Open-source AI and vibe coding tools, ranked on public evidence.
Pick a tool you can defend to your team. Every project is scored from its GitHub data and reviewed for what it does well and where it breaks. The rankings update twice a day.
Every project fact-checked on GitHub: stars, last commit, license, Docker files.
Best of Vibe Coding
Starters to fork, agents that write the code, the skills and MCP servers that make them better, and the stack you ship on. No fluff, and paid never moves a rank.
| Rank | Project | Adoption | Freshness | Maintenance | Easy to run | Agent-ready | Score |
|---|---|---|---|---|---|---|---|
| 1 | skillsAgent skills for planning, TDD, debugging and code review | 98 | 100 | 93 | – | 70 | 94 out of 100 |
| 2 | eccSkills, agents, hooks and rules that add a workflow to coding agents | 96 | 100 | 89 | – | 70 | 93 out of 100 |
| 3 | superpowersSkill library that enforces a plan-then-TDD workflow in coding agents | 100 | 100 | 84 | – | 30 | 89 out of 100 |
| #4 | ponytailPrompt skill that makes coding agents write less, safer code | 93 | 100 | 97 | – | 30 | 89 out of 100 |
| #5 | cavemanProxy and skill that cut token use in coding agents | 79 | 100 | 97 | – | 70 | 89 out of 100 |
| #6 | ui-ux-pro-max-skillDesign-system skill for AI coding assistants, with searchable UI styles | 84 | 100 | 92 | – | 55 | 88 out of 100 |
| #7 | spec-kitCLI and agent skills for spec-driven development, bug fixing and idea assessment | 88 | 100 | 93 | – | 30 | 87 out of 100 |
| #8 | agent-skillsMarkdown engineering skills and slash commands for AI coding agents | 77 | 100 | 86 | – | 70 | 86 out of 100 |
| #9 | impeccableDesign skill and linter for AI coding agents' frontend output | 64 | 100 | 94 | – | 85 | 85 out of 100 |
| #10 | dokploySelf-hosted PaaS for deploying apps and databases on your own servers | 85 | 100 | 84 | 83 | 55 | 85 out of 100 |
Momentum, Verified build, Docs and Privacy are not measured yet; their weight goes to the signals shown. A dash means the signal is not scored for that kind of project. Hover a number for its rating in words.
Best of Open-Source AI
Apps, agents, models and the tools around them: what each one does, what it needs, where it breaks. No fluff, and paid never moves a rank.
| Rank | Project | Adoption | Freshness | Maintenance | Easy to run | Agent-ready | Score |
|---|---|---|---|---|---|---|---|
| 1 | OmniRouteOpenAI-compatible gateway that routes requests across hundreds of AI providers | 94 | 100 | 100 | 67 | 70 | 86 out of 100 |
| 2 | LiteLLMOpenAI-format gateway and Python SDK for calling 100+ LLM providers | 89 | 100 | 83 | 83 | 30 | 84 out of 100 |
| 3 | nanobotSmall Python agent runtime with bundled WebUI, TUI and chat channels | 81 | 100 | 93 | 83 | 30 | 84 out of 100 |
| #4 | LocalAIOne OpenAI-compatible server for text, speech, image and video models | 83 | 100 | 89 | 67 | 70 | 82 out of 100 |
| #5 | MilvusDistributed vector database with dense, sparse and hybrid search at scale | 82 | 100 | 84 | 67 | 70 | 81 out of 100 |
| #6 | LobeHubAgent workspace with builder, groups, scheduling and 10,000+ MCP skills | 86 | 100 | 83 | 67 | 45 | 80 out of 100 |
| #7 | OpenClawPersonal assistant gateway that answers in Discord, Slack, WhatsApp and Telegram | 100 | 100 | 91 | 50 | 45 | 79 out of 100 |
| #8 | llama.cppC/C++ inference engine serving GGUF models over an OpenAI-compatible API | 94 | 100 | 89 | 50 | 70 | 79 out of 100 |
| #9 | hindsightAgent memory server with retain, recall and reflect operations | 81 | 100 | 93 | 50 | 85 | 78 out of 100 |
| #10 | LightpandaHeadless browser written in Zig for AI agents and scraping | 85 | 100 | 92 | 50 | 70 | 78 out of 100 |
Momentum, Verified build, Docs and Privacy are not measured yet; their weight goes to the signals shown. A dash means the signal is not scored for that kind of project. Hover a number for its rating in words.
Open-source alternatives to paid tools
Paying for a closed tool? These are the highest-scoring open-source projects that do the same job, in the category we compare it in. A project marked "own claim" calls itself an alternative in its README.
Instead of Cursor
Compared in Coding agents and assistants- opencodeTerminal coding agent with build and plan modes77 out of 100
- orcaDesktop app that runs CLI coding agents in parallel git worktrees75 out of 100
- ArchonYAML workflow engine that runs coding agents in isolated worktrees73 out of 100
Instead of ChatGPT
Compared in Chat UIs- LobeHubAgent workspace with builder, groups, scheduling and 10,000+ MCP skills80 out of 100
- AnythingLLMDocument chat and agent app with built-in RAG, MCP and multi-user support77 out of 100
- Open WebUISelf-hosted chat UI for Ollama and OpenAI-compatible APIs with RBAC and RAG76 out of 100
Instead of Lovable
Compared in App builder starters and Design to code- ai-website-cloner-templateNext.js template with an agent skill that rebuilds a website from its URL77 out of 100
- screenshot-to-codeTurns screenshots and mockups into Tailwind, React or Vue code65 out of 100
- 47 out of 100
Instead of Perplexity
Compared in Search- MorphicSearch engine that answers with citations and renders rich inline components70 out of 100
- Local Deep ResearchAgentic research assistant with local LLMs, SearXNG and encrypted libraries65 out of 100
- GPT ResearcherResearch agent that writes cited reports from web and local documents64 out of 100
Instead of v0
Compared in App builder starters and Design to code- ai-website-cloner-templateNext.js template with an agent skill that rebuilds a website from its URL77 out of 100
- screenshot-to-codeTurns screenshots and mockups into Tailwind, React or Vue code65 out of 100
- 47 out of 100
Instead of LM Studio
Compared in Model serving- LocalAIOne OpenAI-compatible server for text, speech, image and video models82 out of 100
- llama.cppC/C++ inference engine serving GGUF models over an OpenAI-compatible API79 out of 100
- vLLMHigh-throughput LLM serving engine with OpenAI and Anthropic APIs75 out of 100
How the ranking works
Nobody pays for a place, and every score shows its parts.
Read the full methodologyChecked on GitHub
Stars, last commit, releases, license and Docker files come from GitHub itself, not from the project's own claims.
Scored in the open
Each score is built from named signals with published weights. Every project page shows what its score is made of.
Nobody pays for a place
Sponsors and tips never move a rank. Spot a wrong fact and you can report it from any page.