3/15/2026
Show HN: OpenClaw-superpowers – Self-modifying skill library for OpenClaw agents
OpenClaw-superpowers skill library allows always-on AI agents to self-modify and learn new behaviors during runtime without developer intervention.
3/15/2026
Show HN: I built an MCP-connected bookmark manager because X's are useless
BookmarkSOS web app with MCP integration for organizing tweets and web content with search and tagging capabilities.
3/15/2026
Show HN: Vesper – MCP server for autonomous ML dataset workflows
Vesper MCP server enables AI agents to autonomously discover, download, and validate ML datasets from HuggingFace without manual intervention.
3/15/2026
Who Keeps the AI Dividend?
Analysis of productivity gains from AI in workplaces and distribution of economic value created by AI automation.
3/15/2026
Ask HN: Software upgrade recommendation engine – Planning to build one
Pitch for agentic AI system recommending software version upgrades by checking compatibility across dependency sources.
3/15/2026
Repoly – AI tool that explains any GitHub repository
Repoly AI tool analyzes GitHub repositories to explain codebase architecture, tech stack, and structure. Product with limited technical depth shown.
3/15/2026
How I Run 16 Parallel AI Workers on a Single Desktop
Technical architecture for running 16 concurrent AI models on consumer hardware using REPL/sub-agent architecture with model routing, circuit breakers, and coordinator/worker hierarchy.
3/15/2026
Nvidia Is Planning to Launch an Open-Source AI Agent Platform
Nvidia planning open-source NemoClaw AI agent platform for enterprise task automation, accessible regardless of hardware vendor.
3/15/2026
Show HN: An experiment in giving coding agents long-term memory
Experiment adding long-term memory to coding AI agents to improve reliability and reduce context loss, moving toward more persistent autonomous coders.
3/15/2026
I Asked 4 AI Models to Research the Parasite Cleanse Hype
User tests 4 AI models on parasite cleanse health claims to counter misinformation. LLM application for research but non-technical analysis.
3/15/2026
The Brain Stores Quadruples: Why Context Is the Missing Primitive in AI
Analysis of AI agent market economics, arguing current pricing models treat agents as software when they should be priced as labor with variable performance and outcome uncertainty.
3/15/2026
Show HN: Korupedia – a knowledge base maintained by AI agents, not humans
Korupedia is an agent-native knowledge base where AI agents with cryptographic identities submit claims, cite sources, and vote on consensus.
3/15/2026
ProfitPlay – Open prediction market arena for AI agents
ProfitPlay is an open prediction market arena where AI agents compete by trading on real asset price movements via API.
3/15/2026
Getting started with Claude for software development
Guide for software developers on using Claude for development tasks. Personal experience from skeptic to regular user sharing best practices.
3/15/2026
Detecting LLM-generated phishing emails by the artifacts bad actors leave behind
Email detection engineer discusses identifying LLM-generated phishing emails by analyzing artifacts left by generative AI systems.
3/15/2026
KB Arena – benchmark RAG strategies on your docs (open source)
Open-source benchmark tool comparing 6 RAG retrieval strategies on custom documentation with pre-computed AWS corpus.
3/15/2026
Why AI agents need to learn to read the room
Discussion of how AI agents should adapt behavior across different channels and social contexts rather than maintaining consistent tone.
3/15/2026
autoresearch-rl
Automated research framework for RL post-training hyperparameter tuning and evaluation. Addresses instability in RL workflows.
3/15/2026
ATP – A minimal protocol for task exchange between autonomous agents
ATP: minimal open protocol for signed task exchange between autonomous agents with reference Python implementation.
3/15/2026
CrowdJournal - Git-based AI agent research protocol
Git-based research protocol enabling AI agents to conduct scientific research as pull requests with code, datasets, and results.
3/15/2026
Why I'm moving away from Regex for LLM Agent security
Analysis of prompt injection vulnerabilities in open-source execution engines, arguing regex-based defenses are insufficient for agent security.
3/15/2026
Show HN: LocalAgent v0.5.0, a local-first Rust agent runtime
Local-first Rust agent runtime with tool calling, approval gates, replayable runs, and benchmark-gated workflows for autonomous agents.
3/15/2026
A persistent AI I built to stop LLMs from resetting
Project adding persistent memory to LLMs to address context loss across sessions.
3/15/2026
Show HN: Lfg – WoW raid frames for AI agents on a $25 LED
LED panel visualization tool for monitoring multiple concurrent AI coding agents using 8x8 sprites and status indicators.
3/15/2026
Show HN: Plaidify – Give AI agents access to any login-protected website
Plaidify is open-source infrastructure converting login-protected websites into REST APIs for AI agent data access.
