Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
radiant
Tools & appsA local coding harness for Mac. Chat with coding agents across cloud and local models, watch every tool call in a live activity feed, and drive a real terminal — in one window. Free and MIT licensed.
git clone https://github.com/templetongroup/radiant.git -
codexclaw
Agents & frameworksDevelopment discipline + multi-model subagents for OpenAI Codex — 13 dev skills, PABCD workflow, repo map, recall, skill search. Single plugin, no external harness.
git clone https://github.com/lidge-jun/codexclaw.git -
skill
SkillsOfficial Riffkit skill — change the outfit, place, product or person in your video, or riff a winning short video, from ChatGPT, Claude, Claude Code, Codex, Cursor or the browser.
git clone https://github.com/riffkit/skill.git -
agent-afk
MCP serversThe coding agent you don’t have to watch. Start a task and walk away. AFK builds the feature, verifies its own work, and texts you when it’s done. You come back to a receipt of every step, every decision, and what’s waiting on you. If it’s unsure, it stops and asks instead of guessing.
git clone https://github.com/griffinwork40/agent-afk.git -
ai-agent-engineer-handbook
PromptsAI Agent / LLM 应用工程师面试与学习手册 | 中文 / English
git clone https://github.com/harrisliangsu/ai-agent-engineer-handbook.git -
FABULA-LLM-5
Agents & frameworksA local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every green run leaves a receipt anyone can replay. Built for one small model on one machine (LM Studio, MLX) or any OpenAI-compatible endpoint. No telemetry. macOS · Linux · Windows.
git clone https://github.com/sergezuber/FABULA-LLM-5.git -
picocalc-mcp
MCP serversAI assistant access to PicoCalc MicroPython hardware over USB.
picocalc-mcp@0.1.1 -
scope-guard
MCP serversHard scope boundaries to prevent AI agent drift
scope-guard-mcp@0.1.3 -
pptwise
SkillsA real PowerPoint, not HTML. Tell your AI what to cover and pptwise builds an editable deck on your own machine. Agent skill + DSH plugin, no account and no API key to render. | 真正的 PPT,不是 HTML。跟 AI 说要讲什么,pptwise 在你自己电脑上做出一份能改的 PPT。Agent skill + DSH 插件,不用注册,渲染不用 API key。
git clone https://github.com/liustack/pptwise.git -
mcp-audit-tool
MCP servers🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready.
git clone https://github.com/graygnatconsole/mcp-audit-tool.git -
SKUit BOM Builder
MCP serversNetwork hardware BOMs, built inside your AI assistant
-
notebooklm-mcp-secure
MCP serversSecurity-hardened NotebookLM MCP with post-quantum encryption
@pan-sec/notebooklm-mcp@2026.5.0 -
Subagent MCP
MCP serversLet Codex orchestrate external coding agents through their native harnesses.
subagent-harness-mcp@1.0.31 -
file-organizer
MCP serversSecurity-hardened file organizer with smart categorization and duplicate detection
-
atomadic-fuse
MCP serversAtomadic Fuse MCP — polyglot compiler, harvest logic atoms, discover product chains.
atomadic-fuse@0.1.1 -
reashield
MCP serversDefensive hardening against automated reverse engineering - the defensive mirror of REA.
reashield@0.7.3 -
lsdsk
SkillsGroups disks by the controller they hang off, grades every link against what both ends could do, reads SMART wear and error counters, and reports what is worth acting on. Linux and Windows, no subprocesses, no network.
git clone https://github.com/bitranox/lsdsk.git -
rigorkit
SkillsTool-neutral skills and workflows for rigorous AI-assisted development.
git clone https://github.com/harrypotter48/rigorkit.git -
merrymen
MCP serversAutonomous trading agents for Robinhood Chain, inside hard on-chain limits. Use it from Claude: tell Claude "set up merrymen mcp", or add it in one click at merrymen.dev/claude
git clone https://github.com/millw14/merrymen.git -
Awesome-LLM-Ensemble
Agents & frameworksA curated list of Awesome-LLM-Ensemble papers for the survey "Harnessing Multiple Large Language Models: A Survey on LLM Ensemble" (IJCAI Survey 2026)
git clone https://github.com/junchenzhi/Awesome-LLM-Ensemble.git -
SigVest
MCP serversPortfolio-aware finance tools: drift, risk, earnings, benchmarks, news, tax harvesting
-
Agent Reliability
MCP serversTesting, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
-
physbound
MCP serversPhysical Layer Linter: validates RF and radar calculations against hard physical limits.
physbound@0.3.0 -
audio-analyzer
MCP serversGives LLMs ears. Spectral, harmonic, rhythm, stereo, and structural audio analysis.
https://github.com/JuzzyDee/audio-analyzer-rs/releases/download/v1.0.0/audio-analyzer-darwin-arm64.mcpb
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.