HN faisalishfaq 15d ago

LoopFlow – design loops that prompt your coding agent

LoopFlow: YAML-based system for designing agentic loops with Claude that iterate until verification gates pass, enabling autonomous code agents.

HN Floukie 15d ago

Magpie-Search, THE BEST SEARCH ENGINE FOR LLM'S

Search engine optimized for LLM queries. Limited technical details provided.

HN ryanhughes 15d ago

Show HN: Crossbeam-CLI – Connect Claude to Crossbeam without the enterprise tier

crossbeam-cli: open-source tool connecting Claude LLM to Crossbeam API without enterprise tier, enabling natural language queries on account data.

HN dmarcos 15d ago

Cursor for iOS

iOS app for code editor. Minimal details provided, likely developer tool but insufficient content.

HN matt_d 15d ago

TraceLab: Characterizing Coding Agent Workloads for LLM Serving

TraceLab characterizes coding agent workloads for optimizing LLM serving infrastructure.

HN thinking-nick 15d ago

Show HN: AST-guard A gradient-immune structural guard against RL reward hacking

AST-guard: deterministic gate detecting structural reward hacking in RL-trained code generation models. Research artifact for code model safety.

HN krussikas 15d ago

An interactive PyTorch debugger that looks deep inside your neural net

PyTorch debugging tool for visualizing neural network activations, gradients, and receptive fields during training. Interactive interpretability tool.

HN realitydrift 15d ago

How Reality Gets Lost Inside Organizations

Essay about how organizations lose touch with reality through abstraction and metrics. Management philosophy with no technical content.

HN httppp 15d ago

Local-first SSH/SFTP/Serial client for infrastructure engineers

Local-first SSH/SFTP/Serial client for infrastructure with peer-to-peer session sharing. Infrastructure tool not AI-related.

HN vanilagy 15d ago

TurboRes, an fast WASM Apple ProRes decoder (2x faster than FFmpeg)

WebAssembly Apple ProRes video decoder library in Zig/TypeScript. 2x faster than FFmpeg. Media processing tool unrelated to AI interests.

HN immu4989 15d ago

Does DSPy prompt optimization weaken adversarial robustness?

Research measuring how DSPy prompt optimization affects adversarial robustness against prompt-injection attacks in LLM agents using AgentDojo.

HN williamcotton 15d ago

The Discoverable Evidence of AI-Assisted Software Porting

Case study examining artifacts left by AI code generation (Codex) during software porting tasks.

HN levyathan 15d ago

Relay – open-source coding agent for non-mainstream/Chinese LLM providers

Open-source coding agent supporting non-mainstream and Chinese LLM providers like DeepSeek.

HN punnerud 15d ago

Show HN: Rust / Red Alert inspired WASM game in the browser (open source)

Open source Rust/WebAssembly game inspired by Red Alert. Game development project unrelated to AI/ML interests.

HN chambertime 15d ago

Metasearch Tooling for Agents

Metasearch MCP server for agents built on Dogpile search with metered API integration.

HN speckx 15d ago

What LLMs are doing to conference programs

Discussion on impact of LLM-generated content on academic conference program submissions.

HN ameshkov 15d ago

Show HN: MCP-compress-router – MCP Compressor

MCP-compress-router reduces token overhead from multiple MCP servers by selectively routing tools.

HN hunterx 15d ago

Show HN: Create and Maintain Filesystem Structures for LLMs [v1.0.13 Out]

Tool for creating and maintaining filesystem structures optimized for LLM context.

HN bookofjoe 15d ago

Recognising and mitigating LLM Pollution in online behavioural research

Research on detecting and mitigating LLM pollution in online behavioral research studies.

HN muthuishere 15d ago

Show HN: Toolnexus for .NET – MCP and agent skills as tools for any LLM

Toolnexus .NET library integrating MCP and agent skills as tools for any LLM.

HN chelbi 15d ago

Show HN: DriftGuard – response drift detection for LangGraph agents

DriftGuard detects when LangGraph agents drift from intended domain without ground-truth labels.

HN yu3zhou4 15d ago

AMD contributes their GPU support to tiny-vLLM

AMD contributes GPU support to tiny-vLLM for improved LLM inference performance.

HN luca-sctr 15d ago

Using Aspect-Oriented Programming to Record DRL Agents' Data

PEAK framework uses aspect-oriented programming to automate data recording for deep reinforcement learning agents in game development playtesting.

HN justanything 15d ago

Ask HN: How to use AI to learn faster but effectively?

Discussion thread on using LLMs for learning despite concerns about reliability.

HN ivrr 15d ago

Show HN: Agentic Orchestrator, a TUI for long-running coding agents

TUI tool orchestrating long-running coding agents through full engineering workflow with deterministic phase gates.

