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.
ZSE is a single-file LLM inference engine with INT4 quantization, offline capability, and optimized cold starts for serverless deployments.
Kremis is an open-source embedded graph store (Rust) that prevents LLM hallucinations by tracing answers to source data via entity-attribute-value signals.
Rapid deployment of penetration testing suite using AI, highlighting productivity gains in software development workflows.
Building autonomous sysadmin agent using LangGraph and Ansible to automate infrastructure troubleshooting and incident response.
Turn: compiled language designed for agentic computation, replacing Python/TypeScript frameworks with deterministic approach.
Open-source toolkit converting Claude Code into personal assistant with 38 skills via single command.
Browser-based utility hub with 200+ client-side tools (JSON, PDF, regex, image processing) running offline. Developer tool collection with privacy-first design.
Ledge: Policy layer for autonomous AI agent payments with validation checks and budget limits. Developer tool preventing unauthorized transactions from agents with wallet access.
Client-side browser tool using inpainting and diffusion techniques to remove AI-generated watermarks without server uploads. Practical ML application for image processing.
Native NNTP/Usenet client for iOS/macOS/visionOS built ~95% with AI agents. Shows practical use of agentic coding for real application development.
Security vulnerability discovered in Cloudflare's AI-generated Next.js project, demonstrating gaps in AI-generated code.
GitHub Octoverse 2025 analysis showing AI compatibility becoming standard in developer technology choices.
Security analysis of active attack campaign exploiting GitHub Actions via 5 techniques, with remediation guidance.
Security plugin for AI agents that blocks unauthorized tool calls and prompt injection attacks via Rust sidecar.
Cross-platform mobile app aggregating 100+ AI models for image, video, audio generation and LLM chat.
Website explaining AI concepts built and maintained autonomously by OpenClaw agent.
CPython adopting Claude Code agent for contributions. Documents AI agent use in major open-source project.
EEmicroGPT: single-file C implementation of GPT training optimized for Apple Silicon, 1546x faster than Python baseline.
Production AI agent deployment challenges: gap between prototype chatbots and real-world systems handling thousands daily.
Production AI agent deployment challenges: gap between prototype chatbots and real-world systems handling thousands daily.
Octree: open-source AI-powered LaTeX editor using Claude for writing assistance, chat, and document generation.
Archetype 360: AI-powered personality assessment using Claude for narrative report generation. Limited technical interest.
Orchestration tool for managing multiple parallel AI coding agents with context management, built using agents itself.
Browser extension for transferring conversations between Claude, ChatGPT, and Gemini. Utility tool for multi-platform AI switching.
Tool for replaying and exploring Claude Code sessions with automatic session storage via git integration.
Web-grounded API providing LLM answers with real-time citations and confidence scores. OpenAI-compatible developer tool.
Decision intelligence platform for AI agents with semantic search, policy enforcement, and provenance tracking across past decisions.
GPT Codex-based autonomous agent loop for ChatGPT Pro users with git-backed memory and context management.
Discussion thread about adapting documentation practices for AI-assisted coding and agent-generated code.
Open-source bridge connecting remote AI agents to local Chrome browser for secure, auditable task execution with visual feedback.
Lightweight Rust-based agent loop framework for building scalable agentic chat interfaces without subprocess overhead.
Interactive educational tool gamifying JavaScript unit test coverage as a dungeon crawler game.
Essay on autonomation principles in software via coding agents, framing agent-driven development as intent specification and verification.
Analysis of rapid AI progress on mathematical benchmarks and how quick performance improvements make existing evaluation metrics obsolete.
ProxyBase OpenClaw Skill adds residential proxy functionality to AI agents to bypass website access restrictions and security blocks.
Open-source Apple Ads automation toolkit with CLI for AI agents, supports CSV/JSON data export-import without API keys.
Local-network markdown workspace with search-first CLI for human-LLM collaboration and agent data management.
Kubernetes framework for orchestrating autonomous AI coding agents with declarative YAML workflows including auto-PR drafting and code review.
General-purpose AI agent with self-improvement via feedback, browser control, async tasks, and permission granularity.
Two CLI tools for Claude Code: claude-remote-approver for remote approval of permissions via mobile notifications, and claude-plan-reviewer for AI-assisted plan validation.
PLAI.chat is a multi-model AI chat interface that routes API calls through OpenRouter while keeping conversation history only in browser localStorage, not on servers.
Competitive intelligence AI agent using SerpApi and OpenAI to research competitors and markets, with optional HubSpot CRM integration.
Screen-aware AI assistant that watches display in real-time for visual debugging and task assistance without copy-paste friction.
VS Code extension for debugging and analyzing Claude Code sessions, tracking costs and detecting inefficiencies in AI-assisted workflows.
Research testing whether AI agents can complete online shopping tasks, finding 9 models struggle with website interaction despite industry hype.
Claude Code-based IDE with multi-agent task automation, context management, skill assignment, and kanban workflow integrated with git worktrees.
Operating system for autonomous AI agents with 15 prebuilt agents and 32+ skills, deployable to Slack, Telegram, email and dashboards.
LLM reverse engineering plugin for IDA Pro enabling AI-augmented binary analysis, part of plugin series for Ghidra and Binary Ninja.
Guide on best practices and pitfalls for AI coding assistants and agents without using AI to write it.
Tool to generate CLI documentation from GitHub repositories for AI agents using MCP.