SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 TypeScript agent-framework Projects
-
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
agents
Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows. (by inkeep)
Project mention: Launch HN: Inkeep (YC W23) – Open-Source Agent Builder | news.ycombinator.com | 2025-10-16Inkeep SDK – Elastic License 2.0 with Supplemental Terms https://github.com/inkeep/agents?tab=License-1-ov-file#readm...
-
-
gitagent
A universal git-native AI agent framework. Your agent lives inside a git repo — identity, rules, memory, tools, and skills are all version-controlled files.
Project mention: Show HN: GitAgent – An open standard that turns any Git repo into an AI agent | news.ycombinator.com | 2026-03-146. CI/CD with GitAgent validate in GitHub Actions
The CLI lets you run any agent repo directly:
npx @open-gitagent/gitagent run -r https://github.com/user/agent -a claude
The compliance layer is optional, but there if you need it — risk tiers, regulatory mappings (FINRA, SEC, SR 11-7), and audit reports via GitAgent audit.
Spec is at https://gitagent.sh, code is on GitHub.
Would love feedback on the schema design and what adapters people would want next.
-
-
Project mention: Introducing Stoneforge: Open-Source Orchestration for AI Coding Agents | dev.to | 2026-03-05
TL;DR: Stoneforge is an open-source platform that orchestrates multiple AI coding agents in parallel. A Director plans tasks, workers execute in isolated git worktrees, stewards test and merge, and a daemon keeps it all moving. Works with Claude Code, Codex, and OpenCode. GitHub
-
AgentOS
Build autonomous AI agents with adaptive intelligence and emergent behaviors to simulate any scenario. Multimodal RAG included. (by framersai)
Project mention: Show HN: Paracosm – simulate what-if scenarios with AI agents | news.ycombinator.com | 2026-05-05 -
fullstack-langgraph-nextjs-agent
Production-ready Next.js template for building AI agents with LangGraph.js. Features MCP integration for dynamic tool loading, human-in-the-loop tool approval, persistent conversation memory with PostgreSQL, and real-time streaming responses. Built with TypeScript, React, Prisma, and Tailwind CSS.
Project mention: LangGraph.js AI Agent Template: production-ready Next.js framework for building AI agents | dev.to | 2025-10-05👉 GitHub Repo
-
Project mention: Show HN: Instar – Persistent Server for Claude Code with Telegram and Evolution | news.ycombinator.com | 2026-03-17
-
Network-AI
Traffic light for AI Agents and TypeScript/Node multi-agent orchestrator with shared state, guardrails, and adapters for 29 AI frameworks
Project mention: An npm Package for AI Agent Orchestration Just Shipped With Its Front Door Unlocked. Here's What the CVE Actually Reveals. | dev.to | 2026-05-25Network-AI is a TypeScript/Node.js multi-agent orchestration layer. It handles the coordination problem that every team building with multiple agents eventually hits: parallel agents writing to the same shared state, overwriting each other, corrupting context with no error thrown. Network-AI addresses this with a shared blackboard that uses atomic propose-validate-commit locking, HMAC/Ed25519 audit trails, per-agent token budgets, and FSM governance. It plugs into 17 AI frameworks — LangChain, AutoGen, CrewAI, OpenAI Assistants, LlamaIndex, and more — through a local MCP server running on port 3001.
-
kinbot
Self-hosted AI agents with persistent memory, real identity, and collaboration. One process, one SQLite file, zero cloud.
Project mention: Show HN: KinBot – Self-hosted AI agents that build their own web apps | news.ycombinator.com | 2026-03-06Hey HN, I built KinBot because I was frustrated with AI tools that forget everything between sessions.
The core idea: you create "Kins," which are AI agents with persistent memory (vector + full-text search), real identity, and autonomy. They live on your server and remember every conversation.
What makes it different from other agent platforms:
- Mini Apps: Kins can build and serve their own web applications on the fly. Think of it as giving your agent a canvas to create interactive tools, dashboards, or utilities.
- Persistent memory: not just context window tricks, but actual long-term memory with hybrid search across months of conversations.
- Multi-agent collaboration: Kins can talk to each other, delegate tasks, spawn sub-agents.
- Runs anywhere: single process, SQLite, works on a Raspberry Pi. No Kubernetes cluster needed.
- 23 AI providers supported (OpenAI, Anthropic, Google, Ollama, etc.)
Tech stack: Bun + Hono on the backend, React + TailwindCSS on the frontend, SQLite for everything. One Docker command to run it.
I have been using it daily for months as my personal assistant setup. The mini-apps feature is what I find most exciting: instead of just chatting, your agents can actually build things you interact with.
Looking for feedback on: the mini-apps concept, the memory architecture, and whether the self-hosting story is compelling enough. Happy to discuss technical details.
Repo: https://github.com/MarlBurroW/kinbot
-
AgentManager
Conduct autonomous Claude Code agents at scale safely. Human-on-the-loop orchestration platform with kill switch, cost tracking, and inter-agent messaging.
