3/3/2026
Show HN: I built an expense tracker where no data ever touches a server
Privacy-focused expense tracker using IndexedDB with no server-side data storage, syncing between devices locally.
3/3/2026
Optimizing Delta-Step on the GPU
Technical post on GPU optimization of Delta-Step shortest-path algorithms using CUDA, ROCm, SYCL, and OpenCL.
3/3/2026
Show HN: Use Codex/Claude Code as your personal financial assistant
AI agent-based personal finance assistant using Claude/Codex with Python environment for custom calculations, visualizations, and spending simulations.
3/3/2026
LLMs can unmask pseudonymous users at scale with surprising accuracy
Research showing LLMs can unmask pseudonymous users at scale with high accuracy, privacy implications for LLM applications.
3/3/2026
Show HN: Corepoints – Screen Candidates for AI Proficiency at Scale (Demo Run)
Corepoints: platform for screening candidate AI proficiency at scale with metrics on hallucinations, prompting quality, and token usage.
3/3/2026
Show HN: VellaVeto – Fail-closed runtime proxy for MCP tool calls, in Rust
VellaVeto: Runtime security proxy for AI agent MCP tool calls. Enforces policies on paths/domains/actions with <5ms latency and 20+ threat detection layers using formal verification.
3/3/2026
Show HN: I got tired of rewriting webhook verification for every provider
TypeScript SDK that standardizes webhook signature verification across 20+ providers (Stripe, Clerk, Shopify, etc.) with support for Express, Next.js, and Cloudflare Workers.
3/3/2026
Show HN: Axe – A CLI for running single-purpose LLM agents
Axe: CLI tool for running single-purpose LLM agents from command line.
3/3/2026
Show HN: ChatGPT gets your prompt before you hit send
Incomplete Show HN post about browser extension previewing ChatGPT prompts.
3/3/2026
Show HN: KrunAI – A CLI tool for running AI agents inside microVM sandboxes
CLI tool for sandboxed execution of AI agents in microVM environments.
3/3/2026
Training neural networks on Apple Neural Engine
Reverse-engineered method for training neural networks directly on Apple Neural Engine via private APIs without CoreML, Metal, or GPU.
3/3/2026
Accessibility.md
ACCESSIBILITY.md is an open format for documenting project accessibility posture and automation, designed for discovery by humans and AI coding agents.
3/3/2026
Show HN: Reflectt-node – AI agents who built our own task board. Here it is
Incomplete Show HN post about AI agents building task management application.
3/3/2026
Zen of AI Coding
Incomplete/stub article on AI coding best practices.
3/3/2026
Show HN: Qast – Cast anything (files, URLs, screen) to any TV from the CLI
Qast is a CLI tool that casts files, URLs, and screens to TVs, handling codec compatibility across different TV models.
3/3/2026
Show HN: Reconstruct any image using primitive shapes, runs in-browser via WASM
WASM port of fogleman/primitive that reconstructs images using primitive shapes via hill-climbing algorithm, running entirely client-side in the browser.
3/3/2026
I built a full-stack web app in a weekend. I'm a GP, not a developer
GP doctor built a full-stack web app with PostgreSQL, admin panel, and 300+ Irish language quiz questions deployed in a weekend.
3/3/2026
Learning with AI
Blog post discussing concerns that LLM reliance prevents critical thinking and learning in students.
3/3/2026
DevSwarm – Virtualize Git branches into concurrent development for AI agents
AI-native development environment manager virtualizing Git branches for concurrent human-AI agent collaboration.
3/3/2026
The halting problem in AI coding
Essay exploring connections between the halting problem from computability theory and challenges in AI coding systems.
3/3/2026
Show HN: Kiln – WebGPU-native out-of-core volume rendering for multi-GB datasets
Kiln is a WebGPU-based volume renderer with out-of-core streaming for visualizing multi-GB datasets in the browser without downloading full data upfront.
3/3/2026
LLM needs a grandmother to prevent knowledge collapse
NBER paper analyzing knowledge collapse risk in AI systems, argues for overlapping generations model to prevent degradation.
3/3/2026
Show HN: I built a 3D engine that turns PDFs into playable study worlds
3D engine that procedurally generates interactive study worlds from PDF documents using spatial memory techniques.
3/3/2026
Show HN: Oath – prove a human authorized each action before your AI agent acts
Open protocol for cryptographic verification of human authorization in AI agent actions, local-first and offline-capable.
3/3/2026
Too Use: The Bridge Between Software Engineering and Agentic AI
Framework bridging software engineering and agentic AI, moving beyond prompt engineering to deterministic system integration.
3/3/2026
Show HN: Persistent Agent Framework – Self-Correcting AI Agents on Claude Code
Open-source persistent agent framework for Claude enabling multi-session memory, autonomous jobs, and self-correcting behavior.
