SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 ai-tool Open-Source Projects
-
browser-use
Open-source browser automation framework for AI agents. Browser Use lets AI agents control real browser sessions to complete multi-step web workflows.
browser-use: https://github.com/browser-use/browser-use
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
cc-switch
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Project mention: DeepSeek makes the V4 Pro price discount permanent | news.ycombinator.com | 2026-05-22 -
https://github.com/plandex-ai/plandex/blob/9017ba33a627c518a...
This line tells me your code isn't running within a company with a large number of active users. A limitless select * to get Auth tokens from a database is one of those things that breaks at scale.
-
Skill_Seekers
Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection
Project mention: Turn Docs, Code and PDFs into Claude AI Skills in Minutes | news.ycombinator.com | 2025-11-07 -
nanobrowser
Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.
Try search on a browser extension store for "AI Chat website" or similar. Also you can check out https://github.com/nanobrowser/nanobrowser.
-
ccstatusline
🚀 Beautiful highly customizable statusline for Claude Code CLI with powerline support, themes, and more.
Project mention: claude-statusline: a configurable status line for Claude Code | dev.to | 2026-03-17ccstatusline: customizable formatter with token usage and metrics
-
steel-browser
🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.
-
-
-
Judge0 API
Robust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.
Project mention: Running Python code in a sandbox with MicroPython and WASM | news.ycombinator.com | 2026-06-06If you're interested in not reinventing the sandbox for LLMs, consider Judge0: https://judge0.com/
I have absolutely no relation to the project except for the fact that I went to the same Uni as the creator.
-
Project mention: Modly: Drop a photo, get a 3D mesh, open source and runs on your GPU | news.ycombinator.com | 2026-03-26
skip all the adds (christ almoghty what a shit site. fucking hell.)
https://github.com/lightningpixel/modly
-
claude_codex_bridge
Visible multi-agent CLI teams for Claude, Codex, Gemini, OpenCode, and Droid with project memory and tmux supervision
https://github.com/fengshao1227/ccg-workflow
This one also seems promising, but I haven't tried it yet.
https://github.com/bfly123/claude_code_bridge
All of them are made by Chinese dev. I know some people are hesitant when they see Chinese products, so I'll address that first. But I have tried all of them, and they have all been great.
-
playwright-skill
Claude Code Skill for browser automation with Playwright. Model-invoked - Claude autonomously writes and executes custom automation for testing and validation.
Project mention: I Tried and Failed to Rebuild the 1996 Space Jam Website with Claude | news.ycombinator.com | 2025-12-07Just use Playwright Skill (https://github.com/lackeyjb/playwright-skill). It is a game changer. Otherwise it is Claude the Blind, as OP mentioned.
-
ccs
Switch between Claude accounts, Gemini, Copilot, OpenRouter (300+ models) via CLIProxyAPI OAuth proxy. Visual dashboard, remote proxy support, WebSearch fallback. Zero-config to production-ready. (by kaitranntt)
Project mention: Show HN: CCS – A Multi-Account Switcher and Model Manager for Claude Code | news.ycombinator.com | 2025-12-17 -
agentic-context-engine
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
Project mention: Show HN: LLM agents that write Python to analyze execution traces at scale | news.ycombinator.com | 2026-03-07 -
-
pilot-shell
How real engineers run Claude Code and Codex: spec-driven planning, enforced TDD, persistent memory, and quality enforcement on all levels. Make your agents production-ready.
Project mention: Claude Pilot – Claude Code is powerful. Pilot makes it reliable | news.ycombinator.com | 2026-02-23 -
open-cowork
Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — with sandbox isolation, multi-model support, and Feishu/Slack integration.
-
anything-analyzer
全能协议分析工具:浏览器抓包 + MITM 代理 + 指纹伪装 + AI 分析 + MCP Server 无缝对接 AI Agent/IDE | All-in-one protocol analysis toolkit — built-in browser capture, MITM proxy, JS hooks, fingerprint spoofing, AI analysis & MCP server for agent integration
Project mention: How to Debug Encrypted API Traffic When Console.log Isn't Enough | dev.to | 2026-04-18The protocol analysis landscape has been evolving. Projects like anything-analyzer are combining multiple approaches — browser capture, MITM proxying, and JS hooks — into unified toolkits. Some of these newer tools are also integrating with AI-powered analysis through MCP (Model Context Protocol) servers, which means you can point an AI assistant at your captured traffic and ask it to spot anomalies.
-
Claude-Command-Suite
Professional slash commands for Claude Code that provide structured workflows for software development tasks including code review, feature creation, security auditing, and architectural analysis.
Project mention: Show HN: Claude Command Suite inspired by Anthropics best practices guide | news.ycombinator.com | 2025-06-12 -
-
Project mention: Show HN: Browsernode – Open-source TS browser agent(browser-use compatible) | news.ycombinator.com | 2025-08-07
-
reconmap
Reconmap is a collaboration-first security operations platform for infosec teams and MSSPs, enabling end‑to‑end engagement management, from reconnaissance through execution and reporting. With built-in command automation, output parsing, and AI‑assisted summaries, it delivers faster, more structured, and high‑quality security assessments.
ai-tools discussion
ai-tools related posts
-
Three Commands to Make Claude Code Stop Guessing Your Infra
-
Supabase Skills to run your business ops
-
Stop AI From Recommending Redundant Indexes on Existing GSIs
-
Show HN: Best of AI – Handpicked and Curated Open-Source List of AI Tools
-
Why AI-generated draw.io AWS diagrams have empty squares (and a fix)
-
Aming Claw – Zero-orchestration multi-agent coding
-
Pay for Any API from Inside Claude with Base MCP + APIbase
-
A note from our sponsor - SaaSHub
www.saashub.com | 7 Jun 2026
Index
What are some of the best open-source ai-tool projects? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | browser-use | 97,236 |
| 2 | cc-switch | 90,508 |
| 3 | plandex | 15,439 |
| 4 | Skill_Seekers | 13,941 |
| 5 | nanobrowser | 13,088 |
| 6 | ccstatusline | 10,313 |
| 7 | steel-browser | 7,122 |
| 8 | awesome-ai-tools | 5,403 |
| 9 | logfire | 4,280 |
| 10 | Judge0 API | 4,202 |
| 11 | modly | 3,857 |
| 12 | claude_codex_bridge | 2,899 |
| 13 | playwright-skill | 2,718 |
| 14 | ccs | 2,463 |
| 15 | agentic-context-engine | 2,244 |
| 16 | Awesome AI Coding Tools | 1,761 |
| 17 | pilot-shell | 1,738 |
| 18 | open-cowork | 1,449 |
| 19 | anything-analyzer | 1,337 |
| 20 | Claude-Command-Suite | 1,278 |
| 21 | browserable | 1,196 |
| 22 | browsernode | 1,053 |
| 23 | reconmap | 932 |