Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise. Learn more →
Top 23 TypeScript Cursor Projects
-
oh-my-openagent
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
-
AppSignal
AppSignal knows why the f*#k it crashed. Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
-
onlook
The Developer Tool for Designers • An Open-Source AI-First Design tool • Visually build, style, and edit your code with AI • World's best, top-most agent recommended #1 Developer tool for Designers to design with Real Code.
Project mention: Loupe VS onlook - a user suggested alternative | libhunt.com/r/winchxyz/loupe | 2026-07-22Onlook is a visual editor for existing React/Tailwind codebases; Loupe builds the site from a prompt and verifies every AI edit against the real render, with hand editing on the live page.
-
Happy Coder
Mobile and Web client for Claude Code. Spawn and control multiple Claude Codes in parallel. Happy Coder runs on your hardware. Works seamlessly with your existing tools and workflow. Secure with end-to-end encryption. Hands-free control with voice agent - not just dictation.
Project mention: Happy — The Open-Source App That Puts Claude Code in Your Pocket | dev.to | 2026-04-15Code on GitHub. Live app at happy.engineering. More posts at radarlog.kr.
-
opcode
A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more.
-
Worth reading alongside these: agentmemory#648, a stability pass where two separate bugs turned out to share one root cause — a daemon wrapper surviving stop — and the dawnai memory-tooling commit, which adds a gated live-smoke suite for exactly the reason I am writing this post: some behaviors only appear against a real backend, so they gate a separate suite on a real key and keep it out of CI.
-
It's convenient to place the rules in a separate directory. For example, create a .cursor folder in the project root and put all rules inside a rules folder within it. Be sure to give the AI agent a link to the rules. Here's also an example of a detailed set of rules from another project configured with Framelink MCP:
-
claude-context
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
Claude Code doesn't do anything with semantic search or embeddings out of the box. They use a simple grep tool instead.
Neither does OpenAI's Codex CLI - you can confirm that by looking at the source code https://github.com/openai/codex
Cursor and Windsurf both use semantic search via embeddings.
You can get semantic search in Claude Code using this unofficial plugin: https://github.com/zilliztech/claude-context
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
git-mcp
Put an end to code hallucinations! GitMCP is a free, open-source, remote MCP server for any GitHub project
-
refly
The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more. Build Clawdbot 🦞· APIs for Lovable · Bots for Slack & Lark/Feishu · Skills are infrastructure, not prompts.
Inspired by BulletProof React, I applied its codebase architecture concepts to the Refly codebase.
-
-
mcp
Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser (by BrowserMCP)
Project mention: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding? | news.ycombinator.com | 2026-06-15Pi is decent.
I've used the cli agents for claude, cursor, and pi, plus several custom harnesses I've written myself from time to time as experiments (and I guess technically gastown, if we're calling that a harness).
Pi is... just fine.
It does what I need it to, has a decent selection of tooling out of the box, integrates nicely with other tools, and generally gets out of my way enough that I don't think about it much anymore.
If you can run ~30b models at decent speeds, I think most folks would be pleasantly surprised at how capable they are with pi.
Tack on some of the extensions (ex https://pi.dev/packages/pi-mcp-adapter?name=mcp and https://pi.dev/packages/pi-web-access?name=search) and I get web tooling (ex - perplexity search), access to mcps to do things like drive chrome (https://browsermcp.io/) or firefox (https://github.com/mozilla/firefox-devtools-mcp)
It's fine. Is it as good as a subsidized top tier model? Nope. Is it free and still very capable? Yup.
And personally, I've been having a LOT of fun with the pi sdk (https://pi.dev/docs/latest/sdk)
Which is something that all the other providers charge you api access rates for (ex - thousands a month).
-
OpenCursor
Open-source Cursor-like AI coding agent for VS Code - agentic chat, multi-provider LLMs (OpenAI, Ollama, llama.cpp), semantic search, and MCP support
-
Project mention: Show the Evidence That an AI Action Approval Actually Covered | dev.to | 2026-07-23
For a design critique, I would capture a fixed version of https://github.com/chaitin/MonkeyCode and use its visible workflows only as material for testing whether reviewers understand action, destination, and authority. That is a research prompt, not a representation that the repository supports the approval card above. Researchers who want feedback on their study framing can discuss it with users at https://discord.gg/2pPmuyr4pP without sharing participant data.
-
cc-sdd
Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity.
Project mention: I Refused to Write Specs Until Claude Code Generated Wrong Code Three Times | dev.to | 2026-05-19This isn't original to me. The 2026 wave of spec-driven tooling (OpenSpec, cc-sdd, amux, Kiro) is all built on the same observation. GitHub Copilot Workspace doesn't even let you skip the step: it generates an editable "proposed specification" before it touches code, because the team that built it figured out that the spec is the only artifact in the workflow that the human can actually review.
