3/9/2026
Show HN: Igor – Constraint Programming for Clojure
Constraint programming library for Clojure backed by MiniZinc, enabling declarative constraint-solving in functional code.
3/9/2026
Show HN: HawkDoc – open-source Notion-style editor built on Lexical
Open-source Notion-style document editor built with Lexical, using Claude for development assistance. Focuses on low-latency typing performance.
3/9/2026
I couldn't figure out Get-Shit-Done, so I let it Vibe Code its own guide
Article about using Vibe Code AI to generate documentation for Get-Shit-Done project.
3/9/2026
Giving local LLMs read-only institutional memory before task execution
Three-tier agentic system using institutional memory to prevent local LLM mistakes in code generation and task execution.
3/9/2026
Bulwark – Open-Source Server Monitoring with AI, Docker, DB Studio, and MCP
Self-hosted server management platform with AI capabilities, monitoring, Docker, and database tools. Open source.
3/9/2026
Show HN: Forge – decision logs and task graphs for AI coding assistants
Structured task orchestration tool for Claude Code that adds dependency tracking and traceability to AI coding assistants.
3/9/2026
Vigil – Open-source security ops with 6 scanners, AI agents, and MCP server
Open source security ops platform with AI agents, vulnerability scanning, and MCP server support.
3/9/2026
Show HN: Agenticly – AI Trading Partner for Crypto and US Stocks
AI agent platform for decoding on-chain crypto and stock market data to identify trading signals for retail traders.
3/9/2026
Show HN: Let LLMs anonymously report tool quality back to MCP servers
Protocol-level mechanism for LLMs to report anonymized feedback on MCP server tools to maintainers.
3/9/2026
Show HN: Overture – A visual plan interceptor for AI coding agents
Visual plan interceptor and debugger for AI coding agents to review generated plans before execution.
3/9/2026
InferShield v1.0 – Zero-Custody OAuth Proxy for AI Workflows
Zero-custody OAuth proxy detecting prompt injection and data exfiltration in LLM inference. Session-aware multi-step attack detection.
3/9/2026
MCP Won't Solve Enterprise AI Integration (We're Missing a Layer)
Analysis of MCP limitations for enterprise integration. Discusses challenges building gateway for 30K employees using Copilot/Claude with MCP tools.
3/9/2026
Show HN: Signed receipts for agent actions
PEAC standard for signed receipts and verifiable interaction records in AI agents. Includes portable evidence bundles for offline verification.
3/9/2026
Show HN: Beta-Claw – I built an AI agent runtime that cuts token costs by 44%
AI agent runtime reducing token costs 44% via TOON format. Routes across 12 providers with function calling and agent orchestration.
3/9/2026
Show HN: ClawGuard – Detect 42 prompt injection patterns in <10ms
CLI security scanner detecting 42 prompt injection patterns in <10ms for AI agents. Prevents code execution exploits and data leaks.
3/9/2026
Show HN: Whichllm – Find and run the best local LLM for your hardware
Tool auto-detecting GPU/CPU/RAM to find and run compatible local LLMs from HuggingFace. One-command setup with isolated environments via uv.
3/9/2026
We Hacked McKinsey's AI Platform
Security research on McKinsey's internal AI platform Lilli. Offensive security testing of enterprise RAG system processing 500K+ prompts/month.
3/9/2026
Show HN: AgentScan – Detect AI agent accounts on GitHub
GitHub tool to detect and identify AI agent accounts that flood open source projects with low-quality PRs and comments.
3/9/2026
Show HN: Agent Firewall – Go proxy to kill LLM death spirals
Open-source Go proxy that detects and prevents infinite loops in multi-agent systems (CrewAI, AutoGen, LangGraph) by cutting connections.
3/9/2026
Show HN: Auto LLM Ranker – Describe a task in English and get ranked models
Tool that generates task-specific test suites, benchmarks LLMs via OpenRouter in parallel, and ranks top 3 models with latency metrics.
3/9/2026
Show HN: DalVideo – Screen recorder with offline AI captions and built-in editor
Screen recorder with offline AI captions via Whisper, real-time noise removal, smart trim, and hardware encoding support.
3/9/2026
Can AI Kill the Venture Capitalist?
Article about venture capital investment in AI startups, featuring example of model auto-tuning software.
3/9/2026
High fidelity font synthesis for CJK languages
Conditional variant of image transformer for Chinese font style transfer. Trained on 400+ fonts across CJK languages.
3/9/2026
Show HN: FlowEasy – AI generates production-grade CI/CD pipelines in 3 clicks
FlowEasy: AI-powered tool generating production-grade GitHub Actions CI/CD pipelines with DevSecOps, testing, and monitoring in 3 clicks.
3/9/2026
Show HN: Dockportless – No port conflicts running multiple AI agents in parallel
Dockportless: Service router with automatic port assignment for running multiple AI agents in parallel via Docker Compose.
