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
-
bothouse
Agents & frameworks把 Claude Code、Codex、Gemini 拉进一个群,组长 AI 分活,大家共用一份记忆。| Put Claude Code, Codex and Gemini CLI in one Discord group: a team-lead AI splits the work, and they share one memory.
git clone https://github.com/zuiho-kai/bothouse.git -
exact
Agents & frameworksWrite an app once. It runs natively on the web, macOS, iOS, and Linux, and an AI agent can build it, run it, see it, and test it on every one of them.
git clone https://github.com/expo/exact.git -
clawmetry
Agents & frameworksSee your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons.
git clone https://github.com/vivekchand/clawmetry.git -
scope-recall-hermes
Agents & frameworksLocal long-term memory for Hermes, Codex, Claude Code, WorkBuddy and dsh agents: one SQLite store, source-backed recall, and tools to inspect, correct or delete what is remembered.
git clone https://github.com/410979729/scope-recall-hermes.git -
subpool
Agents & frameworksA lightweight, self-hosted AI subscription pool for teams.
git clone https://github.com/gesta-run/subpool.git -
pydantic-ai-skills
Agents & frameworksThis package implements Agent Skills (https://agentskills.io) support with progressive disclosure for Pydantic AI. Supports filesystem and programmatic skills.
git clone https://github.com/DougTrajano/pydantic-ai-skills.git -
engraphis
Agents & frameworksLocal-first, inspectable memory for coding agents: durable context across sessions and repositories, code-aware recall, bi-temporal history, MCP, and a self-hosted WebUI.
git clone https://github.com/Coding-Dev-Tools/engraphis.git -
mcp_agent_mail
Agents & frameworksAsynchronous coordination layer for AI coding agents: identities, inboxes, searchable threads, and advisory file leases over FastMCP + Git + SQLite
git clone https://github.com/Dicklesworthstone/mcp_agent_mail.git -
agentopology
Agents & frameworksHarness as code — the Terraform for AI agents. Define your agent team AND its memory once, deploy to Claude Code, OpenClaw, Cursor, Codex, Gemini, Copilot, Kiro. Declarative .at language + agent-maintained, Obsidian-portable company brains + interactive visualizer.
git clone https://github.com/agentopology/agentopology.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 -
deer-flow
Agents & frameworksAn open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
git clone https://github.com/bytedance/deer-flow.git -
Heeler
Agents & frameworksNative iPhone and iPad console for herdr: watch and drive coding agents on your machines over SSH, in Herdr TUI or the Herdr desktop app (herdr-core), with a real libghostty terminal, native Chat, QR pairing, and push notifications when an agent needs you
git clone https://github.com/ZingerLittleBee/Heeler.git -
heimdall
Agents & frameworksA lightweight CPU only memory approach with ranked retrieval. Simple, yet effective.
git clone https://github.com/ArihantDeva/heimdall.git -
copilot-app-for-beginners
Agents & frameworksLearn how to get started using the GitHub Copilot app!
git clone https://github.com/github/copilot-app-for-beginners.git -
ai-dive-deep
Agents & frameworksVlad's Playbook — a 58-chapter operator field manual where every artifact is live, clickable, and forwardable. 32 interactive widgets, a self-updating AI radar, hand-verified model leaderboards, embedded case studies — and the repo runs the agent workflow the book teaches.
git clone https://github.com/Belkins/ai-dive-deep.git -
marveen
Agents & frameworksAI csapatod, ami fut amíg te alszol.
git clone https://github.com/Szotasz/marveen.git -
skillshare
Agents & frameworks📚 Sync skills, agents, MCP, plugins to all AI CLI tools with one command and simplify team sharing.
git clone https://github.com/runkids/skillshare.git -
self-hosted-ai-starter-kit
Agents & frameworksThe Self-hosted AI Starter Kit is an open-source template that quickly sets up a local AI environment. Curated by n8n, it provides essential tools for creating secure, self-hosted AI workflows.
git clone https://github.com/n8n-io/self-hosted-ai-starter-kit.git -
embodied-first-exam
Agents & frameworksThe first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.
git clone https://github.com/mll-lab-nu/embodied-first-exam.git -
ai-employees
Agents & frameworksOpen source AI Employees. 8 scheduled business roles, 60 routines, on Claude Code and 10 other harnesses. They drive your browser the way you do and improve every run. You own the files.
git clone https://github.com/markfulton/ai-employees.git -
CodeJury
Agents & frameworksTerminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull requests with deterministic QA and ensemble code review.
git clone https://github.com/krishagarwal314/CodeJury.git -
spec-harness
Agents & frameworks面向 AI 编程智能体的任务包工作流工具,用可验证的范围、证据和 Git 门禁管理长期改动。(Task-package workflow for AI coding agents with verifiable scope, evidence, and Git gates.)
git clone https://github.com/MicTx/spec-harness.git -
ClaudeCode-Workflow-Lab
Agents & frameworksComplete Guide 2026: Claude Code Manual – Workflow Pipelines & Adversarial Budget Loops
git clone https://github.com/Frisher1/ClaudeCode-Workflow-Lab.git -
destructive_command_guard
Agents & frameworksA fast Rust safety hook that blocks destructive shell, git, and filesystem commands before AI coding agents run them. 50+ security packs (databases, Kubernetes, Docker, cloud, Terraform), heredoc/inline-script scanning, CI scan mode, and explain mode; works with Claude Code, Codex, Gemini, Copilot, Cursor, and more.
git clone https://github.com/Dicklesworthstone/destructive_command_guard.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.