Developer gs released tmux-agent-status, an open-source tmux plugin that shows coding agents' status only when they need attention, supporting Claude Code, Codex, opencode and pi. The plugin requires …
Spens, a new open-source tool for sandboxing and observing coding agents, launched on Hacker News, using Docker, nono and mitmproxy to create reproducible sandbox environments that capture all agent t…
The LFORLA Reverse Engineering benchmark scores language models on restoring C source from stripped binaries using deterministic token similarity against server-only references, with a fixed judge and…
The LFORLA Drone Build benchmark evaluates AI agents end to end, requiring models to plan a drone mission, source parts into a bill of materials under budget and physics constraints, assemble a build …
An anonymous "stealth" large language model called Space Bunny Alpha has been available on OpenRouter since September 2026, offering a 1,000,000-token input context window, up to 524,288 output tokens…
A developer benchmarked their AI coding agent Empryo against the rival agent pi on four real bug fixes drawn from the hono and opencode TypeScript repositories, with both agents fixing all four bugs o…
Drawgent is a new tool that connects a user's own Claude Code, Codex or opencode installation to a live Excalidraw whiteboard, letting the coding agent view the canvas via screenshot and scene data, e…
A developer released Sommelier, an Excel add-in plus relay server that lets an AI agent work alongside a user inside an Excel spreadsheet, inspired by the marimo pair tool. The add-in is sideloadable …
Developer Geoffrey Huntley released underclass, an OpenAI-compatible local proxy that pools multiple ChatGPT/Codex and GitHub Copilot subscriptions behind a single endpoint at /v1/responses, /v1/chat/…
AlphaDesk launched a market-research terminal that lets users query market data, SEC filings and US Treasury records through their own AI agent via 37 read-only MCP tools, with the code released under…
A developer released skilldiff, an open-source tool that tests agent skill files like SKILL.md for behavioral regressions by running them in a real agent harness against a fixture repo and asserting o…
A developer used the opencode AI coding agent to recursively scan a personal library of more than 350 programming books and resources, organizing them into 24 topic-based learning roadmaps with founda…
A developer released an open-source template for building deterministic models with structured reasoning, positioning it as an alternative to TypeSafe.ai. The template runs JavaScript rule functions t…
A developer released taskpods, a dependency-free Python CLI that uses Git worktrees to give each coding-agent task its own working directory, branch, and index within a shared repository. The tool wra…
Thurbeen released Thurbox, an open-source tmux-based TUI and headless CLI for running multiple coding-agent CLIs side by side, each in its own persistent tmux session and git worktree. Thurbox launche…
A developer released Polter, an MIT-licensed Ghostty fork with an MCP layer that lets any MCP-capable AI CLI act as a supervisor over other agent CLIs, opening tabs, typing into them, and reading thei…
A developer released minizinc-mcp, an MCP server that exposes MiniZinc constraint solving and optimization to LLM clients including opencode, Claude Desktop, and Cursor, letting agents parse, type-che…
Laravel has released Laravel Vet in beta, a Composer plugin that audits PHP dependencies by showing the code each `composer update` would write into `vendor/` and recording trusted packages in a `vet.…
Agentic coding TUIs including Claude Code, Codex, Aider, Crush, opencode, and Goose each ship their own slash commands, keybindings, pane layouts, and status lines with no shared conventions or docume…
A laid-off software developer used the 83 topics in Dan Vanderkam's book "Effective TypeScript" as hints fed to the opencode LLM agent to convert a personal JavaScript project to TypeScript, removing …