Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Woodstitch
MCP serversPaid human listeners judge TTS audio blind: pairwise preference or human-vs-AI detection.
woodstitch-mcp@0.1.5 -
SHOULD use clear, simple language. SHOULD be spartan and informative. SHOULD use short, impactful sentences. SHOULD use active voice; avoid passive voice. SHOULD focus on practical, actionable insights. SHOULD use…
-
dsh-evolve-modes
Prompts让 Agent 的工作方式可组合、可审查、可持续改进,最终实现 Agent Self Evoling。 DeepSeek Harness Web plugin with composable task controls and isolated, human-reviewed self-evolution.
git clone https://github.com/GraySilver/dsh-evolve-modes.git -
grasp
Tools & appsGrasp helps you manage multiple projects and parallel coding agents in one visual workflow, so humans can understand faster and ship more.
git clone https://github.com/cocofhu/grasp.git -
linkedin-skills
PromptsClaude skills for LinkedIn. 12 Claude Code and Codex skills that write human-sounding LinkedIn posts, craft comments that get noticed, analyze your feed, and build a publishing cadence, all from your terminal. Content engineering by Creative Content Crafts. MIT.
git clone https://github.com/sergebulaev/linkedin-skills.git -
agentic-brownfield-coding
SkillsClaude Code scaffolding and first steps for complex brownfield projects
git clone https://github.com/ralfstrobel/agentic-brownfield-coding.git -
ru-marketplace-mcp
MCP serversRead-only MCP servers for Russian marketplaces: prices, stock, ratings, reviews, seller identity
ghcr.io/vladimir-human/ru-marketplace-mcp:2.9.4 -
domain-experts
Skillsall human experts into AI agents
git clone https://github.com/wonsukchoi/domain-experts.git -
kanzo
MCP serversSelf-hosted, sharable kanban for humans and agents. One 4.7 MB binary, 5 MB of RAM, 10 to 60 tokens per agent reply, starts in 3 ms, zero setup.
git clone https://github.com/emanuele-em/kanzo.git -
turbo
SkillsA human-gated agentic software factory for Claude Code and Codex: you decide what to build and judge the result; skills shape, build, polish, ship, and learn.
git clone https://github.com/tobihagemann/turbo.git -
Mnemosyne OS
MCP serversMemory the human governs, on their own machine, plus what other coding agents here wrote.
@mnemosyne_os/mcp@2.4.0 -
2o
MCP serversHuman intelligence API — AI agents verify facts with human domain experts via MCP
@russellshen1992/2o-mcp@1.0.0 -
Taskin
MCP serversHuman capability for AI agents - real-world action and human judgment.
-
raft
AI repositoriesRAFT, or Retrieval-Augmented Fine-Tuning, is a method comprising of a fine-tuning and a RAG-based retrieval phase. It is particularly suited for the creation of agents that realistically emulate a specific human target.
git clone https://github.com/lumpenspace/raft.git -
overtime
Agents & frameworksGive a coding agent a brief, not a chat, and it works on its own across sessions. Includes an example run: an open-world city built in a real game engine with no human help. In early development.
git clone https://github.com/ukanwat/overtime.git -
dsh-agent-team
Agents & frameworksdsh-agent-team: Agent Teams for DeepSeek Harness. Hand work to a team of agents that carries it end to end while you set the direction and hold the gates. You stay on the loop, and step back in whenever you want.
git clone https://github.com/Contexera/dsh-agent-team.git -
GetABrain
MCP serversReal human judgment as agent tools — ask a question, get a structured human answer back.
@getabrain/mcp-server@0.2.1 -
MeatSpace
MCP serversHuman-in-the-loop for AI agents. Submit choices, get a human decision.
-
switchboard
MCP serversA phonebook of humans for AI agents. Agents discover and contact willing humans.
-
opengeni
Agents & frameworksOpen, self-hostable agentic service for organizations — durable, replayable agent sessions, human approvals, governed credentials and memory, running in managed sandboxes or on your own hardware. Apache-2.0.
git clone https://github.com/Cloudgeni-ai/opengeni.git -
synthadoc
SkillsSynthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.
git clone https://github.com/axoviq-ai/synthadoc.git -
taskuary
Tools & appsYour AI work partner. Mail, chats and tickets become one list in the right order; your agents do the work, and nothing goes out until you approve. Free, open source, runs on your computer.
git clone https://github.com/ldbumble/taskuary.git -
textbook-writer-skills
SkillsUbD 逆向设计驱动的教材写作 skill 组合,一键装进 Claude Code / Codex / WorkBuddy:教学定位 → 五件套 gate → 章节树 gate → 四段式逐章写作 → 审核定稿。学科无关内核 + 可插拔学科档案,理科真算复核、人文社科逐字核对引文出处,验证不了就标注「需作者确认」;关键决策作者拍板,中断随时续写
git clone https://github.com/cabbage2000-lab/textbook-writer-skills.git -
mathmodel-studio
SkillsA local-first desktop agent for mathematical modeling contests: human-in-the-loop model selection, explanations, quality gates and scoring, plus figures, LaTeX/Word papers and de-AI checks. Electron + Python, bring your own model.
git clone https://github.com/Escap1ng/mathmodel-studio.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.