A developer released an open-source reference implementation of an LLM agent that emits typed intents using a domain vocabulary, separating intent from execution. The project introduces the Structured…
Straw, a new tool, compresses large infrastructure data into a single markdown file, achieving a 99.5% reduction in LLM tokens by converting 3,774 log lines into 37 patterns, 746 topology edges into 1…
A developer created a Claude Skill based on the 37signals decision-making framework by Jason Fried, turning a static list of 38 questions into an adaptive conversational coaching tool. The Skill helps…
Lelu, an authorization engine for AI agents, detects prompt injection and low-confidence decisions to gate agent actions, offering four outcomes: allow, human review, compute (sandbox), or deny. The o…
Filaxy Herald is a new open-source tool that automatically generates build-in-public posts from GitHub activity, drafts them with AI, and sends them to Telegram for approval before posting to X. The s…
A developer published a guide to Claude Code's status line feature, a customizable bar at the bottom of the terminal that displays real-time session data such as model name, context usage, cost, and c…
Dale Francis Reding developed StyleSweeper for Draw Things, a professional-grade style sweeping engine that explores high-fidelity visual treatments across creative disciplines. The tool uses 11 style…
SparQ Soft released SparQ Pulse, the first fully open-source Developer Experience suite for GitHub-native teams, offering self-hosted project management, async standups, and team presence features. Th…
PrismorSec released immunity-agent, an open-source runtime security tool that intercepts AI agent actions before they reach the operating system. It blocks prompt injection, malicious packages, and se…
A developer has created a small LLM that runs inside MIT's Scratch by compiling the llama2.c inference code to Scratch blocks using llvm2scratch. The project, called LLM from Scratch, allows users to …
OpenClaw-memgpt, a new plugin for the OpenClaw agent framework, implements MemGPT's three-tier memory architecture—core, recall, and archival memory—to provide persistent, searchable memory across ses…
StockValuation.io launched a local valuation workflow for AI coding agents Codex and Claude, enabling them to research companies, gather evidence, and produce educational DCF valuation reports. The to…
A developer built an inbox manager using n8n that handles sales, HR, customer support, and job application emails. The workflow uses a Gmail trigger, OpenAI's GPT-4o-mini to classify and route emails,…
AI-whisper, a new open-source tool, pairs two coding agent CLIs—such as Claude, Codex, or ezio—in a terminal-native workflow where one agent implements code while the other reviews it, autonomously it…
A developer released a comprehensive, verified reference for Substack's undocumented internal API, mapping 129 endpoints through 14 rounds of probing. The open-source repository includes an OpenAPI 3.…
Mario Guerra released Orchid, a zero-instrumentation proxy for local-first debugging of AI agent pipelines. The tool captures API and LLM calls, enabling step-by-step replay and inspection without clo…
A developer released two open-source templates for Claude Code and OpenAI Codex that prevent AI coding agents from forgetting project context by storing rules and decisions in files and automatically …
RapidThought Labs launched Heku, a single MCP server that dynamically serves tools via JSON configs, eliminating context bloat by lazy-loading only the tools an LLM needs. The open-source tool support…
Parley, a new CLI and MCP server, enables local multi-model deliberation by fusing answers from multiple AI coding agents like Claude, Codex, and Gemini into a single response, providing consensus or …
A developer built Robot, a local AI deck music assistant on a Mac mini that uses Open WebUI, Ollama, Flask, AppleScript, Airfoil, Chrome, and Apple Shortcuts to control outdoor speakers and play YouTu…