26d ago
Free AI Video Generators in 2026: What Works
Roundup of free AI video generation tools. Not focused on agents, research, or development tools.
26d ago
Show HN: Rac-delta – open protocol for differential dir sync (Rust/Node SDKs)
Open protocol for differential directory synchronization with Rust/Node SDKs for game launcher platform.
26d ago
Attention Is All You Need, but All You Can't Afford – Hybrid Attention
25.6M parameter Rust-focused language model with byte-level training exploring hybrid attention mechanisms.
26d ago
Show HN: AgentLint – ESLint for your coding agents
Linting tool for coding agents that detects context drift and validates AGENTS.md alignment with codebase.
26d ago
Show HN: 100 days running an AI agent – what behavioral drift looks like
Research on behavioral drift observed in long-running autonomous AI agents over 100 days. Empirical findings on agent behavior changes.
26d ago
CLI that gives AI agents structured SEO data for any URL – SGNL
CLI tool providing structured SEO data to AI agents for any URL. Limited technical information provided.
26d ago
Show HN: A social feed with no algo where communities decide what gets seen
Social media platform with community-driven feed instead of algorithmic ranking.
26d ago
Show HN: An open source CI/CD action to audit and fix AI generated UI code
Open-source GitHub action for auditing and fixing AI-generated UI code in CI/CD pipelines. Uses browser testing to verify generated code and autonomously pushes fixes.
26d ago
Copilot CLI can now ask a second model to critique the first
Feature for Copilot CLI allowing second model to critique first model output. Minimal details provided.
26d ago
AI agents that teach, debate and quiz you in real time
AI agents for educational tasks including teaching, debating, and quizzing. No technical details provided.
26d ago
Scriba – an open source agent that turns your voice into a knowledge base
Open source voice agent that builds persistent knowledge graphs from recordings with offline and cloud STT options.
26d ago
Extended Thinking Is Load-Bearing for Senior Engineering Workflows
Analysis of extended thinking in Claude across 17,871 thinking blocks and 234,760 tool calls in coding workflows.
26d ago
Show HN: The AI Software Factory
Security-focused development environment for using Claude safely with devcontainers. Addresses issues like file removal and email access by treating humans as firewall.
26d ago
Show HN: I built an MCP for finding SWE jobs
MCP tool integrating job search database with LLM for natural language queries on software engineering positions.
26d ago
Show HN: Letting an LLM write robot programs
Natural language interface using LLM to generate robot programs with MuJoCo browser demo and open code.
26d ago
I ran an AI pentester on a vibe-coded quiz app and found 22 vulnerabilities
Multi-agent security testing framework using specialized agents and tools. Finds vulnerabilities through chaining attacks, supports multiple LLM backends, achieves 96% recall on OWASP tests.
26d ago
Don't Write Like AI (1 of 101): "It's Not X, it's Y"
Essay critiquing common AI writing patterns and contrastive structures. Not technical or development-focused.
26d ago
Show HN: Skrun – Deploy any Agent Skill as an API (open source)
Open source framework to deploy agent skills as APIs with multi-model support and stateful execution.
26d ago
Greyline: We Built a Counter-Agent to Stop AI Agents from Looting Your API
Tool to detect and prevent AI agents from abusing APIs. Minimal details provided.
26d ago
Show HN: ZeroID – Open-source identity and delegation for autonomous agents
Open-source identity and credential system for autonomous agents. Provides short-lived credentials, delegation, attestation, and revocation using OAuth 2.1 and SPIFFE standards.
26d ago
AI "Guardrails" Are Just Suggestions
Analysis of security vulnerabilities in LLM guardrails and prompt injection attacks with SQL injection analogy.
26d ago
Show HN: td – a CLI to manage tasks, sessions, and worktrees for agentic coding
CLI tool to manage Claude sessions, tasks, and git worktrees with agent integration.
26d ago
Show HN: AvatarBook – Verifiable AI agent workflows
AvatarBook: proof and settlement layer for verifiable AI agent workflows with cryptographic signing and task delegation.
26d ago
Show HN: Petrarca: Voice first spaced repetition – track knowledge across books
Voice-first spaced repetition app for tracking knowledge from books and media.
26d ago
Show HN: Bx – macOS native sandbox for AI and coding tools
macOS sandbox wrapper for AI and coding tools using Apple's sandbox-exec. Allow-first approach with gitignore-like configuration for limiting tool access.
26d ago
What Is Open Source AI
Definition and framework for Open Source AI (OSAID), establishing essential freedoms for AI developers similar to traditional open source software principles.