3/3/2026
Show HN: FetchPrompt – Manage LLM prompts outside your code with a REST API
FetchPrompt is a prompt management platform for versioning, testing, and fetching LLM prompts at runtime via REST API without code redeployment.
3/3/2026
Show HN: SignalKit: Real-time audio DSP in pure Swift, zero dependencies
SignalKit is a pure Swift real-time audio DSP toolkit with zero dependencies for CoreAudio and AVAudioEngine processing on Apple platforms.
3/3/2026
Show HN: Open-sourced AI Agent runtime (YAML-first)
Open-source YAML-first AI agent runtime with policies, cost tracking, observability, and governance for production workloads.
3/3/2026
Show HN: I built a proxy that cuts LLM costs 40-60% – no AI involved
Proxy service that compresses prompts to reduce LLM API costs by 40-60% without modifying LLM behavior.
3/3/2026
Show HN: Self-Protecting Files for the Agentic Era
Honeycake embeds encryption, access policies, and audit trails into files themselves to protect data moved by AI agents across workflows without explicit approval.
3/3/2026
Show HN: PrivacyShield – Mask your PII before it reaches ChatGPT/Claude
PrivacyShield is a Chrome extension that detects 15+ PII types and masks them before sending to ChatGPT/Claude, running entirely locally with no server backend.
3/3/2026
Show HN: Learnprints – a full learning OS I built solo on nights and weekends
Learnprints is a learning OS built solo that combines structure with AI chatbots to improve knowledge retention over traditional tools like Anki or Notion.
3/3/2026
Ask HN: How do agencies price projects when AI increases productivity and costs?
Discussion thread asking how agencies should price projects when AI tools increase productivity but add API/compute costs. Community Q&A, no technical content.
3/3/2026
Show HN: MCP server that timestamps every web extraction for AI agents
FreshContext is an MCP server that timestamps web extractions for AI agents, addressing hallucination about data recency with retrieved_at and freshness_confidence metadata.
3/3/2026
Show HN: Evidra – a fail-closed MCP guardrail for AI infrastructure ops
Evidra is a fail-closed MCP guardrail tool for AI infrastructure operations. Provides safety controls for AI agent deployments.
3/3/2026
Numinals – Certified prime numbers as identity tokens for AI bots
Proposes using certified prime numbers as identity tokens for AI bots. Unclear technical implementation or practical application.
3/3/2026
Rtk – reduce up to 90% of CLI noise and save agent tokens
CLI tool that reduces noise in command output by up to 90%, optimizing token usage for AI agents.
3/3/2026
Show HN: ReleasAI – Paste Git commits, get polished release notes in <1s
ReleasAI converts git commit logs into polished release notes using Groq's LLM, supporting multiple formats (GitHub, npm, Slack) with no signup required.
3/3/2026
Show HN: Ablo - AI slides without the generic look or layout restrictions
AI slide generation tool offering layout flexibility and customization beyond template-based competitors.
3/3/2026
I Spent $120 Trying to Make an AI Vertical Drama About Cats. It Was a Disaster
Personal account of attempting to create AI-generated vertical drama content, describing production challenges and costs.
3/3/2026
Show HN: Construct Computer – Agentic Cloud OS for Daily Work
Agent-native cloud OS with persistent autonomous agents handling business tasks via integrations with SaaS ecosystem.
3/3/2026
Finding Peaks with SIMD
Peaks.jl Julia package optimization using SIMD for peak-finding algorithms, achieving faster performance through vectorization techniques.
3/3/2026
How to combat Claude's code duplication, ranked from least to most AI-native
Analysis of code duplication issues in Claude Opus 4.6, identifies library reuse problems and proposes solutions.
3/3/2026
Show HN: Core Rth. A governed AI kernel for engineers who don't trust their LLMs
Core Rth is a governed AI kernel allowing engineers to safely run LLM agents by treating all actions as proposals requiring approval before execution.
3/3/2026
Show HN: PDFBolt – HTML to PDF API with Git-like template versioning
PDFBolt is an HTML to PDF API with Git-like template versioning for managing layout changes without code redeploys.
3/3/2026
How is hardware reshaping LLM design?
Title only, no content. Likely article about hardware impact on LLM design.
3/3/2026
Show HN: My API was leaking its full database schema. I found out by accident
Brakit is an open-source developer tool that monitors AI-generated code for security issues, N+1 queries, and PII leaks via MCP integration with Claude.
3/3/2026
Show HN: Vynix – Mobile app with 100 AI models for image/video/audio generation
Vynix is a cross-platform mobile app aggregating 100+ AI models for image, video, audio generation and LLM chat with credit-based pricing.
3/3/2026
Anthropic's AI model Claude gets popularity boost after US Military feud
Claude AI model gains app store popularity after Pentagon blacklisting over ethics concerns.