-
Project mention: Why the agent needs access to the environment, not a human’s retelling of it | dev.to | 2026-09-10
For databases: crystaldba/postgres-mcp (3.3k stars) has a "Restricted Mode" that "Limits operations to read-only transactions and imposes constraints on resource utilization" and is described as "suitable for production environments". bytebase/dbhub (3.5k stars, release 2026-09-02) covers Postgres, MySQL, SQL Server, MariaDB and SQLite with "Read-only mode, row limiting, and query timeout to prevent runaway operations". Google's MCP Toolbox for Databases (16k stars) ships "Prebuilt generic tools for instant data exploration (e.g., list_tables, execute_sql)". The original reference Postgres server from the Model Context Protocol project is archived; the current reference set is filesystem, git, fetch, memory and a few others.
-
Also in this issue: Matt Nigh analyzed 2,500+ repositories to figure out what makes AGENTS.md files actually useful (spoiler: most aren't), browser fingerprinting via favicon is both creepy and clever, PrinceJS lands in the top 3 performance benchmarks despite being "the smallest backend framework ever," and privacy fans get Ackee for self-hosted analytics. Ultracite brings zero-config linting with opinions baked in, and zerobyte automates backups for self-hosters who want to set it and forget it.
-
cursor-ai-downloads
All Cursor AI's official download links for both the latest and older versions, making it easy for you to update, downgrade, and choose any version. 🚀
-
crystal
(Crystal is now Nimbalyst) Run multiple Codex and Claude Code AI sessions in parallel git worktrees. Test, compare approaches & manage AI-assisted development workflows in one desktop app. (by stravu)
Project mention: Show HN: Offrun – manage every coding agent from one workspace | news.ycombinator.com | 2026-10-03 -
Chaterm
Open source AI terminal for cloud and infrastructure management, enabling you to deploy, troubleshoot, and automate services using natural language and intelligent agents.
Originally published at https://chaterm.ai GitHub：https://github.com/chaterm/Chaterm
-
Project mention: LNAI – Define AI coding tool configs once, sync to Claude, Cursor, Codex, etc. | news.ycombinator.com | 2026-02-03
Is this substantially different than https://github.com/intellectronica/ruler? Or how would you differentiate?
-
DevDocs
Completely free, private, UI based Tech Documentation MCP server. Designed for coders and software developers in mind. Easily integrate into Cursor, Windsurf, Cline, Roo Code, Claude Desktop App (by cyberagiinc)
-
pr-lens
Review code 100X faster. Lens draws every PR as animated architecture and data-flow walkthroughs, inside the pull request itself. Use it as a GitHub App, GitHub Action, CLI, or a Skill for your coding agent
Project mention: Show HN: I stopped reading my agent's diffs, so I made every PR draw itself | news.ycombinator.com | 2026-10-05 -
Project mention: Ask HN: Is there a free MCP for web and documentation search? | news.ycombinator.com | 2026-01-17
* https://github.com/arabold/docs-mcp-server: I didn't test this, but I was turned off by the fact you have to run the server in the background instead of allowing it to be booted by the Codex instance (via npx) like it can for other kinds of MCP servers.
Does anyone have a solution to this that hits on all marks: free, able to read websites including JS ones, thorough and high-quality?
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
NOTE:
The open source projects on this list are ordered by number of github stars.
The number of mentions indicates repo mentiontions in the last 12 Months or
since we started tracking (Dec 2020).
TypeScript Cursor discussion
TypeScript Cursor related posts
-
How Styx keeps coding agents away from production
-
Styx: Hacktoberfest Open-Source AI Challenge!
-
Looking for contributors!
-
Your Repo Has Tests. Can Your AI Agent Find the Command?
-
I tested whether Claude Code follows decisions from earlier chats
-
Measure an AI Coding Harness from L0 to L4 with Harness Score
-
Show HN: I turned my team's coding-agent history into a knowledge graph
-
A note from our sponsor - AppSignal
www.appsignal.com | 15 Oct 2026
Index
What are some of the best open-source Cursor projects in TypeScript? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | oh-my-openagent | 69,901 |
| 2 | onlook | 26,890 |
| 3 | Happy Coder | 24,084 |
| 4 | opcode | 22,421 |
| 5 | agentmemory | 20,972 |
| 6 | Figma-Context-MCP | 15,986 |
| 7 | claude-context | 12,597 |
| 8 | git-mcp | 8,461 |
| 9 | refly | 7,533 |
| 10 | browser-tools-mcp | 7,326 |
| 11 | mcp | 6,866 |
| 12 | OpenCursor | 6,024 |
| 13 | MonkeyCode | 4,822 |
| 14 | cc-sdd | 3,710 |
| 15 | dbhub | 3,626 |
| 16 | ultracite | 3,314 |
| 17 | cursor-ai-downloads | 3,241 |
| 18 | crystal | 3,126 |
| 19 | Chaterm | 3,095 |
| 20 | ruler | 2,943 |
| 21 | DevDocs | 2,108 |
| 22 | pr-lens | 1,874 |
| 23 | docs-mcp-server | 1,800 |
Sponsored
AppSignal knows why the f*#k it crashed.
Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
www.appsignal.com