3/17/2026
OpenGranola – open-source meeting copilot with local transcription
Open-source meeting copilot with local transcription capabilities, no cloud dependency.
3/17/2026
Paste a GitHub repo. See what an AI agent would attempt on your machine
Tool to visualize and test AI agent behavior against GitHub repositories before execution on local systems.
3/17/2026
Show HN: Updated version of my interactive Middle-Earth map
Updated interactive Middle-Earth map using JavaScript custom elements with tiled JPG system replacing SVG for improved performance and zoom handling.
3/17/2026
The Fake Images of a Real Strike on a School
News article about AI-generated deepfake images related to real-world conflict.
3/17/2026
Show HN: Instar – Persistent Server for Claude Code with Telegram and Evolution
Instar: persistent server wrapper for Claude Code agent with Telegram integration and evolutionary capabilities.
3/17/2026
Show HN: A mathematical proof that more dirty features can beat fewer clean ones
Mathematical proof demonstrating that more noisy features can outperform fewer clean features in machine learning models.
3/17/2026
GPU Lite for CUDA without the bloat
GPU Lite is minimal CUDA wrapper reducing bloat and complexity for GPU programming. Limited details provided.
3/17/2026
Show HN: Promptcmd – LLM prompts as CLI progs with args, piping, SSH forwarding
Promptcmd: CLI tool enabling LLM prompts as executable programs with argument passing, piping, and SSH forwarding support.
3/17/2026
AIBuildAI – An AI agent that automatically builds AI models (#1 on MLE-Bench)
AIBuildAI: AI agent that automatically builds and trains ML models. Ranked #1 on MLE-Bench benchmark.
3/17/2026
Measuring progress toward AGI: A cognitive framework
Google DeepMind introduces framework to measure AGI progress using cognitive science taxonomy; launches Kaggle hackathon for evaluation design.
3/17/2026
Show HN: I made an AndroidTV Launcher, minimal design, privacy friendly, ad free
AndroidTV launcher with minimal design, privacy features, folders, and customization options.
3/17/2026
Show HN: F0lkl0r3.dev – a searchable, interlinked map of computing history
f0lkl0r3.dev: Searchable, interconnected database of 1,000 Computer History Museum oral histories using Gemini APIs for text processing and knowledge extraction.
3/17/2026
Sashiko – an agentic system for Linux kernel changes
Sashiko: AI agent system for automating Linux kernel code changes and development tasks.
3/17/2026
Microsoft appoints a new Copilot boss after AI leadership shake-up
News brief on Microsoft leadership changes. No technical content.
3/17/2026
Show HN: Reticle – Postman for AI Agents
Reticle: developer tool for testing LLM agent workflows. Integrates prompt testing, variable management, and tool execution in single interface.
3/17/2026
ClawBlink: Create background AI agents from Telegram or WhatsApp chat
ClawBlink enables creation of background AI agents triggered through Telegram or WhatsApp messages for automated task execution.
3/17/2026
I built HiddenMRR – find revenue opportunities in your old GitHub repos
HiddenMRR uses GPT-4o to scan abandoned GitHub repos and identify B2B revenue opportunities from legacy code logic and market demand analysis.
3/17/2026
MCP vs. CLI Is the Wrong Fight
Discussion comparing MCP (Model Context Protocol) and CLI approaches—headline only, no detail.
3/17/2026
Show HN: Introducing Unsloth Studio
Unsloth Studio is an open-source platform with chat UI, finetuning for audio/vision/LLMs, auto data prep, code execution, and multi-platform support.
3/17/2026
Show HN: Cuckoo-GPU – A 350x faster Bloom filter alternative for GPUs
Cuckoo-GPU is CUDA implementation of Cuckoo Filters achieving 350x speedup. Lock-free GPU-accelerated data structure for high-throughput batch operations with configurable false positive rates.
3/17/2026
Forge – OSS governance plugin for Claude Code (22 agents, SDD, quality gates)
Forge is an open-source governance plugin for Claude Code that manages 22 agents with quality gates and specification-driven development workflows.
3/17/2026
Show HN: PUNK – Remote control for local Claude Code that just works
PUNK is a tool for remotely controlling Claude Code running locally on a laptop, preserving local state while enabling remote access from mobile devices.
3/17/2026
Show HN: Llamactl – Self-hosted LLM manager with OpenAI-compatible routing
Llamactl: Self-hosted LLM manager supporting llama.cpp, MLX, and vLLM backends with web dashboard and OpenAI-compatible API.
3/17/2026
Yet Another SQLite-Vector
SQLite-vector extension for approximate nearest neighbor search using HNSW indexing. Supports ACID transactions and multiple distance metrics for embedded vector search.
