Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
coding-agent-from-scratch
Agents & frameworksBuild an AI Coding Agent from Scratch in Pure Python, Step by Step | 用纯 Python 从零搭建 AI 编程 Agent,边实现边理解其工作原理
git clone https://github.com/liiiiiiiiil/coding-agent-from-scratch.git -
preflight
MCP serversNew Relic MCP server for observing AI coding assistants (Claude Code, Cursor, Copilot, etc.)
@newrelic/preflight@1.73.0 -
Archimedes
SkillsA local-first research agent workspace for customizable research apps and integrated, traceable scientific workflows.
git clone https://github.com/Johanson-colab/Archimedes.git -
gamebot
Datasets & benchmarks[ACL 2025] GAMEBoT: Transparent Assessment of LLM Reasoning in Games
git clone https://github.com/Visual-AI/gamebot.git -
Quarterdeck
MCP serversA persistent captain's mate for Claude Code: give it goals like "keep my inbox under control" and it works on them in the background on a schedule, asks you to approve actions from a pane beside your chat or your phone, and remembers your decisions. Claude Code plugins + MCP server, local SQLite.
git clone https://github.com/shannonbay/Quarterdeck.git -
opencode-mcp
Tools & appsMCP server for OpenCode AI — 70 tools, 10 resources, 5 prompts. Use npx opencode-mcp with Claude Desktop, Claude Code, Cursor, Windsurf, or any MCP client.
git clone https://github.com/AlaeddineMessadi/opencode-mcp.git -
deepdive
PromptsDeepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, claims-ledger triangulation with dissent protection, relevance × authority evidence filter, multi-angle red team, four-layer citation verification. 105 blocks, 29 channels, 460+ stat sources, 47 APIs, 1072 verified endpoints.
git clone https://github.com/Socialpranker/deepdive.git -
hermes-talk
Agents & frameworksHermes Talk: realtime duplex voice for Hermes Agent. Rides your ChatGPT or X Premium subscription, no API key needed. OpenAI, Grok, Gemini. Terminal, Discord, dashboard.
git clone https://github.com/TheSmokeDev/hermes-talk.git -
Assured Workloads API
Public APIsOpenAPI description for googleapis.com:assuredworkloads.
-
Associated Press
Public APIsSearch for news and metadata from Associated Press
-
Assistant Mail MCP
MCP serversAgent email with allowlist and consent via AssistantMail.
@assistantmail/assistantmail-mcp@1.3.1 -
liliumai
Agents & frameworksLilium AI: The ultimate personal AI agent framework for autonomous computer control. Featuring browser automation, shell execution, and multi-channel integration (WeChat/Telegram/Discord).
git clone https://github.com/beidald/liliumai.git -
Assura
MCP serversCheck Assura contracts with Z3. Returns Verified, Counterexample, or Unknown.
assura@0.8.1 -
promptscript
PromptsPrompt-as-Code for Enterprise AI. Standardize, audit, and deploy instructions across any AI coding assistant.
git clone https://github.com/mrwogu/promptscript.git -
awesome-llm-role-playing-with-persona
Docs & tutorialsAwesome-llm-role-playing-with-persona: a curated list of resources for large language models for role-playing with assigned personas
git clone https://github.com/Neph0s/awesome-llm-role-playing-with-persona.git -
opencues
Tools & appsThe open standard for omnipresent AI. Claude Code, OpenCode, Gemini CLI, Shell, Chrome, DeepSeek Harness. Model-agnostic
git clone https://github.com/opencues/opencues.git -
nerve
Agents & frameworksSelf-hosted AI agent runtime — personal assistants, autonomous workers, and everything in between. Built on the Claude Agent SDK.
git clone https://github.com/ClickHouse/nerve.git -
tfmcp
MCP servers🌍 Terraform Model Context Protocol (MCP) Tool - An experimental CLI tool that enables AI assistants to manage and operate Terraform environments. Supports reading Terraform configurations, analyzing plans, applying configurations, and managing state with Claude Desktop integration. ⚡️
git clone https://github.com/nwiizo/tfmcp.git -
rsc-harness
PromptsYour agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives it both, plus the trade to know the job and the reflexes to not break your repo. For Claude Code, Codex and 15 more.
git clone https://github.com/ericrisco/rsc-harness.git -
LoopForge
Agents & frameworksSelf-hosted workflows for coding-agent delivery. Orchestrate CodeBuddy, Codex and Claude Code with scripts and human approval gates. Includes Local workflows for coding assistants.
git clone https://github.com/Tencent/LoopForge.git -
Motifcode
SkillsA coding agent harness built specifically for Motif-3
git clone https://github.com/TaewoooPark/Motifcode.git -
agents
Agents & frameworksCreate AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.
git clone https://github.com/inkeep/agents.git -
verbatim-rag
AI repositoriesProvenance-first extractive RAG: return verbatim source spans with citations using local ModernBERT or optional LLM-assisted extraction.
git clone https://github.com/KRLabsOrg/verbatim-rag.git -
omk
Agents & frameworksOpen-source multi-agent coding CLI for the terminal (TypeScript, MIT). Switch models mid-session; finish goals only when your test passes.
git clone https://github.com/dmae97/omk.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.