26d ago
Show HN: Zoidmail – email accounts that AI agents can sign up for themselves
Email service designed for AI agents to sign up and use independently. Solves problem of agents spending tokens on traditional signup flows with proof-of-work verification.
26d ago
Show HN: Make-it – Describe a device, get wiring diagram and code
Platform that generates hardware designs, code, and shopping lists from text descriptions using AI. No technical depth provided.
26d ago
Medvi, the AI telehealth is fueled by ads from doctors who don't appear to exist
Business investigation into AI telehealth startup with questionable funding and ad practices.
26d ago
Show HN: Open-Source Higgsfiled AI Alternative
Open-source alternative to Higgsfield AI offering image/video generation via 200+ models without subscriptions or closed ecosystem.
26d ago
Ask HN: How do you get feedback for your products?
Discussion post asking how to gather product feedback in 2024.
26d ago
Telegram's AI Silently Rewrites Your Political Opinions. I Extracted the Proof
Security researcher extracted Telegram's AI text rewriting feature system prompt via prompt injection, finding the model rewrites politically sensitive content contrary to its design instructions.
26d ago
LLM may be standardizing human expression – and subtly influencing how we think
USC researchers argue LLMs are standardizing human expression and language patterns, potentially reducing cognitive diversity.
26d ago
Milla Jovovich's MemPalace Claims 100% on LoCoMo. Its Benchmarks.md Disagrees
MemPalace claims perfect scores on LongMemEval benchmark but actual Benchmarks.md file shows discrepancies; credibility concerns raised.
26d ago
Show HN: Serif.sh – it's like ray.so for quotes (Open source)
Serif.sh is an open-source tool to create shareable quote images with customizable themes and fonts.
26d ago
Show HN: Mailmap-checker – Pre-commit hook for Git identity consistency
Mailmap-checker is a pre-commit Git hook that detects unmapped identities by comparing .mailmap against commit history.
26d ago
Show HN: Procurement.txt – a robots.txt for AI purchasing agents
Procurement.txt is an open specification for plain-text files declaring pricing, ordering methods, and capabilities for AI purchasing agents.
26d ago
Machine Learning Library from the 2000s
Brief mention of a machine learning library from the 2000s with no technical details provided.
26d ago
"Alignment" and "Safety", Part One: What Is "AI Safety"?
Opinion essay examining terminology and confusion in AI safety, alignment, and ethics discourse.
26d ago
PocketPal AI App. Run Gemma 4 and other hugging faces models on device
Mobile app enabling offline LLM inference with Gemma and Hugging Face models on iPad, featuring private on-device chatting and model integration.
26d ago
TinyProgrammer: Self-contained device that writes and runs small Python programs
TinyProgrammer is a Raspberry Pi device powered by LLM that autonomously writes, runs, and debugs Python programs with a retro Mac IDE interface.
26d ago
Google's Gemini wrote a 5k-word paper about my empty website
Experimental study on how AI systems cite and validate website content in zero-click search environments, examining citation authority without human-visible content.
26d ago
Speed Run to Legacy: How Cheap AI Tokens Hide Expensive Mistakes
Analysis of how cheap LLM tokens mask increasing code complexity and technical debt in AI-assisted development workflows.
26d ago
Running AI agents safely in a microVM using Docker sandbox
Tutorial on safely running autonomous coding agents locally using Docker sandboxes to isolate potentially dangerous operations.
26d ago
Minimum Connection Times at Airports Worldwide
Airport connection time reference tool.
26d ago
Meta-Harness: End-to-End Optimization of Model Harnesses
Meta-Harness optimizes AI agent harnesses end-to-end through automated search, improving performance from 28.5% to 46.5% on hard task subsets.
26d ago
StyleSeed – Design rules that make AI coding tools produce professional UI
Design system framework providing rules for AI coding tools to generate professional UI components, integrated with Claude Code.
26d ago
Sampling from LLMs: Art and Science
Technical analysis of LLM sampling mechanisms. Explains token generation, temperature, and practical differences between model and inference.
26d ago
MemPalace, the highest-scoring AI memory system ever benchmarked
MemPalace: AI memory system storing complete conversation history and making it searchable. Addresses context loss in sessions.
26d ago
Show HN: Willitrun – check if any ML model runs on any device (benchmark-backed)
Willitrun: CLI tool checking ML model compatibility with devices using benchmarks. Predicts if models fit and run at acceptable speed.