Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Awesome-CUA
Agents & frameworksOpen, source-backed catalog of computer-use agents: reviewed papers, GUI models, datasets, benchmarks, tools, and reusable JSONL/SQLite data.
git clone https://github.com/reacher-z/Awesome-CUA.git -
aws-agentic-document-assistant
Agents & frameworksAn agent based LLM assistant that extends RAG with batch entity extraction and SQL querying to improve performance on multi-step and analytical questions.
git clone https://github.com/aws-samples/aws-agentic-document-assistant.git -
National Vulnerability Database
Public APIsU.S. National Vulnerability Database
-
Dangerous Discord Database
Public APIsDatabase of malicious Discord accounts
-
IBM Db2 for i
MCP serversRead-only SQL queries and schema inspection for IBM Db2 for i over ODBC, JT400 or Mapepire (SSH).
mcp-server-db2i@3.8.8 -
rekindle
MCP serversMCP session continuity engine: boot reports, PreCompact capture, session-start delivery, SQLite.
rekindle@0.5.1 -
memwright
MCP serversEmbedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.
memwright@0.1.3 -
LiteScope
MCP serversOperations toolchain for SQLite, Cloudflare D1 & Turso: inspect, diff, migrate, monitor & repair.
litescope@0.9.0 -
chart-canvas
MCP serversCreate interactive visualizations and query data sources (SQLite, CSV, Parquet, JSON)
@gluip/chart-canvas-mcp@0.3.2 -
Facthouse
MCP serversLocal AI memory: neuroscience-inspired Data→Information→Knowledge in SQLite you own.
@facthouse/mcp@0.31.0 -
sync82
MCP serversPersistent, structured project memory for AI coding agents, stored locally in SQLite.
https://github.com/oito2/mcp-sync82/releases/download/v1.3.1/sync82.mcpb@1.3.1 -
memex
MCP serversPersistent session memory for Claude Code. Local SQLite, no LLMs, no network.
mcp-memex@0.1.9 -
clude
MCP serversPortable agent memory anchored on Solana. Local SQLite + vector recall, open export.
@clude/sdk@3.0.4 -
data-agent-tutorial
AI repositoriesData-Agent:从 0 到 1 构建 Text2SQL 智能体实战教程,覆盖 StateGraph 编排、双重 RAG、关系图谱、HITL 人工确认、SQL 自动纠错、Python Docker 沙盒执行与 A2A + SSE 流式交互。
git clone https://github.com/qifan777/data-agent-tutorial.git -
trench
AI repositoriesTrench — Open-Source Analytics Infrastructure. A single production-ready Docker image built on ClickHouse, Kafka, and Node.js for tracking events. Easily build product analytics dashboards, LLM RAGs, observability platforms, or any other analytics product.
git clone https://github.com/FrigadeHQ/trench.git -
Agent_Memory_Techniques
AI repositoriesAgent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.
git clone https://github.com/NirDiamant/Agent_Memory_Techniques.git -
Chuck Norris Database
Public APIsJokes
-
Cortex RMCP
MCP serversSelf-hosted homelab log intelligence over MCP, CLI, and REST with SQLite/FTS.
@dinglebear/cortex@3.13.2 -
ZenBrain Memory
MCP serversAgent memory: working, episodic, semantic, procedural and core layers. Local SQLite, no account.
@zensation/mcp@0.3.1 -
elen
MCP serversRecords coding-agent decisions with their limits and marks old ones superseded. Local SQLite.
@learningnodes/elen-mcp@0.3.1 -
Palace
MCP serversLocal-first memory for coding agents — MCP server, single SQLite file, local embeddings
https://github.com/AncientiCe/palace-rs/releases/download/v0.20.0/palace-0.20.0.mcpb@0.20.0 -
claude-amplifier
MCP serversPersistent memory + decision tracking for Claude across sessions. Local SQLite, no cloud.
claude-amplifier@1.5.3 -
metabrain
MCP serversMCP server giving AI agents persistent SQLite memory that proves which lessons hold.
metabrain@1.1.2 -
memors
MCP serversLocal, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.
https://github.com/kKEo/memors/releases/download/v1.6.8/memors-mcp_1.6.8_linux_amd64.tar.gz@1.6.8
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.