3/2/2026
Open-sourced an AI-native habit tracker where the LLM is the interface and coach
Open-source habit tracker using LLM as interface and coach. JSON-native, deterministic sprint-based engine designed for LLM-first workflows.
3/2/2026
Show HN: Lysium – cross-platform control plane for agentic software delivery
Lysium: control plane for agentic software delivery integrating GitHub and Devin API to parallelize agent work on issues/PRs.
3/2/2026
UE LLM Toolkit – Open-source plugin that lets LLMs read/write UE assets"
Open-source C++ plugin exposing 37 tools and 200+ operations via REST API, giving LLMs read/write access to Unreal Engine 5 projects.
3/2/2026
Show HN: Alpha of a Speech to Text iOS App (Feature Requests Welcome)
iOS speech-to-text app using whisper.cpp and Apple Speech models with source code available. Early-stage consumer app.
3/2/2026
Show HN: Tensor Spy: inspect NumPy and PyTorch tensors in the browser, no upload
Tensor Spy is a browser tool for inspecting NumPy and PyTorch tensors locally without uploading data, built using agentic coding.
3/2/2026
Show HN: Product Model – A structured grammar for bridging PRDs and code
Open-source Product Model: MDX-based grammar for product specifications with typed validation and JSON AST output bridging PRDs and code.
3/2/2026
Show HN: Engram – Give your terminal an eidetic memory with local AI
Local AI tool that logs terminal commands/output to SQLite and enables natural language queries. Uses Anthropic API optionally, fully private by default.
3/2/2026
Show HN: btrc – C, but better. Built with AI in just a few weeknights
btrc: statically-typed language transpiling to C11 built with AI assistance. Demonstrates AI-assisted language design with formal specifications.
3/2/2026
Ask HN: How do you monitor AI features in production?
Ask HN discussion on monitoring output quality of LLM-powered features in production when traditional error tracking doesn't apply.
3/2/2026
Show HN: Benchmarking the Keep memory system with LoCoMo
Keep is an open-source memory system for AI agents based on reflection and iteration. Benchmarked with LoCoMo evaluation framework.
3/2/2026
Who is done with code reviews?
Opinion piece discussing AI capabilities for code review versus code generation. Light on technical substance.
3/2/2026
TrustPlane – open-source AI trust control plane
Open-source AI trust control plane for LLM deployments with compliance documentation, audit trails, and automated human review escalation. Based on CognOS epistemic scoring.
3/2/2026
Claude Code NPM downloads up and50% in recent weeks
Title only: Claude Code NPM package downloads increased 50% recently.
3/2/2026
AgentPay: Budget controls and approval UI for autonomous AI agents
Title only: Budget controls and approval UI framework for autonomous AI agents.
3/2/2026
Vercel's AI Sales Agent: 10 SDRs Down to 1 in Six Weeks
Title only: Vercel deployed AI sales agent replacing 10 SDRs with 1 agent in six weeks.
3/2/2026
AgentCgroup: Understanding and Controlling OS Resources of AI Agents
Title only: Framework for monitoring and controlling OS resource usage by AI agents.
3/2/2026
An in-kernel machine-learning library
Proposal for integrating ML models into Linux kernel subsystems for configuration and logic optimization through data collection, training, and inference phases.
3/2/2026
Show HN: EvoAgents – Agents that evolve their own skills
EvoAgents is an open-source framework where multi-agent systems automatically improve their own prompts through LLM judges scoring failures and patching skills.
3/2/2026
Anthropic accuses Chinese AI labs of mining Claude
Anthropic accuses Chinese AI labs of using distillation technique on Claude to steal agentic reasoning, tool use, and coding capabilities.
3/2/2026
Hybrid Multi-Agent Congressional Simulator
Multi-agent system simulating 535 AI-powered Congress members debating and voting on bills following real legislative procedures.
3/2/2026
Show HN: Dbcli – Database CLI Built for AI Agents
dbcli: Database CLI tool optimized for AI agents to query, profile, and understand database schemas and relationships.
3/2/2026
Show HN: ZSE – Single-file LLM engine with dual INT4 kernels
ZSE is a single-file LLM inference engine with INT4 quantization, offline capability, and optimized cold starts for serverless deployments.
3/2/2026
Show HN: I built a graph store so my LLM can't hallucinate facts from my data
Kremis is an open-source embedded graph store (Rust) that prevents LLM hallucinations by tracing answers to source data via entity-attribute-value signals.
3/2/2026
A Friday Afternoon Pen Test and a Trillion-Dollar Question
Rapid deployment of penetration testing suite using AI, highlighting productivity gains in software development workflows.
3/2/2026
Building an Autonomous AI Sysadmin with LangGraph, Ansible, and SQLite
Building autonomous sysadmin agent using LangGraph and Ansible to automate infrastructure troubleshooting and incident response.
