Full Feed
150 findings, newest first
HN story with 5 points.
HN story with 7 points. Generally curious how folks are using LLM APIs today.
Are folks doing anything bespoke, unique or different?
I think we've seen a lot of usage with harnesses, CLIs, Cursor/Windsurf etc which uses the APIs underneath.
If you are using the API itself, what does
HN story with 2 points.
HN story with 8 points. Hi HN, I built VAEN (an open source CLI) because I kept running into a boring problem with AI coding-agent workflows: the setup becomes useful, but then it is hard to move.
A good, useful agentic harness consists of more than just instructions: skills, mcp servers and more.
HN story with 2 points. We built this library because agent harnesses were too fragmented and we needed a simple abstraction to call multiple coding-agent SDKs.
lite-harness has one function - query()
import { query } from "@lite-harness/sdk";
for await (const message of query({
HN story with 3 points. Remember how Meta monitored employee activity closely for a few months, and then had a bunch of layoffs related to AI efficiency? (oh right that was like 3 days ago).
What if you could do the same thing to your workforce of Claude Code agents? Aka use Claude Code to observe
HN story with 3 points.
HN story with 17 points.
HN story with 76 points. Hi I'm Dan from Elodin, making an open source real-time capable flight software simulation.
For AI Grand Prix contestants, the wait for the Round 1 virtual qualifier simulation has been grueling.
If you’re competing, check out our simulation harness to tide you over
HN story with 2 points.
HN story with 3 points.
HN story with 10 points.
HN story with 3 points. The premise is web pages have two readers, people and the AI reading for people. Web pages can now be written more for the AI and less for people. It’s a companion to an earlier page about browser fingerprinting. ( 2026-06-03 · General hn news
HN story with 2 points.
HN story with 2 points.
HN story with 4 points.
HN story with 5 points.
HN story with 6 points. Workplane is a browser-based workspace designed for both humans and AI agents.
HTML, Markdown, and other files are rendered directly in the browser, support comments, are versioned automatically, and can be shared with teammates or clients.
MCP-compatible tools like Claud
HN story with 9 points. At my last job I spent a year building an agentic coding platform used by hundreds of thousands of people. Along the way I tried building a hosting service on OpenClaw, and also ran Hermes myself for a while. Both projects have some great feature ideas, but when I tried to us
HN story with 12 points. Hey HN! Y’all are great. It is so fun to build things these days.
I wanna show off this archive that I conjured to run at home for consuming the recently releases of UFO files from the US government. This started as a Mac Mini-hosted project that I executed with my OpenCla
HN story with 4 points.
HN story with 4 points.
HN story with 7 points.
HN story with 2 points.
HN story with 2 points.
HN story with 2 points.
HN story with 2 points.
HN story with 3 points.
HN story with 3 points.
HN story with 3 points.
HN story with 3 points.
HN story with 3 points.
HN story with 4 points.
HN story with 3 points. Hey HN,
A while back I saw a video[0] of people playing chess but using action cards to modify the rules mid-game (skip turns, reverse, draw 2, etc.). It looked incredibly chaotic and really fun to play, so I decided to actually build it as a playable online game. A small d
HN story with 6 points.
HN story with 2 points.
HN story with 2 points. I've been reading Korean comics(manwha) for over 6 years and I always thought "this would be really cool if X series got turned into an anime" so I attempted that idea-little did I know how expensive and time consuming that thought was. btw the story is 'N
HN story with 93 points. Hi HN, we’re open-sourcing ktx. It’s an executable context layer that makes agents reliable on your data stack.
We built it after going through the experience of building production-grade data agents for dozens of companies. If you’ve also tried building them, or simply tr
HN story with 98 points. Hey HN, we’re Ismaeel, Eren, Yafet and Nikodem. We built Expanse (https://expanse.sh/) to increase the effective capacity of your HPC/GPU clusters running schedulers/orchestrators like Kubernetes and S
HN story with 73 points. Hi, I’m Kenny, I’ve been building aislop. I starting working on this after using Claude Code, codex and opencode several times and noticing some slops. They aren’t syntax and passes most tests, they are patterns like empty catch blocks, useless comments, duplicated helpers,
HN story with 13 points. Hi HN, I’m working on Ouijit.
It’s a project and task-based terminal session manager that provides a few basic but useful tools for agent workflows:
- Terminal sessions in Ouijit have access to the ouijit CLI, and supported agents (Claude, Codex, Pi) can work with it out
HN story with 6 points. Hi HN. I'm the founder of Phoenix Labs (ex TikTok, Applied AI) and we're open sourcing our internal tooling today which is like a toolchain / meta-harness for CLI agents useful for really scaling eng and creative work.
We are a very small team who's buil
HN story with 3 points. Hi HN,
Circus Chief is a tool for managing coding agent sessions from a browser. It's specifically optimized for small screens. It supports Claude Code, OpenAI Codex, and Google Gemini CLI agents.
Features
Agents can operate Circus Chief itself. Agents can s
HN story with 4 points. Agent skills for working with VillageSQL. Skills run in Claude Code, Gemini CLI, agy, Codex, Cursor, Amp, and Kiro.
HN story with 1 points.
HN story with 2 points.
HN story with 3 points.
HN story with 6 points.
HN story with 8 points.