HN r13i 15d ago

Show HN: Hail.so – Send and receive emails, calls, SMS via a single MCP/API/CLI

Open-source MCP server/CLI/API for unified email, SMS, and phone integration with LLM providers and AI agents. Production-tested voicebot tooling.

HN syumei 15d ago

I built an anime-style UI for watching AI coding agents review each other's code

Anime-style UI for visualizing AI coding agents reviewing each other's code.

HN TheLuigiplayer 15d ago

Show HN: Llama Legends

Browser-based card game with llama-themed cards, idle mechanics, and auto-battling arena.

HN OnlineInference 15d ago

CoreWeave ARIA: AI Research and Iteration Agent

Stub entry about CoreWeave ARIA AI Research and Iteration Agent with no content.

HN shubh_sidhu 15d ago

Show HN: I built Exfault, agentic mobile app pentesting tool

Exfault: autonomous AI agents for Android app penetration testing using static/dynamic analysis with adb, jadx, apktool and reverse engineering tools.

HN kekqqq 15d ago

Browser CLI for Agents

Standalone Playwright CLI tool for AI agents to control real Chromium browsers with structured commands, achieving 82% task success at $0.22/task.

HN aubanel 15d ago

A playbook to rank #1 of the day on ProductHunt

ProductHunt ranking guide with minimal engagement.

HN conchaestrada 15d ago

Show HN: ZUSE – 69x causal compression of a period-15 CA oscillator

ZUSE agent discovers causal laws in cellular automata using deterministic policy-driven loops without LLMs, achieving 69x compression of period-15 oscillator.

HN saba-ch 15d ago

Show HN: Create agents that grow to fulfill their purpose

Wolli framework creates self-building long-running agents that customize themselves around assigned purposes with integrations.

HN mooreds 15d ago

High AI security confidence may signal higher MSSP risk

Stub entry about AI security confidence and MSSP risk.

HN softwaredoug 15d ago

Does US AI Gatekeeping Hand China the Open-Source Edge?

Stub entry questioning whether US AI export restrictions give China advantages in open-source AI.

HN htfy96 15d ago

VNote: A pleasant note-taking platform in native C++

Qt-based open source note-taking application with Markdown support and notes management.

HN mezark 15d ago

What happens when you run a CUDA kernel?

Technical deep-dive into CUDA kernel execution, tracing vector addition from code to hardware-level operations.

HN vicpitic 15d ago

UGC Agent – Run AI agents that find UGC creators

UGC Agent: AI tool discovering Instagram/TikTok creators, enriching profiles, scoring against ICP, and exporting leads with contact information.

HN ilreb 15d ago

PostgreSQL-Compatible Databases for AI at Scale

PostgreSQL-compatible databases for AI infrastructure scaling; 83% of leaders expect data infrastructure to fail within 24 months without upgrades.

HN javatuts 15d ago

JSON Handbook

Practical guide covering JSON reading, writing, validation, debugging, security, and transformation.

HN benwerd 15d ago

A right-wing media chain tried to replace 47 newspapers with AI. They all died

Media chain's attempt to replace 47 newspapers with AI-generated content failed.

HN LorenDB 15d ago

DankMaterialShell

Desktop shell for Wayland compositors replacing waybar, swaylock, and other components.

HN eigenBasis 15d ago

Model Context Protocol Explained in 3 Levels of Difficulty

Model Context Protocol standardizes how AI applications connect to external tools and data sources, addressing LLMs' knowledge cutoff limitation.

HN gautamdhameja 15d ago

Show HN: Sonar, local cited codebase briefings tailored to your role

Sonar generates local-first codebase briefings for non-technical stakeholders without frontier model subscriptions.

HN mday27 15d ago

Some thoughts from inside the AI bubble

Author shares workplace observations on AI utility for software development, noting developers accomplishing previously infeasible tasks at scale.

HN amichail 15d ago

Ask HN: Why don't bug reporting systems provide workarounds as rewards to users?

Suggestion for bug reporting systems to provide workarounds as incentives for quality reports.

HN fognitix 15d ago

Show HN: Fognitix – AI browser with parallel autonomous agents on the browser

Fognitix: autonomous browser with parallel AI agents executing up to five concurrent tasks simultaneously; vision-native interaction with synthesized results.

HN zernst3 15d ago

AI Writing Code Makes Premature Optimization Viable

AI code generation enables premature optimization strategies previously impractical; developer shares experience with tech debt resolution through AI-assisted refactoring.

HN alexkarpathy 15d ago

Show HN: Running a vision model on every screenshot on-device

Screenmind runs vision model locally on screenshots for privacy-first alternative to Microsoft Recall, supporting search and chat over screen history.