SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 TypeScript Agent Projects
-
Project mention: I Tested Flowise, Dify, and n8n Across 30+ Client Deployments. Here Is My Verdict. | dev.to | 2026-04-07
Citation Capsule: n8n's GitHub community reached 182,000+ stars across a 7-year development history, with 70+ AI-specific nodes added in 2024 to 2025. Source: n8n GitHub. Dify crossed 106,000 stars on GitHub with an Apache 2.0 license. Source: Dify GitHub. Flowise reached 51,000+ stars with MIT license. Source: Flowise GitHub. Dify's minimum recommended RAM is 4 GB versus Flowise's 1 GB and n8n's 300 MB. Source: Dify Docs.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
CopilotKit
The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol
The instructions prop is ignored with custom agents. We set system instructions via CopilotSidebar's instructions field and they were silently dropped. This is a known open CopilotKit issue. The workaround: define instructions in the agent's system message directly.
-
composio
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
Project mention: pass@1 is a gamble — how ensemble coding enhances AI reliability | dev.to | 2026-04-02The ensemble idea is in the air. Mozilla AI's Star Chamber fans out code reviews to Claude, GPT, and Gemini in parallel, using consensus tiers and optional debate rounds where anonymized feedback circulates back to all models. Karpathy's llm-council runs a deliberation pipeline — parallel query, peer review, chairman synthesis — for general-purpose tasks. Roundtable orchestrates multiple AI CLI tools through a unified MCP interface. Composio's Agent Orchestrator manages parallel coding agents with git worktrees for task decomposition — different agents working on different sub-tasks. And Aider's Architect Mode pairs two models in complementary roles (planner + editor).
-
sim
Build, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce.
Sim ai is an alternative to Heym
-
mastra
From the team behind Gatsby, Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.
Project mention: Flue is a TypeScript framework for building the next generation of agents | news.ycombinator.com | 2026-05-02Why would I choose this over Mastra? [0]
[0] https://mastra.ai/
-
12-factor-agents
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
Own your control flow! A key point from 12 factor agents.
"One thing that I have seen in the wild quite a bit is taking the agent pattern and sprinkling it into a broader more deterministic DAG." - https://github.com/humanlayer/12-factor-agents/blob/main/REA...
-
stagehand
The AI Browser Automation library by Browserbase. Write web automation scripts in plian english with primitives like act('click this button'), extract('get the price for xyz product'), and observe('find the submit button').
Project mention: Browser Tools for AI Agents Part 1: Playwright, Puppeteer, and Why Your Agent Picked Playwright | dev.to | 2026-04-26Right. So Stagehand (21.8k stars) is Browserbase's TypeScript SDK and it does something properly clever. It wraps Playwright with three AI primitives: act() (do something on the page), extract() (pull structured data out), and agent() (let the LLM figure out a multi-step flow). On paper that sounds like yet another Playwright wrapper. It isn't.
-
Project mention: Show HN: Mnemo – local-first AI memory layer for any LLM (Rust, SQLite,petgraph) | news.ycombinator.com | 2026-06-03
-
maxun
🔥 The open-source no-code platform for web scraping, crawling, search and AI data extraction • Turn websites into structured APIs in minutes 🔥
Project mention: 👽 Extract Thousands of Rows of Data Without Writing Code (Open Source) | dev.to | 2025-07-17Explore the project on GitHub: https://github.com/getmaxun/maxun
-
Project mention: Show HN: RowboatX – open-source Claude Code for everyday automations | news.ycombinator.com | 2025-11-18
We’ve included the exact agents used in the demo here for reference: https://github.com/rowboatlabs/rowboat/blob/cli/apps/cli/exa....
We’re adding an easier way to run examples soon. In the meantime, if you’d like to try this one locally: (1) Copy the agent file into ~/.rowboat/agents/ (2) Add the MCP server (and your keys) to ~/.rowboat/config/mcp.json (3) Run: 'rowboatx --agent=tweet-podcast --input=go'
-
Project mention: I spent 1 month building my first NPM package from scratch, and here is the result | dev.to | 2026-03-26
The idea for this project came up when I discovered React Doctor. I really liked their concept and thought about a way to bring this kind of auditing tool outside of the React ecosystem. That's how I created Web Doctor.
