Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise. Learn more →
Top 23 TypeScript ai-agent Projects
-
deepseek-harness
DeepSeek Harness &DeepSeek Code is the working name around DeepSeek's new Code Harness hiring signal. This source-based guide explains the team, roles, agent harness layer, and AI coding market context.
>It is built on an everything-is-a-plugin architecture and powered by Cordis, whose design is described in A Programming Paradigm for Spatiotemporal Composability.
https://github.com/deepseek-ai/deepseek-harness
-
AppSignal
AppSignal knows why the f*#k it crashed. Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
-
gstack
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
git clone --single-branch --depth 1 \ https://github.com/garrytan/gstack.git \ ~/.claude/skills/gstack
-
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
Project mention: The tool is installed and on PATH. Your app still can't find it. | dev.to | 2026-09-19Both cases came from real threads: the git one is Kilo-Org/kilocode#13452 and the ffmpeg one is CherryHQ/cherry-studio#18528. I've only had eyes on those two, so your mileage may vary. Hope this helps.
-
OpenMAIC — Open Multi-Agent Interactive Classroom
Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click
The repository metadata reported that OpenMAIC was created on 2026-03-11, uses main as its default branch, was not archived, was not a fork, and had a pushed_at date of 2026-09-02. Its README describes an immersive multi-agent learning and course-creation platform and includes a v1.0.0 section. That is the project's documentation describing itself; it does not verify what the software can do.
-
CopilotKit
The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol
Project mention: Show HN: The Channels SDK – Bring Any Agent to Any Channel (Slack, MS Teams) | news.ycombinator.com | 2026-08-06Not necessarily wrong, but that's just a maturity problem on our end right now. We're aiming to take the same approach as our web SDKs: it works great for open-source deployments and works even better with Enterprise Intelligence. We had some back-and-forth over webhook vs. WebSocket in the last two weeks that caused some churn on our side.
If you point your agent at our SDKs, they should help you use the Slack or Teams adapters directly without leveraging the hosted service: https://github.com/CopilotKit/CopilotKit/tree/main/packages/...
Delivering AG-UI with generative UI to Slack and Teams should work great with the open-source packages. We'll make these interfaces better and more intuitive.
-
OMP (Oh My Pi) is a coding agent that talks to the model APIs directly. I log in to Anthropic, Cursor and OpenAI once, and OMP routes each kind of work to a model through roles:
-
AionUi
Open-source 24/7 Cowork app for OpenClaw, Hermes, Claude Code, Codex, OpenCode and 20+ more CLI Agent | Customize your assistants | Team them up｜Star if you like it!
Project mention: AionUi: Open-Source AI Cowork Platform for Claude Code, Codex and Gemini | news.ycombinator.com | 2026-05-27 -
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
TencentDB-Agent-Memory
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.
Product name. The repo is TencentDB Agent Memory. It turns conversations, docs and code into four reusable memory assets: Chat Memory, Skill, LLM-Wiki and Code-Graph (GitHub repo).
-
activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Project mention: Deploy Activepieces on Google Cloud Run with Production Guardrails Built In | dev.to | 2026-06-17Spinning up Activepieces with docker run takes minutes. Running it so you'd trust it with real business workflows — that's the part that could take weeks. Activepieces isn't just another stateless service: it holds API credentials, OAuth tokens, webhook secrets, and integration keys for every system it touches — your CRM, your payment processor, your data warehouse. A poorly secured Activepieces instance is a skeleton key to your entire integration surface. "Production" for this app means a backed-up database, managed secrets, supply-chain controls on plugins, a zero-trust UI boundary, and the full CI/CD + monitoring stack. We have implemented and published an Activespace module on radmodules.dev that demonstrates how Google Cloud Run and other platform services supports a production deployment with out of the box guardrails.
-
nocobase
NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of production-proven infrastructure and a WYSIWYG no-code interface, so you get both speed and reliability.