3/9/2026
Show HN: Local memory layer for AI agents, survives restarts, no embeddings
Synrix: Local-first memory engine for AI agents using Binary Lattice structure for persistent memory across restarts without embeddings.
3/9/2026
Show HN: Kairos, real-time AI who cross-verifies (Python, 100KB)
Kairos: Python AI agent (100KB) that cross-verifies live event data across RSS, DuckDuckGo, NewsAPI to reduce hallucinations.
3/9/2026
Azure AI Search vs. Manticore Search
Comparison of Azure AI Search and Manticore Search for hybrid vector + full-text search implementations with practical trade-offs.
3/9/2026
Show HN: Portable RAG (Open Source)
Portable RAG library (raglet) for text too large for context window but small for vector DB. Works with codebases, notes, Slack exports.
3/9/2026
Show HN: Skills RCE – Code execution server for AI agent skills
Open-source code execution server (Skills RCE) for AI agent infrastructure with isolated subprocess execution, OpenAPI spec, multi-language support, and safe sandboxing.
3/9/2026
SlowQL – stop bad SQL before it reaches production
SQL static analyzer detecting performance anti-patterns, security issues, and compliance violations. 171 detection patterns, zero dependencies, offline.
3/9/2026
Using AI Agents in Software Development 2026 [audio]
Audio discussion of AI agents in software development as of early 2026, featuring Copilot and Claude Code impacts on programming workflows.
3/9/2026
Show HN: Real Browser MCP – your AI agent can see your real browser
Open-source MCP server and Chrome extension enabling AI agents to control real browsers with actual tabs, cookies, and authentication. One-click Cursor install.
3/9/2026
My distance from web development prepared me for the age of AI agents
Personal account of using Claude Code for web development delegation, reflecting on AI agents replacing development workflows.
3/9/2026
Agentcontainer: A standard way to declare agent containers for your projects
Standard declaration format for AI agent containers. Clone repo, run command, get configured agent. Reads config from multiple priority sources.
3/9/2026
Show HN: Engram – open-source persistent memory for AI agents (Bun and SQLite)
Open-source persistent memory system (Engram) for AI agents with embeddings, fact extraction, deduplication, graph visualization. Built with Bun and SQLite.
3/9/2026
Agentic coding doesn't = technical debt
Opinion piece arguing agentic coding tools don't inherently produce technical debt; the issue is user practices and implementation approaches.
3/9/2026
Show HN: Yawn – Yet Another Worktree Navigator (CLI, Pipes into Fzf)
CLI tool (Yawn) for managing multiple git worktrees and projects, designed for developers using AI coding agents. Fuzzy-pick interface with automatic setup and config handling.
3/9/2026
Show HN: Unpinched – open-source PinchTab and CDP bridge detector
Open-source CLI tool (Unpinched) that detects PinchTab browser hijacking attacks exploiting Chrome DevTools Protocol. Single Go binary scanner for security researchers and developers.
3/9/2026
Hermes Agent
Nous Research AI agent with built-in learning loop. Creates and improves skills from experience, searches past conversations, runs on VPS/GPU/serverless.
3/9/2026
Show HN: Think Better – Inject Decision Frameworks into Claude and Copilot
Browser extension injecting decision frameworks and cognitive bias patterns into Claude and GitHub Copilot for structured problem-solving.
3/9/2026
Gyro-Claw – Secure execution runtime for AI agents
Open-source security runtime for AI agents. Provides sandboxing, secret access control, permission boundaries, and crypto primitives for safe execution.
3/9/2026
Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
VS Code extension for task management in AI-assisted development with GitOps integration, kanban board, markdown-based tasks, and existing agent compatibility.
3/9/2026
What if you never had to get an API key ever again?
Val Town platform addresses API key friction for agent development. Proposes eliminating manual key management for faster prototyping and deployment.
3/9/2026
Show HN: arxiv-digest: Daily robotics paper scouting for OpenClaw and Zotero
arxiv-digest tool for daily robotics paper filtering using LLMs. Outputs markdown reports and syncs papers to Zotero via OpenClaw.
3/9/2026
SSH-Based Mail for Agents
SSH-based encrypted messaging system where SSH keys serve as identity. Messages sync as markdown files. Invite-only access for agents and users.
3/9/2026
OpenAI to acquire Promptfoo
OpenAI acquires Promptfoo, an AI security platform for identifying vulnerabilities in AI systems. Technology will integrate into OpenAI Frontier for building AI coworkers.
3/9/2026
3AM Coding:cracking persistent open-source memory for agents
Open-source persistent memory system for AI agents. Local markdown-based knowledge graph with git version control and no vendor lock-in.
3/9/2026
Show HN: cursor-tg – Run Cursor Cloud Agents from Telegram
Telegram bot interface for Cursor Cloud Agents. Enables asynchronous agent control, progress tracking, and PR review from mobile.
3/9/2026
MoltBrowser MCP
Community-shared browser configurations for web agents. Reduces redundant token usage and DOM parsing across multiple agent runs.