Best Open Source Tools of May 2026
67 Open Source Tools launched on Product Hunt in May 2026. These are the 25 most upvoted, from Kilo Code for VS Code with 878 upvotes down to ShioriCode with 118.
Together they took 6,264 upvotes (75% of the month's Open Source total). 22 finished in their day's top ten, and Kilo Code for VS Code and Ghost were #1 on the day.
- Open Source launches
- 67Open Source launches
- upvotes
- 8,336upvotes
- day top-ten finishes
- 22day top-ten finishes
- makers on this list
- 20makers on this list
The top 25

1. Kilo Code for VS Code
878 upvotesParallel agents, diff reviewer, and multi-model comparisons
We've completely rebuilt Kilo Code for VS Code, built on OpenCode server. New portable core, parallel tool calls, subagent delegation, inline code review, multi-model comparisons. Get started: kilo.ai/install

2. Radar
395 upvotesThe missing open-source Kubernetes UI
Radar brings your Kubernetes workflows into one fast, open-source UI: real-time topology, resources, events, Helm, GitOps, live traffic flows, security & best-practice checks, image filesystem inspection, and MCP for AI agents. Run it…
#3 on May 3, 20261 maker
3. Zed 1.0
365 upvotesHigh-performance, open source, multiplayer code editor
Fast — Written from scratch in Rust to efficiently leverage multiple CPU cores and your GPU. • Agentic — Run agents in parallel to smoothly edit files, navigate code, and run tools at native speed. • Collaborative — Chat with teammates…

4. Ghost
350 upvotesOpen-source, self-hosted game servers
Open-source dedicated game server platform. Spin up Minecraft, Valheim, Rust, Palworld, Enshrouded and Terraria on your own Hetzner Cloud account in seconds.
#1 on May 9, 20261 maker
5. PandaProbe
338 upvotesopen source agent engineering platform
PandaProbe is an open-source agent engineering platform that gives you deep observability into AI agent applications. Use it to trace, evaluate, monitor and debug your AI agents in development and production.

6. ModelHub
317 upvotesThe missing menu bar app for local LLMs on Mac.
ModelHub is a native macOS menu bar app for developers working with local LLMs. It helps you discover models from Hugging Face, download the right local build, manage your model library, and use Hugging Face models with Ollama, MLX, LM…
#2 on May 24, 20261 maker7. Agentmemory
310 upvotesPersistent memory for Claude Code, Codex & coding agents
You can now give Hermes, Claude Code, and Codex infinite memory. Agentmemory is trending on GitHub with 5,000+ Stars. CLAUDE md dumps 22,000+ tokens into context at 240 observations agentmemory: 1,900 tokens. same observations. 92% less.…
#2 on May 16, 20261 maker
8. Second Brain for AI
282 upvotesPersistent memory for Claude, ChatGPT & Cursor. Free.
Every AI conversation starts from zero. Your projects, decisions, and preferences disappear as soon as you close the chat. Second Brain fixes that. It is a self-hosted memory layer that works with Claude, ChatGPT, Cursor, and any MCP…

9. Minions
266 upvotesOpen source mission control for Hermes agent
Your Hermes Agent works great for one task. Try managing 20 in parallel? It's chaos. Cron jobs fail silently, tasks are blocked and you're spending more time fixing your agent than getting results. Minions gives you a single task board to…
#4 on May 8, 20261 maker
10. Files SDK
240 upvotesA unified storage SDK for object and blob backends
A unified storage SDK for object and blob backends. One small, honest API. Web-standards I/O. An escape hatch when you need the native client.
#4 on May 17, 20261 maker
11. Hyperswitch Prism
239 upvotesLibrary to plug-n-switch payment processors
Prism is a stateless payments library that connects your app to multiple payment processors. You can integrate once and point to any payment processor; add fallbacks for redundancy, switch processors based on routing rules - all by…
#4 on May 12, 20261 maker
12. Warp Open-Source
225 upvotesAgentic development environment built with the community
The best, longest-lasting software is built with the people who use it, so we've opened up Warp to the community. To make this possible, Oz-managed agents do the heavy lifting (coding, planning, testing), letting community members focus…
#7 on May 11, 20261 maker
13. Openstatus MCP Health Checker
204 upvotesTest MCP servers like a real AI client, not just a ping
Most monitors just send an HTTP ping. But a 200 OK is useless if the JSON-RPC handshake fails. Our tool is different because it performs a true protocol-level check, acting exactly like a real AI client. Key features: Full Handshake…
#4 on May 30, 20261 maker
14. Raindrop Workshop
187 upvotesOpen source, free, local debugger for AI agents
Raindrop Workshop is the first local debugger for agents. It's free, local, and open source. Your local agent traces stream, token-by-token, instantly. Another Agent like Claude Code can read them over MCP. Then Claude can write evals…
#6 on May 14, 20261 maker
15. Step 3.7 Flash
182 upvotesFlash-speed agents model that can see and act
An Apache 2.0 open-weight Flash model for real-world agents. Step 3.7 Flash combines vision, coding, search, tool use, 256K context, ~11B active params, and up to 400 TPS.

