A developer replaced grep-based code review with a knowledge graph integrated via the Model Context Protocol (MCP), uncovering three bugs that vector search had missed. The graph retrieves code by str…
A developer released agent-memory, an open-source project that provides a shared memory layer for AI coding agents over the Model Context Protocol (MCP). The tool is fully local, using Ollama, Qdrant,…
Anthropic shipped Claude Code v2.1.248 on Thursday with a new `--restricted` permission mode that disables shell execution, web fetching, and project-level settings files, addressing the TrustFall vul…
ViteLens, an open-source developer tool for React and Vite, lets developers Ctrl+Click multiple UI elements on localhost to generate structured Markdown context tables for AI coding assistants like Op…
A new Mac utility called the LLM usage meter clips onto the screen edge to display real-time rate-limit usage for Claude Code and Codex, reading local CLI files without network calls or API keys. The …
A developer's own automation script was killing Instagram login sessions nightly, disrupting a revenue-generating account. The issue stemmed from two separate repositories sharing the same Chrome prof…
Memnest, a new local-first memory tool for AI coding agents, lets pi, Claude Code, and Codex share durable memory across sessions via a single MCP contract. The Rust-based service, which runs entirely…
A developer released Caveman, a skill/plugin for AI coding agents that forces them to communicate in terse 'caveman-speak' to reduce output tokens and improve developer focus. The project claims a 65%…
A developer measured the token cost of their Claude Code configuration and found that 107 skills, 38 agents, and 15 commands consume 9,857 tokens in every session before any input is typed. The develo…
A developer has built Jeffy Loop, a coding agent for Claude Code that enforces a disciplined audit-fix-verify workflow, preventing the model from claiming success without independent verification. The…
CRBRO, a free and open-source (MIT) local MCP server, provides persistent long-term memory for AI agents using a biological neural architecture and file-based storage, with all 22 tools included at no…
A developer has created a three-file design to verify AI agent work, addressing the problem of agents like Codex and Claude Code claiming completion without actually making changes. The system uses se…
A developer reports that a custom 'harness' around Claude Code reduced effective token costs by a factor of 6.94 over 29 days, allowing the AI coding agent to handle more work before hitting usage lim…
A census of 16 surfaces across 11 coding agent harnesses, read on August 30, 2026, found that only four harnesses ship a documented credential-scoping primitive, and only one of those four does anythi…
A developer's benchmark of 22 GPT-5.6 Sol configurations found that High reasoning effort in Fast mode offers the best performance-cost-speed trade-off, scoring 57 on the Artificial Analysis Intellige…
A developer built a system that forces AI coding agents to log their reasoning and decisions into an Obsidian vault, synced across machines and a phone. The setup uses three hooks that inject context,…
A developer shared a tip for managing multiple Claude Code accounts on Linux by using the CLAUDE_CONFIG_DIR environment variable, which allows separate configurations and session states for work and p…
Developer lennney released Stop That Shit 0.1.0, an open-source guard that blocks coding agents like Codex, Claude Code, OpenCode, and Hermes Agent CLI from performing unrequested defensive work such …
Developers are abandoning Discord for structured AI community platforms because chat-based tools bury technical information, according to an analysis by PromptCube. The article compares Discord's poor…
Archify, a developer tool that enables AI coding assistants like Cursor and Claude Code to automatically generate verifiable architecture, workflow, sequence, and data-flow diagrams as self-contained …