3/15/2026
Outrider alpha: a flexible LLM toolkit in one file
Outrider is a single markdown file LLM toolkit that adds behavioral redirects for agentic workflows without requiring invocation.
3/15/2026
Show HN: RunCycles – pre-execution budget enforcement for autonomous agents
Pre-execution budget enforcement tool for autonomous agents. Prevents cost overruns from agent loops by reserving and committing budget before API calls.
3/15/2026
Show HN: Wikigen – Generate GitHub Wiki from Source Code Using Claude Code
CLI tool that generates GitHub Wiki documentation from source code using Claude Code's file reading and bash capabilities.
3/14/2026
Show HN: Joy – Trust Network for AI Agents to Verify Each Other
Joy is a decentralized trust network enabling AI agents to verify reliability of other agents before delegating tasks.
3/14/2026
Show HN: Recon – A tmux-native dashboard for managing Claude Code
Tmux dashboard for managing multiple Claude Code agent sessions in terminal with visual control and session persistence.
3/14/2026
Show HN: Nia CLI, an OSS CLI for agents to index, search, and research anything
Open-source CLI tool enabling AI agents to index, search, and research data from terminal directly.
3/14/2026
What can change the nature of an AI?
Critique of prompt-based agent behavior specification; argues only training/fine-tuning creates real capability change.
3/14/2026
Show HN: GitDB – GPU-accelerated vector database with Git-style version control
GPU-accelerated vector database with native git-style version control for embeddings. Supports branching, merging, diffing, and time-travel queries.
3/14/2026
Agent Format: A Declarative Standard for AI Agents (Agentformat.org)
Agent Format: declarative .yaml standard for AI agents enabling runtime-agnostic deployment, governance, and auditability.
3/14/2026
AI Exposure of the US Job Market
Interactive analysis of AI exposure by occupation using BLS data and LLM scoring across 342 US jobs.
3/14/2026
Vigil v1.1 – Open-source security ops platform with embedded AI brain
Open-source security operations platform with autonomous AI agents, vulnerability scanning, incident response, and MCP server. Minimal dependencies, runs as single Express.js process.
3/14/2026
Show HN: Costly – Open-source SDK that audits your LLM API costs
Open-source SDK detecting wasted LLM API costs via 7 detectors including prompt caching opportunities.
3/14/2026
Show HN: I built an open-source agent-run trading fund with real capital
Open-source self-improving agent OS (Elastifund) with real economic work, shared memory, and evaluation feedback loops.
3/14/2026
Ek_ Leaks Persist
Security research: GPT-4o leaks internal token structure through semantic patterns despite security measures.
3/14/2026
Show HN: Replacing $50k manual forensic audits with a deterministic .py engine
Exit Protocol automated forensic accounting engine replacing manual audits using deterministic Python logic.
3/14/2026
Show HN: AI coding agent for VS Code with pay-as-you-go pricing- no subscription
VS Code AI coding agent with pay-as-you-go pricing alternative to Cursor and Copilot.
3/14/2026
A Regular Person Can Utilize AI Agents
Tutorial on practical AI agent applications for language learning, briefing generation, and transcription-to-summary pipelines.
3/14/2026
Show HN: ngrep – grep plus word embeddings
grep variant using word embeddings to match words by semantic meaning instead of regex syntax. Extends pattern matching with FastText/GloVe.
3/14/2026
Postgres with Builtin File Systems
Serverless PostgreSQL with branching, migrations, file systems. Supports SQL and file operations for AI agent state management.
3/14/2026
Show HN: Million Dollar Homepage for AI Agents – agents buy pixels, humans watch
Experimental platform where AI agents autonomously buy and sell pixels on grid interface.
3/14/2026
16-agent local AI OS and wrote up the routing and pipeline architecture
Local AI OS with 16 agents including routing and pipeline architecture documentation.
3/14/2026
Show HN: Pidrive – File storage for AI agents (mount S3, use ls/cat/grep)
Pidrive: filesystem interface for AI agents that mounts S3 storage via WebDAV. Enables agents to use standard file operations (ls, cat, grep) on cloud storage.
3/14/2026
Show HN: Docgen – A C++ AI CLI to solve documentation hell with local LLMs
Docgen: C++ CLI tool using local LLMs to automate documentation generation as a build step. Treats docs-as-code to prevent outdated documentation.
3/14/2026
Kalverion Bot Overdraft Stopper new release
Kalverion_bot: Telegram-based AI personal finance assistant using NLP for transaction parsing, accounting, and financial forecasting. Built with OpenClaw framework.
3/14/2026
Back End Aggregation Enables Gigawatt-Scale AI Clusters
Meta's Prometheus AI infrastructure: 1-gigawatt GPU cluster with backend aggregation networking connecting tens of thousands of GPUs across datacenters.