16. Rosentic
180 upvotesCatch when coding agents break each other before merge
Rosentic checks every PR against every other open PR before merge. When coding agents work in parallel, they break each other in ways no single-PR tool catches. Rosentic catches it. Deterministic analysis. Same scan, same result, every…

17. Re_gent
178 upvotesVersion Control for AI agent Activity
Git for your AI agent’s actions. Undo, trace, and control every step. re_gent shows what your coding agent changed, which prompt caused it, and lets you roll back agent work across files and sessions.
#6 on May 20, 20261 maker18. Pi Coding Agent
175 upvotesThe coding-agent harness you can make your own
Pi is a minimal terminal coding harness. Adapt Pi to your workflows, not the other way around. Customize Pi with extensions, skills, prompt templates, and themes. Bundle them as Pi packages and share via npm or git. Pi ships with powerful…

19. Memori
168 upvotesPersistent memory from agent trace, not just conversation
Memori launched its new agent-native memory infrastructure, enabling agents to create structured, long-term memory directly from agent trace — including execution paths, tool results, workflow steps, outcomes, and decision-making logic.…
#8 on May 28, 20261 maker
20. TrustClaw by Composio
150 upvotesSelf-hosted AI agent that connects 1000+ apps on Vercel
TrustClaw is a personal AI agent that you can self-host on Vercel with one command. Powered by Composio, it connects to 1000+ apps over OAuth, runs scheduled jobs on its own, and talks to you on the web or Telegram. It is fully…

21. Standboy
139 upvotesA Game Boy that wakes up while your agent works
A Game Boy in your editor sidebar that wakes up while your AI agent works and tucks away when it stops.
#10 on May 15, 20261 maker
22. Ara
137 upvotesAgentic Wispr flow computer-use-agent living in your notch
Automate everything. Bring your own LLM provider and use Codex app like Computer use for free, with several agents that can work for you autonomously.
#9 on May 8, 20261 maker
23. Cline SDK
121 upvotesBuild coding agents with a plugin-based open-source runtime
Cline SDK is an open-source TypeScript agent runtime with plugin architecture, native subagents, MCP support, checkpointing, cron jobs, and web fetch. For developers building custom coding agents or CLI tools.

24. Compartment
120 upvotesOpen-source runtime for internal team software
Compartment is a self-hosted open-source runtime for AI-built internal apps. It gives teams one place to run and share the apps, scripts, workers, and automations created with AI coding agents, on infrastructure they own. Use Cursor…

25. ShioriCode
118 upvotesOpen-source alternative to Codex & Claude Code
A desktop interface for the coding-agent CLIs you already use — Codex, Claude Code, Cursor, Gemini, Kimi, and a hosted Shiori provider. Run long-running sessions with project-aware threads, stream agent activity into a readable timeline…
#13 on May 19, 20261 maker
How this list is made
Junior imports every day's Product Hunt leaderboard. Each launch is filed under the first topic its makers chose, so it appears in one category only. This list takes the Open Source launches dated in May 2026 and ranks them by their upvotes. It refreshes daily.
More best-of lists for May 2026
- Best Productivity Tools214
- Best Design Tools76
- Best Developer Tools58
- Best Mac Apps46
- Best Android Apps37
- Best Marketing Tools38
- Best AI Tools41
- Best SaaS Tools27
- Best iOS Apps23
- Best APIs36
- Best Chrome Extensions28
- Best Analytics Tools27
- Best Health & Fitness Apps23
- Best Social Media Tools13
- Best Sales Tools20
- Best Fintech Tools25
Keep browsing
Questions
- What was the top Open Source launch of May 2026?
- Kilo Code for VS Code ("Parallel agents, diff reviewer, and multi-model comparisons"), with 878 upvotes on May 5, 2026, where it finished #1 of the day.
- How many Open Source Tools launched in May 2026?
- 67 on Product Hunt, with 8,336 upvotes between them. This list shows the 25 most upvoted.
- How is this list ranked?
- By Product Hunt upvotes, as recorded on launch day. Ties go to the launch with the better daily rank. Every launch is counted once, in the category its makers listed first.
- How do I reach the makers of these Open Source Tools?
- Each launch links to its page on Junior, with the people behind it (20 makers across this list). Junior adds their verified work emails, LinkedIn and X profiles for subscribers.
Reach the 20 makers behind the best Open Source Tools of May 2026
Junior lists the founders and makers behind every launch here, with verified work emails, LinkedIn and X profiles, CSV export and a daily Google Sheet. $29/month, cancel any time.