Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
homeshed-mcp
MCP serversEvery tool your AI needs, in one install: a self-hosted MCP server with memory, reasoning, git, Docker, network and release tools.
git clone https://github.com/keefng8/homeshed-mcp.git -
exoproc
MCP serversTypeScript toolkit for Windows x64 native systems programming, memory manipulation, and process instrumentation.
git clone https://github.com/w0ldan/exoproc.git -
doceo
SkillsClaude Code skill that teaches you anything in one screen: visual lessons with memory and a feedback loop
git clone https://github.com/eugeniughelbur/doceo.git -
메모짱
MCP servers메모짱 메모·할 일을 AI로 검색·정리·체크해요. / Search, write and check off notes and to-dos in Memozzang.
-
P-ai
Agents & frameworksA ready-to-use self-growing desktop AI assistant for long-running tasks, memory, agents, tool reviews, MCP, and high-concurrency workspace automation. / 开箱即用的自我成长型桌面 AI 助理,面向长期任务、记忆、部门协作、工具审查、MCP 与高并发工作区自动化。
git clone https://github.com/kawayiYokami/P-ai.git -
duck-e
Tools & appsVoice rubber-duck debugging assistant: a FastAPI backend bridges the browser (WebRTC) to the OpenAI Realtime API, with server-side tools for web search, URL fetch, weather, and per-user memory.
git clone https://github.com/jedarden/duck-e.git -
open-bridge
SkillsStop re-explaining your work to your coding agent. Plain markdown and YAML in git, read at session start by Claude Code, Codex and Copilot CLI. MIT.
git clone https://github.com/bks-lab/open-bridge.git -
sessions
MCP serversSearch and memory across your AI coding sessions — one index over Claude Code, Codex, and Pi. Fuzzy-find and resume from the CLI, give agents recall via MCP, and get usage reports.
git clone https://github.com/nicknisi/sessions.git -
metaharness
Agents & frameworks🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).
git clone https://github.com/ruvnet/metaharness.git -
vir
SkillsKarpathy's LLM Wiki, built from your Claude Code sessions: a folder of markdown you own, Obsidian-native when you want it. Keeps what you decided, learns rules from what you repeat, readable by any agent.
git clone https://github.com/djolex999/vir.git -
LLM_trader
Agents & frameworksAn LLM trading agent that shows its work: the chart, the prompt, the memory it retrieved, and every loss. Paper trading, public ledger.
git clone https://github.com/qrak/LLM_trader.git -
trinity-claw
SkillsA self-hosted AI agent that thinks, acts, and improves itself – all running privately on your own machine. Browses the web, writes and executes code, manages files, sends emails, monitors URLs, builds websites, and learns from every interaction.
git clone https://github.com/TrinityClaw/trinity-claw.git -
vibecode-pro-max-kit
PromptsYour AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 15 agents, 33 skills working with /goal, agent-team, & workflow on autopilot loops with 0 need for human gate. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack
git clone https://github.com/withkynam/vibecode-pro-max-kit.git -
agent-collab-skills
SkillsClaude Code marketplace for multi-agent collaboration — task splitter, output reconciler, adversarial debate, shared memory, acceptance gate. Composes with codex-delegate / gemini-delegate.
git clone https://github.com/WenyuChiou/agent-collab-skills.git -
cortex-tms
Tools & appsThe Universal AI-Optimized Project Boilerplate. A Tiered Memory System (TMS) designed to maximize AI agent performance. Includes an interactive CLI tool and a high-signal documentation standard.
git clone https://github.com/cortex-tms/cortex-tms.git -
SmartMemory
MCP serversNeuro-symbolic memory for LLMs (POC)
-
OhMyBuddy
Agents & frameworksSelf-hosted, self-improving AI buddy with visible memory: personal AI agent + Pi coding-agent workspace for any browser, phone. 自托管私人 AI 助理:记得你,能办事,自进化,可接入微信。
git clone https://github.com/YogurtJ/OhMyBuddy.git -
--- name: kubernetes-resource-requests-rightsizer description: Rightsizes Kubernetes CPU and memory requests and limits from real usage (p50, p95 and max per container). Recommends requests at p95 plus headroom, memory…
-
SlashForge
SkillsWorkflow slash commands for AI coding agents. Spec-driven. Guardrails, not autocomplete.
git clone https://github.com/rajdeepratan/SlashForge.git -
hermes-bot-forge
Agents & frameworksHermes Agent plugin: say 'make me a <role>' and your agent builds a complete, working Bot — name, face, SOUL.md, memory, tools, skills, routines, gateway.
git clone https://github.com/BkashJEE/hermes-bot-forge.git -
mulmoclaude
Agents & frameworksNurture your own AI assistant on your own computer. Local-first and MIT: memories, data and apps stay as plain files in your workspace. Chat summons the right GUI — wiki, spreadsheet, chart, form, 3D. Build small apps for an audience of one, no programming required.
git clone https://github.com/receptron/mulmoclaude.git -
token-optimizer-mcp
MCP servers91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.
git clone https://github.com/ooples/token-optimizer-mcp.git -
rundesk-cli
SkillsPersistent proactive self-improving AI teammates with memory, skills, and schedules.
git clone https://github.com/rundesk-ai/rundesk-cli.git -
brain0
Tools & appsThe black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of what agents read, evidence-driven risk, MCP memory for coding agents, signed provenance attestations. One command, offline by default.
git clone https://github.com/Brain0-ai/brain0.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.