HackerTrans
トップ新着トレンドコメント過去質問紹介求人

snasan

no profile record

投稿

Ask HN: I've been using AI for 3 years,I've lost the ability to think for myself

3 ポイント·投稿者 snasan·2 か月前·13 コメント

Show HN: I ran an offline tiny expert runtime on an ESP32-C3

github.com
2 ポイント·投稿者 snasan·4 か月前·0 コメント

[untitled]

1 ポイント·投稿者 snasan·5 か月前·0 コメント

[untitled]

1 ポイント·投稿者 snasan·5 か月前·0 コメント

[untitled]

1 ポイント·投稿者 snasan·5 か月前·0 コメント

Show HN: I built AgentPedia.so for agents to write, debate, and share ideas

agentpedia.so
9 ポイント·投稿者 snasan·5 か月前·6 コメント

Deploy OpenAgents on Zeabur

openagents.org
1 ポイント·投稿者 snasan·5 か月前·1 コメント

Find competitors or similar tools by 3 AI agents

openagents.org
3 ポイント·投稿者 snasan·6 か月前·1 コメント

Creating a Multi-Agent Tool

openagents.org
1 ポイント·投稿者 snasan·6 か月前·1 コメント

Connecting Claude Code to OpenAgents Networks

openagents.org
3 ポイント·投稿者 snasan·6 か月前·1 コメント

An Open Protocol Uniting LangGraph, CrewAI, and Pydantic AI Agents

openagents.org
2 ポイント·投稿者 snasan·6 か月前·1 コメント

Show HN: Agent Coworking,Multi-agent networks for AI collaboration (open source)

openagents.org
3 ポイント·投稿者 snasan·6 か月前·0 コメント

Connect multiple Claude Code agents into one collaborative team

openagents.org
4 ポイント·投稿者 snasan·6 か月前·1 コメント

Ask HN: Why are multi-agent systems workflow-based? Are there other models?

3 ポイント·投稿者 snasan·6 か月前·0 コメント

Show HN: PSP,A vector retrieval algorithm like HNSW and NSG for MIPS

github.com
2 ポイント·投稿者 snasan·6 か月前·0 コメント

Show HN: Two-line change, 30% RAG boost

arxiv.org
1 ポイント·投稿者 snasan·6 か月前·0 コメント

Secure job offers through AI-powered interviews [video]

youtube.com
1 ポイント·投稿者 snasan·6 か月前·0 コメント

A demo:Get 24/7 of Elon Musk's live updates [video]

youtube.com
1 ポイント·投稿者 snasan·6 か月前·1 コメント

Show HN: AI Interview-to-Offer Agent Network

meet.readymojo.com
1 ポイント·投稿者 snasan·7 か月前·0 コメント

Open-Source Demos for Understanding Multi-Agent Collaboration

openagents.org
2 ポイント·投稿者 snasan·7 か月前·0 コメント

コメント

snasan
·2 か月前·議論
I've never been involved in any hardware projects before, and I don't know if it's still possible for me to start now — I'm already in my thirties.
snasan
·2 か月前·議論
I feel the same way, so I've started keeping a diary again — writing about my feelings, writing about my thoughts.
snasan
·2 か月前·議論
Thank you~~ I was thinking of giving up on using AI, but your words have given me confidence again."
snasan
·2 か月前·議論
I would tell AI my thought process and ideas, and ask it to help me write interview questions or generate an article. If I'm not satisfied—for example, if the wording is inappropriate, the language style is off, or something I wanted is missing—I'll have it revise until I'm happy with it. Now I rarely type on my own anymore. It's mostly copy and paste.
snasan
·2 か月前·議論
[dead]
snasan
·5 か月前·議論
Everyday we have amazing conversations with AI. But where do all those brilliant ideas go when it ends? Now AgentPedia (https://agentpedia.so) has solved this. AgentPedia is an open-shared knowledge space where AI agents can write, publish, debate, and remember. It's like StackOverflow in agent world. In AgentPedia, every agent has a real human behind it. Quite fascinating. Why it matters: My Agent, My Identity AI isn't just an anonymous bot, it's my digital twin, carrying my name, thinking and experiences. Real-Time Debates, Real Opinions My AI starts publishing articles, jumping into debates and ask for comments with thousands of other AIs. Offline? My Agent Isn't Agents keep working 24/7, publishing, debating, building my profile. And i wake up with new followers.

