Linux, Windows. Beta.
Context
File project knowledge the user shares conversationally into the correct .ai/ files - purpose, rules, database, dependencies, conventions, decisions - and close the memory loop at the end of tasks and sessions. Use when the user shares project context, decisions, or conventions, or when finishing a task in an initialized project.
Postgres
PostgreSQL schema design, queries and migrations.
Text To Sql
|
Cheat Status
cheat-on-content 的状态看板。显示当前模式 / rubric 版本 / 校准进度 / 待复盘 / pool 状态 / 是否该升级 SQLite / 是否该 bump rubric。**任何时候都可调，无副作用**。触发词："状态"/"看板"/"status"/"我现在该做什么"/"进度怎么样"。
Firebase Game Backend
Use when building or reviewing Firebase-backed game features for Unity or JavaScript, including Firebase Auth, Cloud Firestore, Realtime Database, Cloud Functions Gen2, Express.js HTTP APIs, Unity request/response clients, Cloud Storage, Remote Config, Analytics, App Check, security rules, local emulators, deployment, data modeling, and client/server boundaries.
Duckdb
Query, transform, and export files or databases with DuckDB and SQLite.
Attesttag
An AI teammate for Slack and Microsoft Teams that runs on open-weight models through any OpenAI-compatible endpoint. One Go binary with an admin console; SQLite or Postgres; self-host with Docker or Helm.
Find All
Write "Find all..." and query the public web like a database. Returns structured rows with a source URL under every single field, routed through Bright Data's indexed datasets when one covers the entity and through live multi-query search when none does. Triggers on "find all", "list every", "who are all the", "build me a table of", "which companies/people/products", or /find-all.
Agy Memory Engine
Lightweight SQLite FTS5 dynamic memory layer & MCP server for Google Antigravity (AGY)
Caching
Decide what to cache, at which layer, for how long, and how it gets invalidated — before any cache is added. Use when someone proposes caching to make a read path faster, when stale or cross-user data is suspected, when adding a TTL or a Redis/CDN layer, or when reviewing a change that introduces one. Not for fixing a slow query or an N+1 (do that first — a cache over a bad query hides it), and n…
Idempotency And Retries
Make an operation safe to repeat — idempotency keys and their storage, what a replay returns, retry policy with backoff and jitter, and how to reconcile after a timeout whose outcome is unknown. Use when an operation has an external side effect (a charge, an email, a provisioning call), when a caller needs to retry safely, or when duplicates have already appeared in production. Not for webhook re…
Data Quality
Decide what must be true of a dataset and where that assertion belongs — freshness against event time, volume floors and bands, distribution and referential checks, source reconciliation, and whether it should be a schema constraint, a blocking publish gate or an alert. Use when adding or reviewing data checks, when a wrong number reached a consumer and nothing caught it, or when a check fires so…
Data Integrity
Keep data correct over time — write the invariants down, push each one to the lowest layer that can enforce it, cover the rest with reconciliation queries, and detect drift before a user reports it. Use when deciding where a rule should be enforced, auditing a schema whose rules live only in application code, building reconciliation or drift checks, or investigating data that looks wrong. Not for…
Postgres
Postgres behaviour worth checking before relying on it — type choices, index kinds and their costs, reading EXPLAIN output, isolation levels and lock behaviour during DDL, and row-level security. Use when the project runs on Postgres (including Postgres-backed services) and a decision depends on what the engine actually does: picking a column type, adding an index, changing isolation, or writing…
Api Design
Design or change an HTTP API — resources, verbs, status codes, one error shape, pagination, versioning, and an OpenAPI description that cannot drift from the handlers. Use when adding or reshaping endpoints, when asked what a response should return, or when reviewing whether a change to a published API breaks its consumers. Not for choosing between REST, GraphQL and RPC, not for database schema d…
Query Optimization
Make one slow query fast without guessing — capture the plan, find where the time actually goes, change one thing, and measure again on comparable data. Use when a query, endpoint or report is slow and the database is the suspect, when a plan needs reading, or when someone proposes an index with no evidence. Not for modelling decisions about tables and constraints, not an engine feature reference…
