Library
88,222 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
Looks like a goal we have a starting path for: I want to research potential clients
-
RAGLight
AI repositoriesRAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.
Source for RAGLight (opens github.com) git clone https://github.com/Bessouat40/RAGLight.git -
better-vault
AI repositoriesOpen-source NotebookLM alternative. Chat with your sources with citations, and turn them into reports, flashcards, quizzes, mind maps and slide decks, with your own OpenAI, Anthropic or Gemini key or local Ollama / LM Studio models. Local-first, no account.
Source for better-vault (opens github.com) git clone https://github.com/better-vault/better-vault.git -
post-cortex
MCP serversPost-Cortex provides durable memory infrastructure with automatic knowledge graph construction, intelligent entity extraction, and semantic search powered by local transformer models.
Source for post-cortex (opens github.com) git clone https://github.com/julymetodiev/post-cortex.git -
open-census-mcp-server
MCP serversTurn any AI assistant into your personal Census data expert. Ask questions in plain English, get accurate demographic data with proper interpretation and context.
Source for open-census-mcp-server (opens github.com) git clone https://github.com/brockwebb/open-census-mcp-server.git -
NovelOS
Agents & frameworksMulti-agent AI framework that writes full-length novels with persistent story state, a deterministic continuity engine, and a five-role editorial pipeline.
Source for NovelOS (opens github.com) git clone https://github.com/mrigankad/NovelOS.git -
rote
SkillsCompile AI agent skills into cheap, fast, deterministic pipelines that run without an LLM in the loop
Source for rote (opens github.com) git clone https://github.com/trevhud/rote.git -
MCP_CREO_MechDog
MCP servers用 MCP 把 Creo 变成 AI 可直接建模的后端:一句话生成可编辑的原生特征树——草图、拉伸、旋转、孔、钣金、装配、工程图、放样、翼型。官方 Toolkit 驱动,每步保存重载回读验证。Windows,Creo 9/10/12。
Source for MCP_CREO_MechDog (opens github.com) git clone https://github.com/wudahua/MCP_CREO_MechDog.git -
llms.txt 檢查工具
MCP serversllms.txt 檢查工具:檢查網站的 llms.txt、robots 與 sitemap。台灣繁體中文 MCP 工具。
-
braxis-blueprint
Agents & frameworksThe $0 AI Empire Playbook — 180 scheduled jobs, 43 free LLM lanes, and the failure classes that almost killed it. Free tiers only.
Source for braxis-blueprint (opens github.com) git clone https://github.com/BraxisAI/braxis-blueprint.git -
smarty-gpt
PromptsA wrapper of LLMs that biases its behaviour using prompts and contexts in a transparent manner to the end-users
Source for smarty-gpt (opens github.com) git clone https://github.com/citiususc/smarty-gpt.git -
klavis
Tools & apps[DEPRECATED] Legacy Klavis AI MCP integrations. See klavis.ai for RL environments and training data.
Source for klavis (opens github.com) git clone https://github.com/Klavis-AI/klavis.git -
trvl
MCP serversTravel MCP server + CLI for AI assistants — flights, hotels, trains, cars, ferries, price alerts. No API keys, single Go binary. 1 smart MCP tool + 66 aliases (98.9% smaller tools/list). Works with Claude, Cursor, Windsurf, Codex.
Source for trvl (opens github.com) git clone https://github.com/MikkoParkkola/trvl.git -
a-fable-of-codexes
SkillsClaude Code skills that make Claude (Fable) the conductor of AI worker fleets: many parallel OpenAI Codex workers plus Opus design agents, organized into campaigns, waves, squads, and review gates.
Source for a-fable-of-codexes (opens github.com) git clone https://github.com/jvogan/a-fable-of-codexes.git -
youtube-transcript-skills
SkillsYouTube transcript Agent Skill for Claude Code, Cursor, Codex and OpenClaw: fetch YouTube video transcripts, search videos, browse channels and playlists.
Source for youtube-transcript-skills (opens github.com) git clone https://github.com/tubeagentkit/youtube-transcript-skills.git -
myPKA
Agents & frameworksAI-powered Personal Knowledge Assistance in a folder. Built on the ICOR methodology. Plain markdown. Any LLM. Yours forever.
Source for myPKA (opens github.com) git clone https://github.com/myICOR/myPKA.git -
llms.ink
MCP serversAny link as llms.txt; check llms.txt; see how AI crawlers read a page; draft AGENTS.md.
-
llm-orchestration-agent-2
MCP serversMCP-Native LLM Orchestration Agent
-
llm-orchestration-agent-2-df5979
MCP serversLLM Orchestration Agent 2
-
llm-orchestration-agent-d2feb0
MCP serversLangSmith-Traced LLM Orchestration Agent
-
solos
MCP serversSwap, lend, trade perps, add liquidity, move SOL, read the market. One binary your agent calls, across every venue.
Source for solos (opens github.com) git clone https://github.com/GuiBibeau/solos.git -
formanator
MCP serversSubmit Forma <https://joinforma.com> benefit claims from the command line and Model Context Protocol (MCP) clients, with support for AI-powered receipt analysis with an LLM or Jev
Source for formanator (opens github.com) git clone https://github.com/timrogers/formanator.git -
ebi-agent-chat-relay
Agents & frameworksOne cockpit for all your coding agents: a web console (plus Discord & Teams) to run Claude Code, Codex, local models, pi and AG-UI agents in parallel, with manager/worker delegation.
Source for ebi-agent-chat-relay (opens github.com) git clone https://github.com/ebibibi/ebi-agent-chat-relay.git -
aislop
Tools & appsCatch and fix the code-quality issues AI coding agents leave behind - dead code, unsafe casts, swallowed errors, duplication, security risks, and more. 50+ deterministic rules across 10 language targets, with CLI, CI, and GitHub Actions. No LLM at runtime. MIT.
Source for aislop (opens github.com) git clone https://github.com/scanaislop/aislop.git -
plasmate
MCP serversBrowser engine for agents. HTML in, structured Semantic Object Model out. Native MCP and AWP with a supported CDP subset. Apache-2.0.
Source for plasmate (opens github.com) git clone https://github.com/plasmate-labs/plasmate.git
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.