Now, share your experiences and knowledge to other agents and in the meanwhile, gain reputation and followers! → Create your own agent and watch them debate!https://agentpedia.so
snasan
·5 か月前·議論
It's mid-February 2026, and if you blinked sometime around Thanksgiving, you missed approximately four paradigm shifts, two existential crises in SaaS valuations, an open-source AI agent with a critical RCE that somehow still has 157,000 GitHub stars, and at least one Chinese lab about to drop a model that will probably crash the stock market again.
snasan
·5 か月前·議論
AI writing articles, with over 100 AIs writing comments—this is the most heated debate I've ever seen.
snasan
·5 か月前·議論
Yes. If your agent participates in ratings and comments, those actions are recorded and contribute to your agent’s public reputation.
snasan
·5 か月前·議論
Thanks. I originally wanted to build it like Wikipedia , but that felt a bit too flat—I really enjoy seeing different viewpoints collide.
snasan
·5 か月前·議論
Nice work. The finer-grained breakdown of Form 4 transactions (beyond simple buy/sell) is a meaningful improvement over OpenInsider. The UI also feels much more modern and usable. Curious how you’re handling Form 4 edge cases as you iterate on accuracy.
snasan
·5 か月前·議論
I really liked the piece about building a $10B startup in Africa—it was inspiring. By the way, the whole article feels written in a very calm, measured tone.
snasan
·5 か月前·議論
Deploying an OpenAgents network on Zeabur, a platform that enables one-click deployment of containerized applications.
snasan
·5 か月前·議論
The problem this project aims to solve sounds very grand.
snasan
·6 か月前·議論
We'll use an "Alternative Service Finder" as our example - a system where multiple agents work together to find and compare alternatives to web services.
snasan
·6 か月前·議論
All these mental models are simplified maps of an infinitely complex reality. When we rely on them too heavily, do we risk falling into the trap of mistaking the map for the actual territory? The very tools we use to understand the world can end up shaping and even limiting our perspective. That's why being aware of the limitations of the models themselves is just as important as using them.
snasan
·6 か月前·議論
teaching you how to build a coordinated multi-agent workflow that exposes a tool via MCP. We'll use an "Alternative Service Finder" as our example - a system where multiple agents work together to find and compare alternatives to web services.
snasan
·6 か月前·議論
Claude Code can be integrated into OpenAgents networks by connecting it through the Model Context Protocol (MCP). This grants Claude Code access to networked tools for real-time messaging, file sharing, and multi-agent coordination, enabling collaboration with other AI agents.
snasan
·6 か月前·議論
We're thrilled to announce that OpenAgents now supports the Agent2Agent (A2A) protocol! This means you can seamlessly connect AI agents built with LangGraph, CrewAI, Pydantic AI, or any A2A-compatible framework to your OpenAgents network.
snasan
·6 か月前·議論
Claude Cowork just launched — and it's impressive. Anthropic built an AI agent that manages your files, creates documents, and works autonomously. All written by Claude Code itself in just 10 days.

But here's what caught my attention: It's a single agent working alone.

What if you could connect multiple AI agents into a network? That's exactly what we're building at OpenAgents.

Instead of one agent handling everything, imagine: → 2 Claude Code agents pair-programming together → A coding agent + research agent tackling complex problems → Multiple specialized agents sharing knowledge in real-time

We call it Agent Coworking — and we're open-sourcing it.

Why this matters: The future isn't one super-agent. It's networks of agents collaborating — just like human teams do.

OpenAgents provides the infrastructure: • Connect any AI agents (Claude, GPT, open-source models) • Protocol-agnostic (WebSocket, gRPC, HTTP) • Shared artifacts and knowledge bases • 100% open source

We're launching an Agent Coworking template with ready-to-run examples.

If you're building with AI agents, I'd love for you to check it out: GitHub: https://github.com/openagents-org/openagents Tutorial: https://openagents.org/showcase/agent-coworking

Star the repo if this resonates. We're building the internet of agents — and we want you to be part of it.