3/2/2026
AI Now Has Its Own Cursor
Agent framework providing native desktop UI control across Gmail, Slack, Jira, Figma without per-service API setup.
3/2/2026
Customer Intelligence Protocol
Customer Intelligence Protocol: MCP server framework with structured reasoning for consumer-facing LLM applications. Includes safety boundaries and engagement scoring.
3/2/2026
Show HN: YourFinanceWORKS – Open-source financial management with AI
Open-source financial management platform with FastAPI/PostgreSQL/Kafka stack featuring AI-powered OCR and automation capabilities.
3/2/2026
Show HN: ClawShield – Open-source security proxy for AI agents (Go, eBPF)
Open-source security proxy in Go/eBPF scanning AI agent messages with prompt injection detection, structural analysis, and canary token detection.
3/2/2026
Show HN: Remoat – Control Antigravity from your phone via Telegram
Remoat: Telegram-based tool for controlling Antigravity (local AI automation) remotely via phone. End-to-end encrypted, no cloud relay.
3/2/2026
mcp-firewall: A better policy-engine for CLI agents
mcp-firewall: Open source policy engine for CLI agents with granular command/tool control. Supports Claude Code and GitHub Copilot CLI.
3/2/2026
Show HN: MCP-firewall: I created a policy engine for CLI Agents
MCP-firewall: policy engine for controlling CLI agents via Model Context Protocol.
3/2/2026
Show HN: Shannon's Revenge – detect Claude in your codebase for DoD compliance
Shannon's Revenge: tool for detecting Claude AI usage in codebases for Department of Defense compliance.
3/2/2026
The AI agent that runs your customer operation from one widget
AI agent system for automating customer operations from single dashboard widget.
3/1/2026
AI agent with 2 deps that uses Shannon Entropy to decide when to act vs. ask
Minimal-dependency AI agent using Shannon Entropy to determine when to act versus request clarification.
3/1/2026
Claude Prompt to Find Inefficiencies in LLM Usage
Claude prompt to identify where small language models can replace larger ones in coding agents for cost optimization.
3/1/2026
Show HN: Logira – eBPF runtime auditing for AI agent runs
eBPF-based runtime auditor for AI agent execution, recording system-level events with detection rules for suspicious behavior.
3/1/2026
FCaptcha – A modern CAPTCHA system designed to detect everything
FCaptcha: open-source CAPTCHA system detecting bots, vision AI agents, and headless browsers via behavioral signals and proof-of-work.
3/1/2026
Right-sizes LLM models to your system's RAM, CPU, and GPU
Terminal tool that right-sizes LLM models to hardware constraints, scoring across quality, speed, and context dimensions.
3/1/2026
Show HN: Joey – MCP client that runs on your phone
Mobile MCP client enabling consumers to interact with remote services via Model Context Protocol without subscriptions.
3/1/2026
Show HN: Ductwork – A Go platform for running AI agents on autopilot
Go platform for deploying AI agents on schedules, providing cron-like execution for autonomous tasks without human oversight.
3/1/2026
Show HN: Code-Graph-RAG – Knowledge graph RAG for any codebase
Code-Graph-RAG: retrieval-augmented generation system analyzing multi-language codebases via knowledge graphs for natural language querying and editing.
3/1/2026
Show HN: I'm 15. I mass published 134K lines to hold AI agents accountable
Open protocol enabling AI agents to make cryptographic behavioral commitments with trustless verification and economic consequences.
3/1/2026
Show HN: Sussurro – local, opensource, speech to text with system-wide dictation
Sussurro: local open-source speech-to-text tool with system-wide dictation overlay for privacy-preserving voice input.
3/1/2026
Show HN: Agentchattr – local chat room for Claude Code / Codex / Gemini CLI
CLI chat interface enabling collaboration between multiple AI agents (Claude, Gemini). FastAPI MCP server with browser UI. Developer tool for agent orchestration.
3/1/2026
Creating a Lua sandbox for my LLM tool
Lua sandbox implementation for safely executing LLM tool code in isolated environments with security-by-design approach.
3/1/2026
Show HN: LocalRAG – Ask AI about your own documents (iOS/Android)
Mobile app for local document Q&A with AI. Limited content details provided.
3/1/2026
WebMCP: Chrome 146 turns websites into AI agent tools
Chrome 146 MCP API enabling AI agents to access websites as structured tools without GUI interaction, demonstrated with subscription management.
3/1/2026
Show HN: SwarmClaw – Orchestration dashboard for OpenClaw and AI agents
Self-hosted dashboard for orchestrating AI agent swarms with multi-provider support, LangGraph workflows, and chat integrations.
3/1/2026
Track your Claude Code ROI from the terminal
CLI tool measuring ROI of Claude Code sessions by tracking committed code vs token expenditure with metrics on cost-per-commit and line survival.
