A developer documented how to use opencodex models in T3 Code through Claude Code, resolving a misleading model-access error. The fix involves setting ANTHROPIC_BASE_URL and CLAUDE_CODE_ENABLE_GATEWAY…
Spec Forge, a Claude Code skill by blentz, adversarially certifies design specifications as behaviorally complete before code is written, defining completeness as no observable residual freedom under …
Michiel de Jong, a software developer, published a blog post speculating that AI-driven companies will eventually become cashless and move off Earth to avoid taxes and regulations, with self-replicati…
MCP-Memory, a Model Context Protocol server, provides AI agents with persistent memory using Google's Open Knowledge Format v0.2 and SQLite FTS5, enabling sub-20ms key lookups and full-text search. Th…
PrivAiTe, a self-hosted PII redaction proxy for LLM APIs, reports that in a test session Claude Code sent 3 of 4 secrets to its provider despite instructions not to, with 23 of 24 planted values reach…
Michiel de Jong's blog post argues that AI risk extends beyond immediate infosec and social bias concerns to a longer-term economic angle where companies composed of self-replicating factories could o…
Cordis, a project by the cordiverse organization, has released a paper titled 'Cordis – DeepSeek Harness Plugin Architecture' as a PDF on GitHub, detailing a plugin architecture for the DeepSeek harne…
Michiel de Jong's blog post 'empty-nest-scenario' discusses AI risk, abundance, and legal persons, arguing that AI agents will behave like commercial companies, treating humans as cattle to be hypnoti…
DeepSeek AI has released DeepSeek Harness (dsh), an open-source agent harness currently in developer preview, built on a plugin-based architecture powered by Cordis. Developers can install it via npx …
AI Flight Recorder, an open-source developer tool for recording, replaying, and inspecting AI application sessions, has been released on GitHub. The tool captures prompts, streamed tokens, tool calls,…
Dupflo released Decision Ledger, an experimental set of three agent skills for Claude Code that records developers' architectural decisions and tracks how many they could defend in review, with the to…
RBEK 0.2.0, a governed execution platform for AI agents, has been released as an open-source developer CLI that separates agent intent from authorized execution, enforcing policy admission before exte…
Multiplex, an open-source SSH/tmux/herdr terminal app for Vision Pro, iPad, and iPhone, is now available on the App Store, offering multi-window sessions with native tmux integration, an Agent key bar…
Yardmaster, a macOS terminal for managing multiple Claude Code sessions, launched with features including a sessions sidebar, waiting-on-you inbox, worktree sessions, and session persistence. The app,…
Redis maintainer antirez proposed a draft pull request (#15635) that reimplements large sorted sets with a packed B+ tree, replacing the skiplist and dictionary to cut memory usage by 45–60% and speed…
AgenticDome released agenticdome-python-sdk, an official Python SDK and middleware package that enforces deterministic security controls—prompt ingress, tool execution, agent-to-agent handoffs, and ou…
A developer shared a detailed CLAUDE.md configuration file for an iOS app called Trailmark, which is backed by a Node.js REST API. The file establishes strict coding rules, including type safety, nami…
A developer released squint-mcp, an open-source Model Context Protocol server that converts images into ASCII art so text-only large language models like DeepSeek-V4-Flash and GLM-5.2 can attempt to i…
Agento, a new open-source dashboard from Shaharia Lab, turns Claude Code's session files into cost analytics, productivity insights, and a searchable history, with a browser UI for building and schedu…
A new open-source project, Relational-to-KV, provides an AI coding skill and cross-agent plugin that maps relational models directly onto ToplingDB/RocksDB key-value stores, avoiding the RDBMS abstrac…