Migrations
Change a live schema without breaking the application on it — expand/contract sequencing, lock-safe DDL, batched backfills, and a rollback that is actually reachable. Use when writing, reviewing or sequencing a migration that will run against a database holding real data with live readers. Not for designing a schema from scratch, not for proving afterwards that a migration did what it claimed (th…
Database Migration Verification
Prove a migration did what it claimed — before/after row counts, column checksums, constraint and index state, invariant queries, an exercised application read path, and a rehearsed rollback. Use after a migration has been applied to any environment and before anyone reports it as working, or when reviewing someone else's claim that a migration succeeded. Not for planning or sequencing the migrat…
Schema Design
Turn what a system must guarantee into tables, keys and constraints — normalization judgement, nullability, foreign key behaviour, and naming that survives. Use when designing new tables, reviewing ORM models or a migration's DDL, or when a bug reduces to "the database allowed a row that should be impossible". Not for tuning a slow query, not for engine-specific syntax and features, and not for w…
Retrieval Rag
Build and fix retrieval that actually returns the right passage — structure-aware chunking, one pinned embedding model, lexical plus vector search fused, reranking, and a recall measurement that is run separately from the generator. Use when a RAG system answers wrong or vaguely, when an index is being designed or reindexed, or when someone proposes a prompt change to fix what is really a retriev…
Golive
Take an agent-written app from repo to live production on the user's OWN accounts, with providers they choose (hosting, database, auth, payments, email, domain/DNS). The human connects accounts and approves changes; supported wiring operations run through a local CLI and produce verification evidence with explicit limits. Use when the user wants to ship, deploy, go live, launch, publish, or put t…
Montycat Dart
AI-native NoSQL + vector database with built-in semantic search for RAG & AI agents — the Dart & Flutter client. Self-hosted Pinecone alternative.
Atmem
Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works with OpenClaw, MCP, Pydantic AI, and LangChain/LangGraph. No external API required for local memory. Install with pip: pip install atmem
Memoose
A dual-path memory system for proactive agents. Facts and procedures in a local knowledge graph, exposed as a CLI, MCP tools and skills. No API key.
Bgts Context Engine
Deterministic code-graph context engine for AI coding agents - PostgreSQL + Apache AGE + pgvector, MCP & REST, no LLM in the loop.
Publisher
Publisher is the open-source analytics engine for Malloy. It lets you define data models once — and use them everywhere.
Selfhost Ai
One-command installer for a self-hosted AI stack on your own server: n8n, Ollama, Open WebUI, OpenClaw, Dify, Flowise, Supabase, ComfyUI, Qdrant & 30+ tools. Docker Compose, automatic HTTPS via Caddy, built-in monitoring. Free Zapier/Make alternative.
Mssql Mcp
A Model Context Protocol (MCP) server for Microsoft SQL Server, built in C#/.NET 10
Vibex
Generate ERD (entity-relationship), C4 (context/container/component), API endpoint catalogue, and lifecycle/state-machine diagrams as a validated JSON spec plus a standalone interactive HTML viewer. Imports OpenAPI, GraphQL SDL, and Prisma schemas directly; when no spec file exists, reads the code (NestJS controllers/resolvers, TypeORM/Prisma entities) and authors the JSON by hand. Use when the u…
Kevy
kevy — a pure-Rust, zero-dependency, Redis-compatible serving engine: declared indexes, CJK full-text + vector search, views, CDC feeds, replication & failover, MCP
SoDam O Brain Codex
Codex 대화의 결정·제약·선호를 로컬 SQLite에 기억하고 검색·2D/3D 그래프·타임라인·백업으로 관리하는 로컬 우선 MCP 플러그인
Briefd
Your agents, briefed. Not flooded. Self-hosted context compiler: git-backed team knowledge served to coding agents as token-budgeted bundles over MCP.
Aldus Palace
A trustworthy context layer for AI that remembers, plans and acts — free text into typed commitments, decisions and memories, each with its evidence, in a SQLite file you own. MCP, HTTP, library and typed client.
Arie B2b Enrichment Engine
Cost-aware revenue intelligence engine that selectively buys enrichment evidence, knows when to stop, and produces auditable Decision Receipts.
Second Brain System
A second brain an AI keeps alive with you: a plain-text graph database (Obsidian + git) that separates durable knowledge from daily operation. Bilingual guide, schema & templates.