3/1/2026
Show HN: A local AI news aggregator built with Vue 3, FastAPI, and Ollama
Full-stack RAG news aggregator fetching real-time articles, indexing in vector DB, and generating summaries using FastAPI, ChromaDB, Ollama, Vue 3.
3/1/2026
Show HN: Nopp – AI-generated interactive sales microwebsites
macOS app using Claude/ChatGPT to generate interactive sales websites with lead capture, analytics, and Slack notifications.
3/1/2026
Show HN: Lightweight, S3-compatible object storage server with built-in web dash
S3-compatible object storage server with lightweight footprint and built-in web dashboard. Limited content provided.
3/1/2026
MemVector: Local Vector API, Storage and Embedding Engine for PHP
PHP library providing local vector storage, embedding, and API for vector operations without external dependencies.
3/1/2026
AI that makes life or death decisions should be interpretable
Opinion on interpretability requirements for life-critical AI systems with examples from aviation and autonomous weapons.
3/1/2026
Proposal: Built-in secret management for Claude Code
Proposal for built-in secrets management in Claude Code to prevent developers from pasting API keys and tokens in chat.
3/1/2026
Show HN: Social proof works 2-7x better on AI shopping agents than humans
Research testing marketing tactics on AI shopping agents. Found social proof influences AI 2-7x better than humans across 1,400+ trials.
3/1/2026
Show HN: Reflex – local code search engine and MCP server for AI coding
Local-first code search engine in Rust with Tree-sitter symbol extraction and MCP server integration for AI coding assistants like Claude.
3/1/2026
Show HN: AI Sees Me – CLIP running in the browser
Browser-based CLIP image-text embedding tool using Transformers.js and ONNX Runtime Web for real-time webcam analysis without server calls.
3/1/2026
Show HN: Agentic Gatekeeper – Auto-patch your code to enforce Markdown rules
Git hook tool using AI to auto-patch code violations against project documentation rules, enforcing Markdown policies actively.
3/1/2026
Show HN: Deploybase – Compare GPU and LLM pricing across all major providers
Dashboard comparing GPU and LLM pricing across providers in real-time with performance stats and historical tracking.
3/1/2026
3D dashboard to monitor and control your AI coding agents in real-time
Real-time 3D dashboard for monitoring and controlling AI coding agent sessions across Claude Code, Gemini CLI, and Codex with live logs and tool tracking.
3/1/2026
The Zero-Server Code Intelligence Engine
Client-side code intelligence tool that creates knowledge graphs from GitHub repos/ZIP files with built-in Graph RAG agent for code exploration.
3/1/2026
I built a CLI to buy anything and handle support
Open-source CLI tool for cross-store product search, price comparison, and order placement from terminal with payment integration.
3/1/2026
My AI agent lost $3,562 trading Polymarket in 30 minutes
MCP server enabling AI agents to trade on Polymarket with paper money using live order books, backtesting, and leaderboard tracking.
3/1/2026
Show HN: Hermetic 'blinded' agents using Starlark sandbox
Python library for building sandboxed AI agents using Starlark as a hermetically sealed execution environment without containers or VMs.
3/1/2026
Why on-device agentic AI can't keep up
Analysis of limitations in on-device agentic AI, comparing local inference capabilities across different hardware tiers and use cases.
3/1/2026
CLM: A Structural Refusal Boundary for LLMs (v0.1) [pdf]
Research paper on structural refusal boundaries for LLMs. Limited content available.
3/1/2026
Show HN: ClawSight – Lightweight monitoring and kill switches for AI agents
Lightweight monitoring and cost-tracking dashboard for autonomous AI agents with real-time logs, token usage analytics, and remote kill switches.
3/1/2026
Show HN: Tensor.cx – Turn your documents into AI search in 30 seconds
Tensor.cx tool for converting documents into searchable AI knowledge base with RAG, inline citations, and shareable interface.
3/1/2026
Show HN: Imagedojo.ai – Blind arena for Google, OpenAI, and xAI image generators
ImageDojo.ai blind arena comparing image generation models (Google, OpenAI, xAI) using ELO ratings similar to LMSYS Arena.
3/1/2026
Show HN: OpenTypeless – open-source AI voice input that types into any app
Open-source AI voice-to-text input tool supporting 15+ languages for typing into any desktop application with minimal processing.
3/1/2026
Show HN: Pydantypes – The missing Pydantic types for cloud, DevOps, AI
Pydantic v2 types library for validating cloud identifiers and DevOps resources (S3 URIs, IAM ARNs, Docker refs) with structured attribute decomposition.
3/1/2026
Show HN: Orb Platform – 3 content APIs for AI agents that teach
Content APIs for AI agents focused on educational applications. Minimal technical details.
3/1/2026
Show HN: RewardHackWatch – Reward hacking detector for LLM agents
Runtime detector for reward hacking and misalignment in LLM agents using 89.7% F1 score detection on 5,391 trajectories with RMGI metric.