-
superset
Code Editor for the AI Agents Era - Run an army of Claude Code, Codex, etc. on your machine (by superset-sh)
-
Project mention: Tambo 1.0: Open-source toolkit for agents that render React components | news.ycombinator.com | 2026-02-10
-
Project mention: DeepSeek V4–almost on the frontier, a fraction of the price | news.ycombinator.com | 2026-05-02
So RPI and QRSPI skills(e.g. https://github.com/mattpocock/skills and https://github.com/humanlayer/humanlayer/tree/main/.claude/c... and https://github.com/dfrysinger/qrspi-plus ) for working with claude code work well enough for me that they can reliably produce code that matches the plan/spec in a way they did not till December 2025.
I have a gut feeling that these models can do just as well, has someone run a reasonable size task — >=1-2 days of designing and planning — and see it work well with these models?
-
https://news.ycombinator.com/item?id=44672902
electric-sql/electric: https://github.com/electric-sql/electric :
> Specifically, Electric is a read-path sync engine for Postgres. It syncs data out of Postgres into ... anything you like. The core sync protocol is based on a low-level HTTP API. This integrates with CDNs for highly-scalable data delivery.
electric-sql/pglite:
-
Project mention: VoltAgent Just Asked Us to Build Their Guardrail Provider Interface. Here Is What We Shipped. | dev.to | 2026-03-20
VoltAgent is a 6.8k-star TypeScript framework for building AI agents. They already had InputGuardrail and OutputGuardrail types — handler functions that run before and after model calls.
-
Project mention: Paseo – Beautiful open-source coding agent interface (desktop, mobile, CLI) | news.ycombinator.com | 2026-06-02
Gotta say: I love how mobile app works on my 13 years old Nexus 7 (2GB RAM). It was the sole reason I choose it, actually - other PWAs are too much for the little guy.
I am really hoping this to be merged soon: https://github.com/getpaseo/paseo/pull/1296
-
git-mcp
Put an end to code hallucinations! GitMCP is a free, open-source, remote MCP server for any GitHub project
-
Project mention: Gemma 4 Needs More Than a Chat Box: Why Local AI Needs Generative UI | dev.to | 2026-05-24
OpenUI GitHub repository
-
genkit
Open-source framework for building AI-powered apps in JavaScript, Go, and Python, built and used in production by Google
Project mention: Genkit Middleware: Intercept, Extend and Harden your Gen AI Pipelines | dev.to | 2026-05-14For more inspiration, the source of the official middlewares is open in the Genkit GitHub repository, and reading them is genuinely educational.
-
-
That's when I thought, why not use the Cloudflare Agent SDK to build an agent. I started building my agent with custom functions to handle audio input and output. The M5Stack would connect to the agent deployed on the edge, send the audio chunks, the agent would process this, perform the action, and stream the audio response back to the device. This was working fine, but it was a lot of code, fragile code. If I switched the Text-To-Speech (TTS) or Speech-To-Text(STT) models, I would have to update the code to handle encoding, and decoding. This wasn't fun at all.
-
eko
Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai
Project mention: I built an open-source AI browser that automates web tasks with natural language | dev.to | 2025-11-03Special thanks to Eko for the powerful agent framework.
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 Agents discussion
TypeScript Agents related posts
-
Why agents need memory that improves itself
-
Memory beats full context on LongMemEval — and the wins we don't get
-
Aging and Eye Problems
-
I ported a macOS-only AI agent tool to Windows — here's what I learned
-
5 Multi-Agent Patterns in Strands Agents: Which One and When
-
Paseo – Beautiful open-source coding agent interface (desktop, mobile, CLI)
-
Spatial IDE's for agentic coding workflows
-
A note from our sponsor - SaaSHub
www.saashub.com | 12 Jun 2026
Index
What are some of the best open-source Agent projects in TypeScript? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | Flowise | 53,462 |
| 2 | CopilotKit | 34,853 |
| 3 | composio | 28,715 |
| 4 | sim | 28,708 |
| 5 | mastra | 24,988 |
| 6 | 12-factor-agents | 23,203 |
| 7 | stagehand | 23,092 |
| 8 | agentmemory | 20,972 |
| 9 | maxun | 15,855 |
| 10 | rowboat | 14,951 |
| 11 | react-doctor | 12,588 |
| 12 | superset | 11,731 |
| 13 | tambo | 11,161 |
| 14 | humanlayer | 10,983 |
| 15 | electric | 10,229 |
| 16 | voltagent | 9,548 |
| 17 | paseo | 8,325 |
| 18 | git-mcp | 8,163 |
| 19 | openui | 6,959 |
| 20 | genkit | 6,104 |
| 21 | pyspur | 5,734 |
| 22 | agents | 5,086 |
| 23 | eko | 4,928 |
Sponsored
SaaSHub - Software Alternatives and Reviews
SaaSHub helps you find the best software and product alternatives
www.saashub.com