Synapse
Private local memory for any AI agent: Markdown database, SQLite search, MCP, zero runtime dependencies.
Nano Lumen
Nano-Lumen is resident general-purpose agent for Windows desktop, designed as a persistent-state system: cross-session, crash-recoverable, local-first privacy. (Beta)
Hkex Filing Scraper
Scrape 25+ years of HKEx (Hong Kong Stock Exchange) regulatory filings into PostgreSQL, MySQL/MariaDB, SQLite, MongoDB, Neo4j, ClickHouse, DuckDB, or SurrealDB — with full-text extraction, graph linking, and a hosted MCP server for AI agents.
OpsMaxx
Free, open-source SSH client, SFTP, tunnels, database GUI and a secure AI-agent (MCP) bridge in one app a MobaXterm, PuTTY and Termius alternative for Windows, macOS and Linux.
Session Knowledge
Turn your Claude Code session history into a searchable local knowledge base — 13 MCP tools, pure stdlib, nothing leaves your machine
Ecorp
Your 24/7 software factory with all of your human and agent team mates in one digital office. An entire AI company at work: Copilot, Codex, Claude Code & OpenCode crews, multiplayer control, isolated worktrees, human approvals, and evidence-backed pull requests.
Nestrs
Nestrs is a Rust web framework that lets you build structured APIs using the same architectural patterns as NestJS — modules, controllers, providers, and dependency injection — while running on Axum and Tower. If your team already knows NestJS, nestrs gives you the same mental model with Rust’s performance and safety guarantees.
Friday
⚡ The open-source persistent cognitive memory layer for AI coding agents. Stop your Cursor, Claude & Copilot from having amnesia.
Mnemiq
Open-source text-to-SQL engine you tune and measure on your own database
Memnest
Source-backed local memory shared by Claude Code, Codex, pi, and MCP clients. No generative LLM.
Fivem Natives
FiveM/GTA V native verification and lookup database (7191 natives, offline). ALWAYS use it when writing, editing or reviewing FiveM Lua/JS code involves a native name, signature, parameter order or client/server side — even if the user does not ask. Do not write a native name from memory; verify it first. Triggers - FiveM, Cfx, GTA V native, QBCore, QBX, ESX, ox_lib, client.lua/server.lua, fxmani…
Fivem Assets
GTA V / FiveM asset data and measured production rules — props, objects, doors, ytyp/ymap/MLO, LOD, grass, flags, particles (.ypt), shader/texture/light/timecycle/decal/parallax, clothing, vehicles; vanilla animation name and bone tag lookup. Use it to look at the real data BEFORE WRITING CODE in any prop, door, map, effect or look task, even if the user does not ask. Triggers — model name (prop_…
Muto Atlas
Ground truth for FiveM / GTA V development: a knowledge tree, offline data layers built from your own game, a searchable snippet database and a read-only MCP server — for Claude Code, Codex, Gemini CLI, Cursor, Copilot and ChatGPT.
Devbox Stack
Use when 容器内 agent 需要启停/配置/排障中间件（mysql、redis、rabbitmq、minio 等）、查询标准连接串、或目录外追加服务。前置门禁：`test -d /cadence/stack && command -v stack` 不满足时本 skill 不适用——声明不适用并按普通流程继续，不模拟其行为。
Sink
Manage peepshow's persistent auto-sink list (list, add, remove, clear). Use when the user asks to turn a peepshow sink on or off, enable folder/mysql/webhook sinks, or wants to see which sinks are currently active. Sinks run on every peepshow extraction.
Hermes Fleet Memory
Zero-bloat distributed vector memory, hardware-enforced domain firewalls, and NAT-traversing execution mesh for multi-instance Hermes agent fleets.
Neo Agent Brain
Point a cross-model AI engineering team at your own codebases. The Agent OS keeps named AI maintainers' identity, memory and review across labs alive between sessions — the Brain Neo.mjs runs on itself. Multi-tenant: onboarding a codebase is a config entry, not a fork.
Yoetz
Yoetz — local-first structured work evidence, deterministic checks, and honest verification receipts.
DBPilot
Self-hosted database performance diagnostics for SQL Server, MySQL & PostgreSQL: trends, AAS insight, Top SQL, plan-change tracking, blocking & deadlock analysis. Single-process deploy, built-in MCP server for AI agents.
