Sentinel, a new open-source tool, scans codebases of up to 25,000 files in 55 seconds to generate structured, token-efficient context packs for AI coding agents. It operates entirely offline with zero…
A developer audited three AI coding tools—Claude Code, Cursor, and Cline—for privacy and found that all archive conversations in local plaintext without informing users. Claude Code stored 43MB of con…
A developer discovered that Claude Code, an AI coding assistant, secretly stored 43 MB of conversation data, including code snippets, file paths, and even password queries, in local directories withou…
A developer explains that 'Bring Your Own Model' (BYOK) in AI tools means supplying your own model and API credentials, giving control over cost, avoiding model lock-in, and keeping data relationships…
Z.ai (formerly ZhipuAI) launched GLM-5.2, an open text model with a 1M-token context window and up to 128K output tokens, designed for long-horizon coding agents and full-repository tasks. The model u…
NVIDIA offers over 100 AI models for free through its NVIDIA NIM service at build.nvidia.com, providing developers with an alternative to paid subscriptions like Cursor's $20/month plan. Users can sig…
Oracle's managed MCP server for database queries works with desktop AI clients like Claude Desktop and VS Code Cline, but fails with server-hosted web UIs due to OAuth discovery issues. A developer su…
Anthropic released agent-stdlib, a standard library for building AI agents that packages Claude Code skills, MCP servers, and a tool-gating hook derived from its engineering blog. The library includes…
A high school student in Italy built TITAN (Token Intelligence Through Agent Narrowing), a zero-dependency CLI framework that compresses AI coding agent token consumption by 70% to 85% without degradi…
GitHub Copilot's switch to usage-based billing on June 1, 2026, has caused bills for power users to jump 10x to 50x, with developers reporting monthly costs rising from $29 to $750 or $50 to $3,000. T…
Burpwn, a transparent intercepting proxy and execution sandbox for AI agents, has been released in early development. The tool allows autonomous agents to perform web pentesting with full TLS-MITM, tr…
A new open-source project called Ponytail reduces AI agent code output by 80-94%, cuts costs by 47-77%, and speeds up execution 3-6× by enforcing a lazy, minimalist coding philosophy that prioritizes …
Z.ai released GLM 5.2 on June 13, offering a 1M-token context window and compatibility with Claude Code and other coding agents via an Anthropic-compatible API, coinciding with the shutdown of Anthrop…
A developer built sessionmem, a local-first MCP server that gives AI coding assistants persistent memory by injecting compact session summaries at the start of each new session. The tool reduces token…
TaskPrio has launched a task management system that lets AI coding agents pull work from a single ranked queue and execute it autonomously. The MCP-native tool allows developers to maintain one global…
Anthropic's Claude Code can be redirected to any compatible backend using a single environment variable, `ANTHROPIC_BASE_URL`, enabling caching, rate-limit pooling, multi-vendor routing, and audit log…
ProofLayer released version 4.3.0 of its open-source application security scanner for AI coding agents, adding critical security and reliability fixes including GitHub Actions now failing closed inste…
Cline released an open-source TypeScript SDK for embedding its agent runtime into custom scripts, products, and CI workflows. The SDK allows developers to build focused agentic applications, such as a…
A developer built Project Overseer, a file-driven project management system that enables AI agents to maintain context across sessions in OpenClaw, Claude Code, Codex CLI, Cline, and Gemini CLI. The s…
BoxAgnts has introduced a Rust-based AI Agent platform designed for desktop, edge, and security-sensitive deployments, offering compile-time safety and zero-runtime startup. The project argues that wh…