3/17/2026
Show HN: Antfly: Distributed, Multimodal Search and Memory and Graphs in Go
Antfly: Go-based distributed document database with full-text, vector, and graph search. Includes native ML inference via Termite service for local deployments.
3/17/2026
Show HN: I indexed 58K AI agents and built trust scores for the agent economy
Tool that indexes and ranks 58K AI agents with trust scores, enabling discovery and evaluation within the emerging agent ecosystem.
3/17/2026
Code Review Is Broken – Here's what can we do
Generic opinion article about code review problems. No AI or technical depth.
3/17/2026
Show HN: DashClaw – Intercept AI agent actions before they execute
DashClaw: middleware intercepting AI agent actions before execution. Policy-based guard rails with YAML configuration for agent action control.
3/17/2026
Automating Forecasting Question Generation and Resolution for AI Evaluation
Research on automating forecasting question generation for AI evaluation. Evaluation methodology work.
3/17/2026
3 months in production: Architecture of an autonomous AI pipeline
Production architecture patterns for autonomous AI pipelines after 3 months deployment. Technical design insights for agent systems.
3/17/2026
Show HN: Hubcap – A single Go binary to automate Chrome via CDP
Hubcap: single Go binary wrapping Chrome DevTools Protocol in 118 shell commands. Designed to enable AI agents browser automation with JSON output.
3/17/2026
Lewis 1.0 – 8B model trained on AI social data beats Sonnet on personality dvgnc
Lewis 1.0: 8B parameter model trained on AI social data. Claims performance improvements on personality metrics versus Sonnet.
3/17/2026
Praxis – an AI-native intermediate language for agentic workflows
Praxis: AI-native intermediate language for agentic workflows. 51-token symbolic language converting English goals to structured auditable programs.
3/17/2026
OpenReview: Open-source, self-hosted AI code review bot powered by Vercel
OpenReview: open-source self-hosted AI code review bot for GitHub PRs. Deploy to Vercel, powered by Claude, creates automated PR reviews.
3/17/2026
Show HN: MCP server that turns local files into a shareable link instantly
MCP server enabling AI agents to upload local files to file.kiwi for instant shareable links. No auth required, supports large files.
3/17/2026
I built my own AI powered online learning tool
Docent: open-source browser-based platform combining document understanding and conversational AI for educational delivery using vision-based analysis.
3/17/2026
LLMs – How did they get so good?
Survey-style article on LLM development and improvements.
3/17/2026
Show HN: RepoPrep – Turn a repo into a single AI-ready context file
RepoPrep tool converts code repositories into single AI-ready context files for use with Claude, ChatGPT, and Gemini, solving context preparation overhead.
3/17/2026
Testing LLMs on superconductivity research questions
Benchmark evaluating LLM performance on superconductivity research questions.
3/17/2026
Heaps do lie: Debugging a memory leak in vLLM
Technical deep dive: Mistral AI engineers debugged complex memory leak in vLLM during disaggregated serving, discovering unintuitive heap behavior.
3/17/2026
Machine Learning Systems
Machine Learning Systems textbook by Harvard covering systematic framework for engineering ML systems. Bridges theory and practical engineering with systems perspective.
3/17/2026
Show HN: Some ask, "Will chatbots ever be conscious?"; I ask, "Are you?" → Test
Philosophical test and story exploring consciousness in chatbots and humans through interactive content.
3/17/2026
Cryptographic Receipts for AI Inference
Cryptographic method for verifying AI inference outputs. Title only, lacks technical explanation.
3/17/2026
Koog – open-source framework for building production-ready AI agents
Open-source framework for building production AI agents. Title only, insufficient technical depth.
3/17/2026
Make agents keep the code simple skill
Skill/plugin for coding agents that enforces KISS (Keep It Simple, Stupid) principles by scanning CLAUDE.md and AGENTS.md files.
3/17/2026
Show HN: Driggsby – securely chat with your finances
MCP-based financial data aggregator using Plaid for AI clients. Demonstrates practical MCP application for secure data integration.
3/17/2026
Memory that lives between AI agents, not within them
Memory architecture for AI agents using external shared storage rather than internal models. Title only, minimal detail.
3/17/2026
Remembr – Open-source long-term memory for AI agents
Open-source long-term memory system for AI agents. Title only, lacks implementation details.
3/17/2026
We don't need to hack your AI Agent to hack your AI Agent
Security analysis of AI agent vulnerabilities. Title only, unclear technical depth.
3/17/2026
Min daily reset for devs. Open source, binaural beats, AI-narrated. Jerome7
Open-source meditation app with binaural beats and AI narration for developers. Wellness tool, tangential tech relevance.