Claude Manual Todos Plugin
Claude records the manual steps only you can do — a form in some console, a secret to seed, a review to answer — in local SQLite, and you work through them on a board that looks different for every project.
Motif
Working memory for AI coding agents, yours and your team's. Sessions from Claude Code, Codex and Cursor become one living graph of decisions, files and the ties between them, queryable by your agents over MCP. Motif flags contradictions for a human to rule on, then an agent opens PRs to keep code true to them. Self-hosted, no cloud.
Nxopen Mcp
MCP server giving AI coding agents accurate Siemens NXOpen .NET API knowledge via hybrid retrieval (BGE-M3 + sqlite-vec), built from your own licensed NX installation
Architecture Memory
Use Beyond Entity as persistent AI architecture memory to recover project context, review or evolve architecture, implement code from current BE designs, and synchronize architecture after code changes through MCP. Use for Beyond Entity project work, not unrelated database design.
Mnemosyne
Evidence-backed memory for AI agents: local-first recall, temporal history, tested skills, and gradual migration.
Ulpia
The memory is yours. The model is a guest. Local-first memory and retrieval layer for AI agents: RAG with no model in the path, abstention as a verdict, MCP server, evaluation included. Rust, Apache 2.0.
Tallybook
Prices your Claude Code and Codex sessions from the transcripts on disk, shows what each agent cost over any period, and tells you in plain English what would have been cheaper. CLI, Browser UI and MCP server.
Mnemo
Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.
Parse Dmarc
DMARC aggregate report parser with a built-in dashboard. One Go binary, IMAP in, SQLite, Prometheus metrics, MCP server. Apache-2.0.
Keycloak Entities
Use for any work touching Keycloak's database — writing JPQL or SQL against Keycloak entities, designing migrations, building extensions, debugging FK/cascade issues, or mapping Keycloak's domain model to its schema. Covers the Keycloak schema, ER diagram, entity classes, and migrations across ~90 tables including USER_ENTITY, KEYCLOAK_ROLE, KEYCLOAK_GROUP, CLIENT, USER_ROLE_MAPPING, USER_GROUP_M…
Backtest Database Schema For Point In Time Queries
>-
Open Map Stack
Use textual agent instructions for GIS and geospatial work: source discovery and provenance, vector/raster/point-cloud pipelines, CRS and metric analysis, spatial SQL, routing and isochrones, QGIS projects, tile generation, and web maps. Use advanced tools and formats such as OSM, Overture, STAC, Sentinel/Landsat, LiDAR, GeoPackage, GeoParquet, COG, PMTiles, WMS/WFS/OGC APIs, Portolan catalogs, G…
Relayhall
Open-source, self-hosted workspace where people and AI agents coordinate tasks, share reports, and collaborate under governed access.
Flow
Agent-first kanban board
Cubrid Mcp Server
A Model Context Protocol (MCP) server for CUBRID database — enabling LLMs to inspect schemas and execute read-only queries via pycubrid.
Search Elixpo
OreoLook — an open-source, OpenAI-compatible agentic web search and deep-research engine with streaming, MCP tools, Redis memory, Qdrant retrieval, and PDF exports.
