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
-
Grandet
Tools & appsFind the cheapest API for any model and connect it from your AI agent: Grandet Skill and an anonymous MCP server, backed by listed prices from 1,800+ official, inference and relay providers on grandet.ai.
git clone https://github.com/hanzohanzhe/Grandet.git -
repomind
Tools & appsAn open-source, AI-powered application using Agentic CAG to chat with any public GitHub repository or developer profile, offering deep code analysis, visual architecture maps and security audits
git clone https://github.com/403errors/repomind.git -
festival
Tools & appsVibe Engineering Framework, Organize your intent, loop your work and achieve the outcome you want from AI without wasting tokens
git clone https://github.com/Obedience-Corp/festival.git -
Kaimon.jl
Tools & appsMCP server giving AI agents full access to Julia's runtime via a live Gate — code execution, introspection, debugging, testing, and semantic search
git clone https://github.com/kahliburke/Kaimon.jl.git -
Yorishiro
Tools & appsA terminal that gives AI a body and a living space.
git clone https://github.com/sktkkoo/Yorishiro.git -
linggen-memory
Tools & appsLocal-first semantic memory for AI assistants — one store your preferences, decisions and gotchas follow you into, across Claude Code, Codex, Cursor and Zed.
git clone https://github.com/linggen/linggen-memory.git -
dafthunk
Tools & appsA workflow execution platform built on top of the fantastic Cloudflare infrastructure.
git clone https://github.com/dafthunk-com/dafthunk.git -
mcp
Tools & apps🤖 Taskade MCP · Official MCP server and OpenAPI to MCP codegen. Build AI agent tools from any OpenAPI API and connect to Claude, Cursor, and more.
git clone https://github.com/taskade/mcp.git -
ArcRift
Tools & appsPersistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats (Claude, ChatGPT, DeepSeek) straight to your local IDE agents (Cursor, Claude Code, Windsurf) powered by a local SQLite knowledge graph.
git clone https://github.com/Eshaan-Nair/ArcRift.git -
awesome-n8n-templates
Tools & apps🔥 The largest open-source collection of n8n workflow templates — 8,697+ ready-to-import workflows across 25 categories, 236 integrations, and 11 use cases.
git clone https://github.com/ScraperNode/awesome-n8n-templates.git -
hermes-ide
Tools & appsOne console for every coding agent. Claude Code, Codex, Copilot, OpenCode and any CLI run in their own terminal, each task on its own branch, with one inbox for agents waiting on you. Free desktop app for macOS, Windows and Linux.
git clone https://github.com/hermes-hq/hermes-ide.git -
workflowbuilder
Tools & appsWorkflow orchestration framework for your product, open source: a white-label React workflow builder, durable execution on your own Temporal, human approval steps for AI agents, and a live view of every run.
git clone https://github.com/synergycodes/workflowbuilder.git -
kent
Tools & appsAgentic Coding platform for Professional SWE work focusing on output quality. Self-review, supervision, dynamic workflows, dynamic agent loops.
git clone https://github.com/respawn-llc/kent.git -
cognicore-env
Tools & appsPersistent memory, reflection & safety for AI agents. No vector DB, no embedding server — BM25 + multi-hop retrieval runs in-process. MCP server with 10 tools. Apache 2.0.
git clone https://github.com/cognicore-dev/cognicore-env.git -
termdock-issues
Tools & appsTermdock is an AI terminal for macOS and Windows. Run Claude Code, Codex, Antigravity CLI (agy), OpenCode and GitLab Duo side by side; connect computers, review Git changes and access terminals by phone.
git clone https://github.com/termdock/termdock-issues.git -
claude-overlay
Tools & appsA floating, screen-aware Claude Code chat for Windows - it reads your screen to answer, and runs on your own Claude (And Codex btw) subscription (no API key).
git clone https://github.com/shengyanlin/claude-overlay.git -
canvas-pilot
Tools & appsLocal-first Canvas LMS AI agent that learns each course's recurring assignment workflow and reuses it through scan -> approval -> execute with student review.
git clone https://github.com/X-isdoingreat/canvas-pilot.git -
NodePilot
Tools & appsAgentless Windows workflow orchestration. Self-hosted, open source, alternative to System Center Orchestrator with SCOrch workflow import.
git clone https://github.com/Sev7eNup/NodePilot.git -
Claude-Code-Workflow
Tools & appsJSON-driven multi-agent cadence-team development framework with intelligent CLI orchestration (Gemini/Qwen/Codex), context-first architecture, and automated workflow execution
git clone https://github.com/catlog22/Claude-Code-Workflow.git -
LoomFlow
Tools & appsLightweight AI-native workflow builder for individuals and small teams — describe your idea in natural language, get a runnable workflow on a visual canvas, publish it as an API. One-command Docker self-hosting. Open-source alternative to Dify / n8n.
git clone https://github.com/banmu123/LoomFlow.git -
claude-vibe-squad
Tools & appsMarkdown-first orchestration for 71 specialists across Codex, Claude, Gemini, and Grok. Chrono coordinates scoped tasks in isolated git worktrees, with tests, cross-family review when triggered, and private Markdown memory. Runs locally in tmux.
git clone https://github.com/mtarcure/claude-vibe-squad.git -
goskill
Tools & apps长任务执行 Skill:先定成功标准再逐轮验收,让 Claude Code/Codex 跑完长任务不半途而废|Goal-driven long-running agent tasks
git clone https://github.com/AIPMAndy/goskill.git -
ai-research-os-workshop
Tools & appsHow to turn your Second Brain into a living research memory that your agents maintain. Workshop with slides, video and code.
git clone https://github.com/iusztinpaul/ai-research-os-workshop.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
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.