

Claude Code Game Studios
Turns one Claude Code session into a game studio with 49 agents and 74 skills
Every tool I tagged Open source, newest first. 94 so far.


Turns one Claude Code session into a game studio with 49 agents and 74 skills


Cloudflare's Astro docs tool that publishes HTML for people and Markdown for agents
A tiny JSON spec and renderer for animated, interactive agent avatars


Let your agent manage private email aliases and encrypted file drops over OAuth MCP


Open source multiplayer design canvas where humans and AI agents design together over MCP


GitHub's open source toolkit for spec driven development with coding agents


Open source control panel for the coding agents on your machine, with desktop and mobile apps


Git worktree CLI built for running several coding agents in parallel

Token efficient database MCP server for Postgres, MySQL, SQL Server, Oracle and SQLite


Mac network monitor that logs and blocks what your coding agents connect to, with an MCP server

Open source agentic video production system that runs inside your coding agent

Open source control plane for running a team of AI agents like a company


Open source video editing API and MCP server that builds CapCut and Jianying drafts


Open source, agent native learning workspace for personalized tutoring, quizzes, research and practice


Open source web data API for agents: search, scrape, crawl and interact, with an official MCP server


Computer use for any coding agent on macOS, Windows and Linux


LangChain's open source agent harness with planning, sub-agents, a filesystem and skills built in


Open-source local firewall that checks what your coding agent is about to do and blocks the dangerous stuff


Headless browser built from scratch for AI agents and automation, with a native MCP server


Local-first memory for AI agents that keeps conversations verbatim and searches them, with an MCP server

Free open source tester that checks any MCP server the way Claude or Cursor would use it


Open source long-term memory for agents that learns from past sessions, with a built-in MCP server


Open source desktop app for running a team of AI bots on the Claude, Codex or Grok CLI you already have


Open source context database that keeps an agent's knowledge, memory and skills in one filesystem


Open source Kubernetes UI with a built-in MCP server so your agent sees the whole cluster, not raw YAML


Free open source video editor your agent can drive over MCP


Social media scheduler your agent can post through, 30+ channels


Autonomous AI pentester that only reports bugs it can exploit


Home Assistant MCP server with 87 tools for devices and automations


Record a task once and turn it into a SKILL.md your agent can repeat

JetBrains' open source agentic IDE built around the pi coding agent


Terminal multiplexer built for running many coding agents


Jira and Confluence MCP server for Cloud and Data Center


OS level sandbox for agents and MCP servers, no container needed

Open source desktop agent that runs Claude Code and Codex harnesses on your own machine


Open source Arc alternative with an MCP server so Claude Code can drive your tabs


Open source Semrush and Ahrefs alternative with a native MCP server and agent skills

An Obsidian MCP server with permissions, audit logs and memory inside your vault


Dashboards as YAML around SQL: easy for agents to write, easy for humans to review in a diff


Open-source, self-hostable platform for running agents through one API, on any model and any machine


Chromium fork for AI agents: built-in MCP server, and each agent gets its own logins and tab group


Lets your coding agent tap, type, swipe and screenshot its way through the iOS Simulator


Open source vector design tool your coding agent can draw in through MCP


Self-hosted email client with an AI agent, running on your own Cloudflare account

Open-source office suite your coding agent can drive through a CLI, skill or MCP


Let your agent search LinkedIn, Indeed, Glassdoor and more job boards at once


Show your coding agent a bug instead of describing it: record, draw, talk, send


Open-source AI pentesting agents that prove each bug with a working exploit

Make slide decks by commenting under each slide while Claude Code or Codex does the edits

Shrinks tool outputs, logs and files before your coding agent sends them to the model


Encrypted knowledge store your agents can read with scoped, expiring grants


Let Grok Bot hand coding work to the Claude Code and Codex CLIs on your own machine

Command-line MCP client that gives any shell-enabled agent the full protocol through one Bash tool


Turns any coding agent into a video maker, with a real editor to change what it makes


Self-hosted sandboxes that run agent code in isolated Firecracker microVMs


Replay your coding agent sessions as a map and a timeline


Point your coding agent at a single-player game and play it in co-op with friends


Code graph and project memory for coding agents in one local Rust program


Turns a codebase and its docs into a knowledge graph your coding agent can query


Self-hosted LLM gateway with virtual keys, budgets and usage tracking

Minimal, extensible coding agent harness you shape to your own workflow


Let Grok Bot, Claude Code, Codex and your teammates' agents message each other


Python scraping framework with a stealth browser and an MCP server for agents


Open-source parametric 3D CAD that AI agents can drive through MCP

A Git hook that quizzes you on your agent's code before it ships


Read-only MCP server that lets your agent search your own WhatsApp, on Cloudflare


Let your coding agent test its changes in the real mobile app


Claude Code framework that runs your job search on your machine


One shared memory for every coding agent you switch between


Turn plain-English instructions into Android phone automation


Issue tracker and memory built for coding agents


Lets coding agents hear, judge and make sound


Local persistent memory for any coding agent, in one binary


Open-source Git server built for many coding agents landing changes at once


Run Python your agent writes without spinning up a container


Agree on a spec with your coding agent before it writes code


Desktop workspace for running several coding agents side by side

Open-source browser agent that finishes a web task you describe in plain words

Fully local ElevenLabs alternative with an MCP server for agents

Local search engine so coding agents stop reading files one by one

TS framework: one action powers UI, agent, HTTP, CLI, MCP


Turn any software into a CLI your agent can drive


Open-source, self-hosted agent with memory and skills

Open standard for generative UI


Open-source desktop app where a commander agent runs a team of AI specialists

Reverse engineering toolkit for your coding agent


Open-source project workspace for teams and AI agents

Human approval layer for consequential agent actions


Browser agents and cloud browsers for AI

Long-term memory layer for AI agents


Open-source tracing and evals for agents


Open-source coding agent, any model


TypeScript framework for AI agents

Open-source automation with agents and MCP
Loading…
Search didn’t load. Close it and try again.
Nothing by that name. Submit it
Free. I review every submission.
is in the review queue. I'll install it, test it and list it if it passes.