GitHub Releases — the 3.0 alpha notes
-
Project mention: Harness Engineering ทักษะใหม่ 2026 จาก 10 สัญญาณบน X สัปดาห์เดียว | dev.to | 2026-09-24
[2] Walking Labs. "Learn Harness Engineering." github.com, 2026. https://github.com/walkinglabs/learn-harness-engineering
-
holaOS
Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps, browser, local files — with shared memory. Any agent (Claude Code, Codex), any model, or BYOK. Set up in clicks, not months. Local-first: your data never leaves your machines.
Project mention: Show HN: HolaOS––An Opensourced workspace that alternative to Claude | news.ycombinator.com | 2026-09-11 -
presenton
Open-Source AI Presentation Generator and API (Gamma, Canva, Beautiful AI, Decktopus, Presentations AI Alternative)
-
-
PI-Desktop
Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins
That is the idea behind PI-Desktop: a local-first desktop workspace for AI coding agents. It brings persistent projects, sessions, model switching, permissions, and multi-agent workflows into one app that runs on macOS, Windows, and Linux.
-
wigolo
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
-
In case you are looking for an open-source alternative without vendor lock-in (https://github.com/agenta-ai/agenta)
-
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.
-
Project mention: OpenScience: Workbench for scientific research using custom LLMs | news.ycombinator.com | 2026-07-04
-
FlyEnv
Native local development environment for Windows, macOS & Linux. A modern alternative to XAMPP, MAMP, Laragon and Laravel Herd, with runtimes, databases, web servers, local sites, HTTPS, AI coding tools and MCP.
-
Project mention: Show HN: Kite AI Agent: Conversational Operations for Kubernetes | news.ycombinator.com | 2026-03-06
-
Project mention: CyberStrike – open-source AI harness for offensive security (AGPL) | news.ycombinator.com | 2026-08-22
-
nexu
The simplest desktop client for OpenClaw 🦞 — bridge your Agent to WeChat, Feishu, Slack & Discord in one click. Works with Claude Code, Codex & any LLM. BYOK, Oauth, local-first, chat from your phone 24/7.
Project mention: Every AI Startup Should Watch Out: 1000+ Ghost Accounts Drained Our Platform in 15 Days | dev.to | 2026-04-16🦞 Nexu: https://github.com/nexu-io/nexu
-
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 ai-agent discussion
TypeScript ai-agent related posts
-
AgentConnect vs. Claude Tag: comparing the two ways to bring agents into team chat
-
Tell HN: Claude Code refuses to login to any website not running on localhost
-
Show HN: Browsentic Open-source Claude for Chrome alternative for any agent CLI
-
Steadywag: I Vibe-Coded a Dog Care App Where Missing Paperwork Is Data
-
I filed it as a flaky test. It was a crash that try/catch can't reach.
-
DeepSeek Harness Desktop for macOS and Windows
-
I ran six coding agents on seven local models, 30 times each
-
A note from our sponsor - AppSignal
www.appsignal.com | 6 Oct 2026
Index
What are some of the best open-source ai-agent projects in TypeScript? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | deepseek-harness | 241,594 |
| 2 | gstack | 134,901 |
| 3 | cherry-studio | 52,347 |
| 4 | OpenMAIC — Open Multi-Agent Interactive Classroom | 39,826 |
| 5 | CopilotKit | 37,700 |
| 6 | oh-my-pi | 33,887 |
| 7 | AionUi | 33,314 |
| 8 | TencentDB-Agent-Memory | 27,692 |
| 9 | activepieces | 24,860 |
| 10 | nocobase | 24,433 |
| 11 | learn-harness-engineering | 17,807 |
| 12 | holaOS | 11,452 |
| 13 | presenton | 10,943 |
| 14 | inkos | 10,100 |
| 15 | PI-Desktop | 6,332 |
| 16 | wigolo | 5,442 |
| 17 | agenta | 4,804 |
| 18 | MonkeyCode | 4,769 |
| 19 | openscience | 3,910 |
| 20 | FlyEnv | 3,251 |
| 21 | kite | 3,150 |
| 22 | CyberStrike | 2,925 |
| 23 | nexu | 2,566 |
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