A new Claude Skill called vc-teardown, available for download from GitHub, stress-tests startup ideas by researching incumbents, attacking the idea with investor-style objections, and rebuilding it in…
A developer used Anthropic's Claude to build TrueScreenTime, a minimal Android app that reconstructs accurate foreground time from UsageEvents and lets users include or exclude specific apps from a cu…
The Awesome-FDE-Roadmap, a comprehensive guide for Forward Deployed Engineers (FDEs), outlines the hybrid role of software engineer, AI/data architect, and strategic consultant, emphasizing the need t…
A new open-source token budget circuit breaker, called Paradox, cuts multi-agent retry waste by 98.3%, reducing token consumption from 49.44 million to 817,500 in a benchmark harness with 100 agents, …
A developer released Yet Another OpenCode Plugin, an opencode plugin that adds terse response modes, a YAGNI-based 'lazy dev' ruleset, and two read-only agents (Review and Dream) to the opencode AI co…
A developer released renovate-log-parser, a CLI tool that detects and analyzes problems in Renovate Bot debug logs, with commands for CI pipelines, coding agents, and a web interface. The tool aims to…
Swiftlet, a Swift + Metal runtime for Qwen3-Next and Qwen3.5/3.6 MoE hybrid models, runs an 80B Qwen in 4.3 GB of RAM on a Mac and a 35B on an iPhone 17 in about 2.5 GB of RAM at about 1 token per sec…
OpenAI's Codex CLI implements context compaction via a server-side encrypted blob rather than client-side summarization, according to a developer's analysis of the Codex source code and live captures.…
A non-engineer running OpenAI's Codex 5.6 Sol autonomously for 15 days has consumed 8.2 billion tokens and is about a month from completion, with the build publicly available at github.com/nelsonwerd/…
Rudder, a new Apache-2.0 licensed plugin for Codex and Claude Code, aims to help developers regain ownership of AI-generated code by forcing agents to rewrite unit tests based solely on user intent, t…
DamiMartinez released book-skills, an open-source collection of Claude Code skills that encode methodologies from management and programming books such as The Lean Startup, High Output Management, and…
Driftty, a mobile-focused web TTY layer built on ttyd, introduces a real editable text field to enable speech-to-text and easier editing for coding agent CLIs, addressing limitations of terminal UIs. …
A developer has created the Knowledge Pack Generator v3, a tool that transforms long AI chat conversations into adaptive Markdown documentation with Mermaid diagrams, preserving knowledge instead of c…
Headroom, a new browser extension, provides a real-time visual gauge of context window usage in AI chat conversations, warning users before the AI forgets earlier information. It supports DeepSeek, Ch…
MinerU, a high-accuracy document parsing engine for LLM, RAG, and Agent workflows, released version 3.4 on 2026/06/18, upgrading the pipeline backend's OCR model to PP-OCRv6, which improves OCR accura…
HOM-AIMOS, a local-first persistent-memory backend for AI agents, retains poisoned data instead of deleting it, using a signed, append-only provenance system that adjusts retrieval weights within [0.1…
Rescene, a free AI agent aggregator, has been released, requiring no API key. It aggregates 7 free providers and 18 model entries, featuring intelligent routing, browser automation, and Computer Use, …
Nexurate Technologies, an AI-powered digital marketing and automation agency based in Coimbatore, Tamil Nadu, India, offers AI CRM, WhatsApp automation, AI chatbots, voice AI, and SEO services for SME…
Angeliasrl released norms-mcp-engine version 0.1.0, a fail-closed evidence engine that computes the evidentiary status and admissibility of norms used by AI agents, without any I/O, network, or transp…
Runthru, an open-source tool for creating interactive demos and walkthroughs of web-based software, was released on Hacker News by its developer. The tool allows users to point it at a site and either…