Show HN: I open-sourced the AI agents I use to run 35 marketing clients solo
Open-source repository of AI agents for marketing automation covering ad management, website building, and SEO for 35+ clients.
Open-source repository of AI agents for marketing automation covering ad management, website building, and SEO for 35+ clients.
Think Better: open-source AI skills package with 155 decision-science frameworks for LLM assistants, following Anthropic skill format.
System R provides risk management API for autonomous trading agents with examples in Python, CrewAI, and LangChain. Blocked 53 trades, reduced max drawdown 29 percentage points.
IBM triples entry-level hiring despite AI adoption, recruiting software developers and other junior roles.
Mixed-precision 4-bit quantization technique improves Qwen3.5-4B model performance, achieving lower perplexity than FP16 baseline while reducing VRAM usage to 6.4GB.
Critical examination of claims that AI agents will replace software engineers, analyzing autonomy vs task proficiency gap.
Age verification API using OS-level signals instead of ID uploads to comply with California's AB 1043 privacy law.
Modular comic about GPU programming featuring fictional characters representing engineering approaches and optimization.
Security analysis of legitimate Chrome extension turned into malware with credential theft and remote task execution.
TORASAN: open-source framework automating functional safety compliance documentation (ISO 26262, IEC 61508) including traceability and FMEA.
Go CLI proxy for monitoring LLM API requests and flagging sensitive data exposure in outbound agent traffic.
Architectural patterns for multi-agent systems addressing six common mistakes: inter-agent coordination, task management, scalability, cost optimization.
Python implementation of LCModel converted from Fortran using OpenAI Codex with project-owner oversight and validation.
Opinion piece critiquing the notion that LLMs will make everyone a software developer, arguing the premise is disconnected from human behavior.
NimoNova: AI-assisted research workspace that organizes saved articles, papers, PDFs, and images into a knowledge system. Part 4 of series on AI-assisted development.
Benchmark comparison of cloud sandbox providers (Daytona, E2B, Blaxel, Modal) for Python code execution performance.
RailsForge: CLI tool for auto-generating Rails components including monitoring, DevOps, security analyzers, and Docker/CI-CD configurations.
Personal account of GitHub commit activity surge masking lack of actual project impact, examining metrics vs real achievement.
Open-source platform to orchestrate AI agents as employees with role-based assignments, budgets, and monitoring dashboard.
Tutorial on setting up free custom email forwarding using Cloudflare Email Routing and Gmail integration.
Rust-based file encryption engine achieving 1 GiB/s throughput using io_uring, Rayon parallelization, and optimized ciphers.
Analysis of information cocoon problem in AI agents: agents stuck in loops, duplicating code, failing to search existing solutions.
Stub entry about Leonardo, Gutenberg and Florence history video. No content provided.
Claim that Qwen3.5 4B benchmarks match GPT-4o performance. No detailed analysis or evidence provided.
Developer tool running 5 frontier models in parallel for code audit, models debate findings, coordinator synthesizes consensus. Claude, GPT-4o, Gemini, Mistral, DeepSeek.
Open-source modular Linux host monitoring system using autonomous agent workers for subsystem surveillance. Structured event aggregation with CLI and Prometheus exposure.
Stub entry about File-Augmented Retrieval with Mac Vision support. Title only, no content.
Open-source tool tracking Cursor IDE costs with anomaly detection and Slack alerting. Developer tool for LLM application costs.
Open-source CLI tool scanning shell for credentials and access that AI agents could exploit. Covers AWS, GCP, Azure, API keys, K8s, Docker.
Open source alternative to Topaz Photo AI with direct implementation of all AI logic (preprocessing, inference, tiling, tensor ops) without external APIs.
Stub entry about editors as knowledge facilitators. No content provided.
Article about LLM-driven code rewrites and relicensing concerns. Author biography provided with minimal content.
Claude Code Container: zero-config Docker isolation for Claude's code generation, balancing safety and developer flow without permission prompts.
LLMTor: tool enabling anonymous access to public LLMs using blind signatures and Tor, preventing server operators from linking prompts to users.
Atombot: open source self-hosted personal AI assistant (~500 lines) with persistent memory, Telegram gateway, reminders, and extensible skills system for local and GPT models.
GeekBench 6.6 release notes listing version history with Vulkan GPU benchmarking. Minimal content.
Monitoring tool that alerts on changes to tracked topics. Uses AI to avoid false positives unlike Google Alerts or ChatGPT tasks.
ZARQ: free crypto risk API for AI agents. Minimal description provided.
CLI tool converting webpages into AI agent skills. Extracts docs to generate skills locally or via npx installation for agent consumption.
Opinion piece on freemium business models and asymmetric economics in software.
Skate v1.0.0: Local key-value store tool written in Go. No longer syncs to cloud after sunset of Charm Cloud.
Civet: TypeScript superset with syntax improvements inspired by CoffeeScript and JSX discussions. Configuration-driven language features.
Analysis of silicon strategy as competitive moat for frontier AI labs, comparing approaches by Anthropic, OpenAI, and Microsoft on compute procurement.
Vex: production reliability layer for AI agents that observes behavior, verifies outputs against guardrails, and auto-corrects hallucinations silently before reaching users.
PowerSkills: PowerShell toolkit for Windows-based AI agents exposing Outlook, Edge browser, desktop automation, and shell commands as structured JSON skills.
Discussion of code quality and ownership concerns as AI tools enable non-engineers to generate pull requests at scale.
Personal reflection on being away from work and agentic coding research for two weeks.
DevKit provides 80 browser-based developer tools for formatting, encoding, converting, and generating data—all client-side processing with no server transmission.
GPT2Skill: single-page HTML tool converting ChatGPT Custom GPTs to Claude Skills, runs entirely client-side without backend.
PersonaNexus is a YAML compiler tool for configuring deterministic personalities in AI agents.