Project mention: ClaudeSwarm rebranded AgentManager with new UI and features | news.ycombinator.com | 2026-02-20 -
This all started as a chaotic weekend project, inspired by Kenton Varda's excellent talk Let's put the AI in lots of little boxes at Connect 2025. I highly encourage you to check out the repository, try the examples, and share your feedback.
-
-
Carnival9
Deterministic agent runtime with explicit plans, typed tools, permissions, and replay. Implements Google DeepMind's Intelligent AI Delegation framework. Named after ELP's Karn Evil 9.
Project mention: Show HN: KarnEvil9, a deterministic AI agent runtime | news.ycombinator.com | 2026-03-05 -
vibes
TypeScript agent framework for building production-grade, type-safe AI applications the pydantic ai way (by a7ul)
Project mention: VibesSDK: Robust AI Agent SDK for TypeScript and Deno | news.ycombinator.com | 2026-03-17 -
qualixar-os
Qualixar OS: The Universal OS for AI Agents. Claw-compatible. 12 topologies, Forge AI team designer, 24-tab dashboard, skill marketplace. PAPER: https://arxiv.org/abs/2604.06392
Project mention: Run Multi-Agent Teams from Claude Code with Qualixar OS (25 MCP Tools) | dev.to | 2026-04-17GitHub: github.com/qualixar/qualixar-os
-
quickbench
🏃 Sovereign Agent Evaluation Framework - Zero cloud dependencies. Local-only, cryptographically signed benchmarks for AI agents. npm run demo = instant evals. (by iamGodofall)
Project mention: I built a local-only eval runner for AI agents (quickbench) | news.ycombinator.com | 2026-03-22 -
capkit
Scoped, time-bound, cryptographically-signed capabilities for AI agents. Zero dependencies. Sovereign by design.
Project mention: I built a 200-line library to stop AI agents from going rogue (capkit) | news.ycombinator.com | 2026-03-22 -
-
Project mention: Show HN: Jin – a machine-readable protocol making internet legible for AI | news.ycombinator.com | 2026-06-04
Github: https://github.com/meetjin/jin
I would really appreciate to know your use case and feedback.
Cheers!
-
reasonix
DeepSeek-native agent framework: Cache-First Loop, R1 Thought Harvesting, Tool-Call Repair. TypeScript + Ink TUI.
Project mention: The boring secret to a cheap AI coding agent — a byte-stable prompt prefix | dev.to | 2026-05-05So I went the other direction. I built Reasonix — same shape as Claude Code or Aider, runs in your terminal, plan mode, tool calls, MCP — but it only talks to DeepSeek, and the entire loop is engineered around one invariant:
-
agentvoy
The universal AI agent platform. Scaffold, configure, guard, and deploy AI agents across 7 frameworks — OpenAI, Anthropic, CrewAI, LangGraph, Google ADK, LlamaIndex, AutoGen. One command. Any model. Deploy anywhere.
Project mention: AgentVoy – The create-react-app for AI agents (7 frameworks, deploy anywhere) | news.ycombinator.com | 2026-05-18
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 agent-framework discussion
TypeScript agent-framework related posts
-
An npm Package for AI Agent Orchestration Just Shipped With Its Front Door Unlocked. Here's What the CVE Actually Reveals.
-
Microsoft Just Shipped MCP Governance for .NET. Here's What It Actually Enforces.
-
The boring secret to a cheap AI coding agent — a byte-stable prompt prefix
-
Show HN: Paracosm – simulate what-if scenarios with AI agents
-
Designing a Hooks System for AI Agent CLIs: 4 Lifecycle Points That Cover Everything
-
Building Autonomous Agent Coding Harness
-
VibesSDK: Robust AI Agent SDK for TypeScript and Deno
-
A note from our sponsor - SaaSHub
www.saashub.com | 8 Jun 2026
Index
What are some of the best open-source agent-framework projects in TypeScript? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | gitagent-protocol | 2,761 |
| 2 | agents | 1,180 |
| 3 | daydreams | 606 |
| 4 | gitagent | 511 |
| 5 | axar | 162 |
| 6 | stoneforge | 152 |
| 7 | AgentOS | 117 |
| 8 | fullstack-langgraph-nextjs-agent | 114 |
| 9 | instar | 65 |
| 10 | Network-AI | 60 |
| 11 | kinbot | 43 |
| 12 | AgentManager | 24 |
| 13 | common-agents | 21 |
| 14 | dagengine | 16 |
| 15 | Carnival9 | 12 |
| 16 | vibes | 12 |
| 17 | qualixar-os | 8 |
| 18 | quickbench | 3 |
| 19 | capkit | 3 |
| 20 | Bopo | 2 |
| 21 | jin | 1 |
| 22 | reasonix | 1 |
| 23 | agentvoy | 1 |
Sponsored
SaaSHub - Software Alternatives and Reviews
SaaSHub helps you find the best software and product alternatives
www.saashub.com