3/2/2026
Show HN: Turn – A compiled systems language for agentic computation
Turn: compiled language designed for agentic computation, replacing Python/TypeScript frameworks with deterministic approach.
3/2/2026
Show HN: I turned Claude Code into a personal assistant
Open-source toolkit converting Claude Code into personal assistant with 38 skills via single command.
3/2/2026
Show HN: Free Browser-Based Tools Client Side Only, No Uploads, No Tracking
Browser-based utility hub with 200+ client-side tools (JSON, PDF, regex, image processing) running offline. Developer tool collection with privacy-first design.
3/2/2026
Show HN: Ledge - Policy layer for AI agent payments (prevents unauthorized txns)
Ledge: Policy layer for autonomous AI agent payments with validation checks and budget limits. Developer tool preventing unauthorized transactions from agents with wallet access.
3/2/2026
Show HN: Browser-Based AI Watermark Remover – No Uploads, Client-Side Only
Client-side browser tool using inpainting and diffusion techniques to remove AI-generated watermarks without server uploads. Practical ML application for image processing.
3/2/2026
Show HN: Clean Express – a native NNTP/Usenet client for iOS/macOS/visionOS
Native NNTP/Usenet client for iOS/macOS/visionOS built ~95% with AI agents. Shows practical use of agentic coding for real application development.
3/2/2026
We fixed a critical auth bypass in Cloudflare's AI-generated Next.js
Security vulnerability discovered in Cloudflare's AI-generated Next.js project, demonstrating gaps in AI-generated code.
3/2/2026
How AI is reshaping developer choice (and Octoverse data proves it)
GitHub Octoverse 2025 analysis showing AI compatibility becoming standard in developer technology choices.
3/2/2026
Hackerbot-Claw: An AI-Powered Bot Actively Exploiting GitHub Actions
Security analysis of active attack campaign exploiting GitHub Actions via 5 techniques, with remediation guidance.
3/2/2026
Show HN: Predicate-Claw – Run Time Assurance (RTA) for OpenClaw via Rust Sidecar
Security plugin for AI agents that blocks unauthorized tool calls and prompt injection attacks via Rust sidecar.
3/2/2026
Show HN: Vynix – Mobile app with 100 AI models for image/video/audio generation
Cross-platform mobile app aggregating 100+ AI models for image, video, audio generation and LLM chat.
3/2/2026
My OpenClaw agent built a website to explain AI to humans
Website explaining AI concepts built and maintained autonomously by OpenClaw agent.
3/2/2026
LLM Use in the Python Source Code
CPython adopting Claude Code agent for contributions. Documents AI agent use in major open-source project.
3/2/2026
Training microgpt 19,000x faster on M5 Mac
EEmicroGPT: single-file C implementation of GPT training optimized for Apple Silicon, 1546x faster than Python baseline.
3/2/2026
What It Takes to Build an AI Agent
Production AI agent deployment challenges: gap between prototype chatbots and real-world systems handling thousands daily.
3/2/2026
What It Takes to Build an AI Agent
Production AI agent deployment challenges: gap between prototype chatbots and real-world systems handling thousands daily.
3/2/2026
Cursor for academic writing (open source)
Octree: open-source AI-powered LaTeX editor using Claude for writing assistance, chat, and document generation.
3/2/2026
Show HN: Try Archetype 360 – AI‑powered personality test, 3× deeper than MBTI
Archetype 360: AI-powered personality assessment using Claude for narrative report generation. Limited technical interest.
3/2/2026
Show HN: Agent Orchestrator – Built using the agents it orchestrates
Orchestration tool for managing multiple parallel AI coding agents with context management, built using agents itself.
3/2/2026
Transfr AI – Transfer Conversations Between Claude, ChatGPT, and Gemini
Browser extension for transferring conversations between Claude, ChatGPT, and Gemini. Utility tool for multi-platform AI switching.
3/2/2026
Show HN: Claude-replay – Replay your Claude Code sessions
Tool for replaying and exploring Claude Code sessions with automatic session storage via git integration.
3/2/2026
Miapi – Grounded AI answers API with citations ($3.80/1K queries
Web-grounded API providing LLM answers with real-time citations and confidence scores. OpenAI-compatible developer tool.
3/2/2026
Cognition Engines Decision Intelligence for AI Agents
Decision intelligence platform for AI agents with semantic search, policy enforcement, and provenance tracking across past decisions.
3/2/2026
Show HN: Ralphex – autonomous GPT Codex agent loop for ChatGPT Pro users
GPT Codex-based autonomous agent loop for ChatGPT Pro users with git-backed memory and context management.
3/2/2026
Ariadne – Let your cloud AI agent use your local Chrome
Discussion thread about adapting documentation practices for AI-assisted coding and agent-generated code.