Dream IDE, a desktop integrated development environment for managing multiple AI coding agents, has been released. The tool supports agent CLIs including Codex, Claude Code, OpenCode, and Cursor Agent…
A developer built Jean2, an AI coding agent that accumulates knowledge across sessions by writing to markdown files on disk instead of relying on vector databases or fine-tuning. The agent features fo…
Foreman, a self-hosted LLM gateway, routes requests to the cheapest model allowed by user-defined policies while maintaining deterministic behavior and prompt cache efficiency. The open-source tool su…
Dreamer, a new open-source tool, mines coding-agent session history to identify recurring corrections and proposes updates to context files like AGENTS.md or CLAUDE.md, requiring user approval before …
A developer surveyed coding agents to determine which support the disable-model-invocation frontmatter field, which prevents AI models from automatically loading skills. The survey found that Claude C…
OpenCode released data on real-world AI model usage, cache ratios, and costs, showing DeepSeek's v4-flash leading with 8.2T tokens, followed by DeepSeek v4-pro and Zhipu's glm-5.2. The data reveals sh…
A developer evaluated AI coding tools including web interfaces, custom IDEs, and VSCode extensions, finding Claude Code and Codex to be the most consistent and powerful options as of July 2026. The ar…
Moraine, a local trace stack for agent work, indexes sessions from agent harnesses such as Codex, Claude Code, Kimi CLI, OpenCode, Hermes, and Pi Coding Agent into ClickHouse, providing a unified loca…
A developer is using llama-cpp's tool-calling feature to let large language models execute system commands such as reading files and editing code, comparing the approach to bash scripting but easier t…
Can Celik's Herdr launched publicly on July 2, 2025, as an 'agent multiplexer' that runs multiple AI coding agents in persistent terminal panes, keeping them alive after the laptop closes and allowing…
Paseo, an open-source tool for orchestrating coding agents, launches with support for running agents across laptops, VMs, and phones via direct connection or encrypted relay. It integrates with provid…
A developer replaced Claude Code with open-source coding agent OpenCode for two weeks, finding it 78% slower but keeping it due to its model-agnostic design that unifies local and hosted AI models. Th…
Backlog, a local-first task and context manager for AI coding agents, has been released as an open-source tool that stores tasks, plans, and memory in a single SQLite file shared between humans and AI…
OpenGenie, a free and open-source AI-powered game engine, launched to let anyone build video games by describing them in plain language. The tool packages Godot 4, git, and an AI agent into a single a…
Cloudflare released official instructions for setting up AI development environments on its platform, providing validated commands to install Cloudflare Skills and MCP servers across multiple agents i…
Thoughtworks technologist Birgitta Böckeler tested running local large language models for agentic coding on Apple M3 Max and M5 Pro machines, finding that while RAM constraints limit model size to 15…
A developer shares a workflow for learning to code by building projects with AI coding agents like Claude Code, OpenCode, and Codex, arguing that software engineering remains a valuable skill even as …
Bastion, an open-source orchestrator for running background coding agents on self-hosted Linux infrastructure, was released. Each agent runs in a separate Cloud Hypervisor VM with a reproducible dev e…
A developer compares OpenCode and Claude Code for running AI models against codebases, favoring OpenCode for its open-source nature, git-native flow, and hybrid cost control, while acknowledging Claud…
A developer successfully runs the Qwen3.6-27B-FP8 model locally on an Nvidia DGX Spark, achieving reasoning, tool use, and multi-token prediction at 256K context, and uses it to ship real code for an …