Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
Meta_Kim
Agents & frameworksGoverned execution layer for AI coding assistants: clarify intent, route capabilities, review evidence, verify results, and write back lessons across Claude Code, Codex, OpenClaw, and Cursor.
git clone https://github.com/KimYx0207/Meta_Kim.git -
Delimit — Keep the state. Change the model.
MCP serversKeep the state. Change the model. Shared context and a multi-model panel across coding assistants.
delimit-cli@4.24.0 -
Xenon
Agents & frameworksVerifiable AI coding agent harness / 可验证的 AI 编码代理:evidence hash-chain · hollow-answer gate · manual verification checklist · 6 engines + MCP · multi-model · Windows/CJK · listed in awesome-opensource-ai & Collabnix awesome-mcp-lists
git clone https://github.com/xianyu-sheng/Xenon.git -
mcp-server-tree-sitter
MCP serversMCP Server for Tree-sitter
git clone https://github.com/wrale/mcp-server-tree-sitter.git -
agent-skills
SkillsA collection of Agent Skills for AI coding assistants (Claude, Cursor, Copilot). Following agentskills.io specification.
git clone https://github.com/rlespinasse/agent-skills.git -
willdeep-cli
Agents & frameworks自托管 AI Coding Agent(Rust):常驻 Runtime 撑起终端 / 浏览器 / 手机三端;每行改动可追溯到具体 Agent 与工具调用,子 Agent 的活由退出码裁决,检查点回退、目标 token 预算与验收清单跨轮次跨重启累计,用量与反馈账本留在本地。接任意 OpenAI 兼容或 Anthropic 端点。Self-hosted auditable AI coding agent: per-line attribution, exit-code-verified sub-agents, restart-safe goal budgets, local usage and feedback ledgers.
git clone https://github.com/niuwoai/willdeep-cli.git -
SWE-ATLAS turns Claude Code into a senior AI software engineer agent: multi-project workspaces with memory, wireframe & prototype first planning, secrets kept out of chat, psql, browser QA runners, and CI/CD-aware deploys. One command: npx swe-atlas new-project
git clone https://github.com/syahiidkamil/Software-Engineer-AI-Agent-Atlas.git -
GYO-AGENTS
MCP serversMCP server + prompt that turns any AI coding agent (Cursor, Claude Code, Cline, Kiro, Windsurf…) into your Digital Twin — generate a project-specific AGENTS.md and give every tool a shared, persistent memory of how you build.
git clone https://github.com/youssef-jad/GYO-AGENTS.git -
buddy
Tools & appsA virtual pet companion for your AI — Designed to provide in-context code review feedback with personality. Grow with your buddy and level up together. Works with Claude Code, Codex, CursorCLI, Github CopilotCLI, OpenClaw, and any MCP compatible clients
git clone https://github.com/fiorastudio/buddy.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 -
agentic-os
PromptsGovernance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.
git clone https://github.com/KbWen/agentic-os.git -
workspace-architect
SkillsWorkspace Architect is a zero-friction CLI tool that provides curated collections of specialized agents, instructions, and prompts to supercharge your GitHub Copilot experience.
git clone https://github.com/archubbuck/workspace-architect.git -
Artificial-Intelligence-Universe
MCP serversCurated directory of AI tools, agents, LLMs, MCP servers, and learning resources for developers, researchers, and builders.
git clone https://github.com/frangelbarrera/Artificial-Intelligence-Universe.git -
claude_code_vs
Tools & appsBring Claude Code to Visual Studio 2026: A native diff with accept/reject, a live debugger Claude can drive autonomously, Roslyn code navigation, and Test Explorer integration. The IDE half of Claude Code's integration protocol. Community-built, unofficial.
git clone https://github.com/firish/claude_code_vs.git -
Agent-Skills
SkillsCurated Agent Skills for Microsoft & Azure – giving AI coding assistants structured, real-time expertise from Microsoft Learn docs.
git clone https://github.com/MicrosoftDocs/Agent-Skills.git -
qwen38-strix-halo-harness
Datasets & benchmarksAI coding agent harness for any hardware, local or cloud (OpenAI-compatible engines). Tuned for AMD Strix Halo: Qwen3.8 125B on the iGPU, NPU side-jobs, crash recovery, logged benchmarks.
git clone https://github.com/aic0d3r/qwen38-strix-halo-harness.git -
memorykit
MCP serversCognitive memory for AI coding assistants — persistent memory across sessions
memorykit-mcp-server@1.4.2 -
beagle
SkillsAgent Skills marketplace: framework-aware skills for code review, documentation, test-plan generation, AI-writing detection, architectural analysis, and git workflows — for Python, Go, Rust, Elixir, React, Remix, and iOS/Swift. Works with Claude Code, Codex, and any agent that supports Agent Skills.
git clone https://github.com/existential-birds/beagle.git -
agent-skills
SkillsPractical Agent Skills for AI coding assistants: installable engineering standards and a curated index of third-party skills.
git clone https://github.com/Miaoge-Ge/agent-skills.git -
SlashForge
SkillsWorkflow slash commands for AI coding agents. Spec-driven. Guardrails, not autocomplete.
git clone https://github.com/rajdeepratan/SlashForge.git -
AI-Rig
SkillsA collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.
git clone https://github.com/Borda/AI-Rig.git -
mason
MCP serversEngineering decisions, change impact, documentation audits, and CI evidence for coding assistants.
mason-context@0.24.0 -
AIContextBuilder
MCP serversSymbol-aware C# and .NET code context for AI coding assistants.
AIContextBuilder@0.5.464.66 -
MCPSense
MCP serversInspect MCP configurations, tool metadata, and changes from your coding assistant.
mcpsense@0.5.1
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.