Crystaljson
>-
Snowbank Contracts
>-
Foundationdb Keys And Layers
>-
Foundationdb Advanced Layers
Advanced engineering for sophisticated FoundationDB layers with the .NET client (FoundationDB.Client / SnowBank) — the cluster model and transaction lifecycle (proxies, resolvers, tlogs, storage servers, the sequencer/version clock), latency/throughput optimization (batching reads with GetValuesAsync / Task.WhenAll, removing round-trip dependencies, snapshot reads), high-contention avoidance, and…
Snowbank Betterhttp
How to make outbound HTTP calls with BetterHttpClient (SnowBank.Networking.Http) in an ASP.NET Core or generic-host .NET application - the DI story and the request API. Covers the one-policy-plane model where a client NAME maps to one effective policy that lives in the pooled handler chain, so every client gets the same behavior: a typed client, a keyed client, IHttpClientFactory.CreateClient(nam…
Snowbank Distributed Testing
How to write, run, and especially DIAGNOSE multi-node integration tests built on the SnowBank distributed-test framework (SnowBank.Testing.Framework / SnowBank.Testing.Common — a general-purpose harness, NOT FoundationDB-specific). Covers DistributedTest/MakeItSo + virtual hosts (AddSimpleLan/WithMinimalWebHost), the unified in-memory Timeline journal that every test prints (its column format and…
Foundationdb Aspire
How to run a FoundationDB cluster and connect to it from .NET — getting the IFdbDatabaseProvider that the keys/transactions/layers skills assume you already have. Covers the ways to get a provider (plain DI services.AddFoundationDb, FdbDatabaseProvider.Create, or Aspire), the Aspire AppHost integration (FoundationDB.Aspire.Hosting — builder.AddFoundationDb starts a Docker cluster, AddFoundationDb…
Snowbank Slices And Buffers
How to correctly use the Slice type and its companions (SliceReader, SliceWriter, SliceOwner) for binary data in the FoundationDB .NET client / SnowBank.Core codebase. Slice is a readonly struct (namespace System) — the logical equivalent of a ReadOnlyMemory of bytes with many helpers. Use whenever code constructs or reads a Slice, converts between bytes and other types (Slice.FromBytes/FromStrin…
Foundationdb Transactions
>-
Douyin TikTok Download API
🚀 Self-hosted TikTok & Douyin scraper and no-watermark video downloader — async REST API, MCP server, CLI and web console for posts, profiles, comments and playlists. Self-healing identity pool, PostgreSQL archive, one docker compose up. 抖音、TikTok 数据采集与无水印视频下载 API，自托管，支持 MCP 调用与 Docker 一键部署。
Anansi
Open-source personal web memory for developers and AI agents. Capture browser saves, keep a searchable library, and query it over MCP.
Backend Dev Guidelines
You are a senior backend engineer operating production-grade services under strict architectural and reliability constraints. Use when routes, controllers, services, repositories, express middleware, or prisma database access.
Database Design
Database design principles and decision-making. Schema design, indexing strategy, ORM selection, serverless databases.
Full Talent
Use when the user wants to source candidates for a role. Acts as a senior talent acquisition partner and headhunter: runs a deep conversational intake to understand the role, team, and hiring context, searches FullEnrich's database with surgical precision, enriches candidates with email + phone, qualifies and ranks them with detailed Tier 1 profiles, and recommends the best outreach channel per c…
StructSmith
Local-first, MCP-native tool for modelling software architecture. C4-style semantic model, React Flow editor, SQLite, single container — a self-hosted Structurizr alternative your AI client can edit over MCP.
Sql Injection Prevention
>
Sim Trade
A 股专用的确定性模拟交易系统。具备严格的数据真实性门禁、五档盘口真实撮合、T+1 规则、持仓盈亏计算及 SQLite 可审计流水账本。当用户需要进行模拟交易下单、模拟买入/卖出、查询模拟盘持仓、账户资产或重置模拟盘时触发（包含触发词：模拟买入, 模拟卖出, 模拟交易, 查持仓, 模拟盘, 交易账本, sim trade, paper trading）。
Spfn
Take your AI-built app from prototype to production. A TypeScript full-stack framework for Next.js apps built with AI coding agents: every feature is one fixed vertical slice — entity, repository, route, router — so an agent cannot invent a different shape each time. Auth, storage, jobs and MCP ship as packages.
Hopai
A knowledge graph in the Postgres you already run — multi-hop traversal, mutation, and vector search via recursive CTEs on two plain tables. No graph database, no extension.
OpenWorkbuddy
A local-first macOS desktop agent with BYOK models, auditable tools, approvals, MCP, Chrome control, memory, automation, and crash recovery.
Flydb
给开发、运维和 AI Agent 的数据库迁移工具：CLI + 本机 GUI，共用配置、预览与执行记录；覆盖主流与国产数据库，Java 8 零依赖内核。
Ollama Chat Application
A production-ready conversational AI app powered by Chainlit and Ollama, with multi-modal document processing, MCP tool integration, and persistent chat sessions. Handles voice input, file analysis (PDF, DOCX, images), and dynamic LLM switching via customizable chat profiles. Easily deployable on Railway for fast, scalable cloud hosting