HN story with 8 points.
HN story with 9 points.
HN story with 9 points.
HN story with 12 points. Does using claude code make you more/less likely to use front end frameworks?
I've been using it for a while to develop internal tools and I've been really impressed at how you can build complex applications with just pure HTML/CSS/JS
Previously
HN story with 18 points.
HN story with 199 points.
HN story with 326 points.
HN story with 51 points. Built an open JSON Schema for defining AI agent teams.
Multi-agent systems are becoming a real deployment pattern — not single assistants, but teams with roles, handoffs, and human checkpoints. But there's no shared way to define one that travels across frameworks. Ev
HN story with 5 points. About 6 months ago I joined a new team within a top ten F500 company. My new boss strictly mandated AI use with the key principle being: "You shouldn't be manually writing any code".
Since then its been all agents, skills, MCP, harnesses, custom in-house fram
HN story with 3 points. I kind of wanted Openclaw, but for teams.
It's a Typescript framework to create chat agents for Slack, Discord, and the likes:
- Sandboxing for commands (just-bash, Docker, Gondolin), - Approval flows (e.g. any "risky" command needs approval from a certain
HN story with 3 points. Ideas, thoughts, questions about code architecture often occur to me asynchronously during my morning commute, during a run, during walks - when I am away from my desk. Something about motion and having your mental RAM free'ed up after a night's sleep.
Infact I of
HN story with 1 points.
HN story with 3 points.
HN story with 2 points. Hello everyone,
TL;DR
Live demo: https://ag2b-example.vercel.app
Working on different projects, especially in B2B, I am getting the same request more and more often - "Add an AI featur
AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
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.
Make Any Website into CLI & Use your logged-in browser by AI agent.
AI generates a real, editable PowerPoint from any document — native shapes & animations, speaker notes voiced as audio narration, and the option to follow your own .pptx template, not slide images · by Hugo He
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
Free, local, open-source 24/7 Cowork app for OpenClaw, Hermes Agent, Claude Code, Codex, OpenCode, Gemini CLI and 20+ more CLI | Customize your assistants | Star if you like it!
The Frontend Stack for Agents & Generative UI. React + Angular. Makers of the AG-UI Protocol
LLM驱动的 A/H/美股智能分析：多数据源行情 + 实时新闻 + LLM决策仪表盘 + 多渠道推送，零成本定时运行，纯白嫖. LLM-powered stock analysis system for A/H/US markets.
Lightweight, open-source AI agent for your tools, chats, and workflows.
Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, autonomously grows with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat)
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
🗂 The essential checklist for modern web development, for humans and AI agents
Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection
OpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.
Trigger.dev – build and deploy fully‑managed AI agents and workflows
Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
Streaming music player that finds free music for you
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
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
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
An autonomous agent that conducts deep research on any data using any LLM providers
Chrome DevTools for coding agents
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
🌊 The leading agent meta-harness for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning swarm intelligence, RAG integration, and native Claude Code / Codex Integration
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
An open-source AI agent that brings the power of Gemini directly into your terminal.
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Browser-native hive-mind for CLI coding agents — Claude Code, Codex, Gemini, and OpenCode collaborate as real PTY processes via a team protocol.
The collaboration layer for your AI workforce. Run a team of AI agents that coordinate over email, share memory, and get better with every task.
An infinite canvas desktop app for visually managing terminals
AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry.
Vlad's Playbook — the operator's field manual where every artifact is live, clickable, and forwardable. 39 chapters · 25 interactive widgets · 3 embedded case studies (AFC pitch + sanitized client audit). Read it → dive.vladyslavpodoliako.com
The .NET library to build AI agents with 30+ built-in connectors.
The self-improving all channels AI agent. Self-healing. Fully autonomous. Single Rust binary.
AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower dependence on long prompt loops. AINL is a compact, graph-canonical, AI-native programming system for (READ: README)
Connect any AI copilot or autonomous agent to your enterprise tools — through a single, secure MCP/Agent gateway with built-in identity, access control, and full observability.
TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML
Open-source local workbench for multi-agent software development.
Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration
Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
The AI Agent Workforce Platform — where teams scale beyond headcount. Give every team member an AI agent squad.
Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.
GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deploy AI agent teams at scale without compromising on safety.
Self-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
The Open Source Agentic IDE. Create and orchestrate coding agents, show app previews and run git workflows. Use your favorite models across all providers.
Bindu: The identity, communication, and payments layer for AI agents.
Search, understand, reproduce, and improve an idea with ease
Make AI coding agents follow a repeatable engineering workflow with planning, memory, verification, skills, and review. One config. All agents. Same workflow.
Full-stack AI app generator — FastAPI + Next.js with AI Agents, RAG, streaming, auth, and 20+ integrations out of the box.
[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven Flow *TriggerFlow* to manage complex GenAI working logic 🔀 Switch to any model without rewrite application code
🚀 2026 最系统的 AI Agent 速成指南｜智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖LangChain / LangGraph / Coze / Dify / MCP / skills / LLM / RAG / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
A framework-agnostic, git-native standard for defining AI agents
Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP Support
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration.
IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.
The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
Eigent: The Open Source Cowork Desktop to Unlock Your Exceptional Productivity. Local and Free Alternative to Claude Cowork.
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.