Tofu launched a code deployment platform that lets MCP-compatible AI agents take a project from code to production, according to founder's Show HN post. Tofu provides frontend and backend hosting, a m…
Moonshot AI released Kimi Code Desktop, a desktop client for Kimi Code that lets users open a local project and have an Agent read and modify code through conversation, with file previews, change trac…
Adios launched a hosted MCP service that lets coding agents build, preview, debug, and deploy apps from clients including Codex, Claude Code, Gemini CLI, Kimi Code, GitHub Copilot, and ChatGPT. The se…
Kimi released K2.8 Preview on September 11, 2026, a Kimi Code model documented behind the ID kimi-for-coding with up to 1M context across membership tiers and a default reasoning setting of max, accor…
A new cross-platform desktop app called Maestro runs multiple CLI coding agents — including Claude Code, Codex, Cursor, OpenCode, Kimi Code, and Grok Build — in parallel, each in an isolated git-workt…
A developer built GroundControlAI, an open-source real-time observability daemon that aggregates local telemetry from AI coding agents including Claude Code, Kimi Code, and Google Antigravity into a c…
Runta's FrontierHarness v1.0 benchmark, evaluating nine harnesses across 12 configurations on software development and terminal tasks, found pass rates ranging from 50.0% to 66.7% but cost per complet…
FrontierHarness Eval, a new benchmark from Runta, tested nine AI coding harnesses on the same model and found median cost per successful task varies by 17x, with Claude Code v2.1.237 passing 19 tasks …
A developer tested session-migrate 0.8.0 by transferring a frozen Claude Code session into seven target formats, finding that conversation and tool context transferred well but organizational controls…
Jean, an open-source development environment for AI-assisted coding, is available under the Apache 2.0 license, free forever with no paid tiers or feature gates. It enables running multiple AI agents …
Chaitanya Giri's Munder Difflin v0.4.5 fixes inaccurate cost reports, broken semantic memory on Apple Silicon, and unreliable communication between AI workers in the local-first agent harness that wra…
A census of 12 coding-agent command-line interfaces found that file-write permission defaults in headless mode split three ways: 7 ask or propose until a flag is passed, 2 refuse to write until flagge…
Moonshot released the weights for its 2.8-trillion-parameter Kimi K3 model on July 27, 2026, 11 days after launching the model across Kimi, Kimi Work, Kimi Code, and the Kimi API, extending CEO Yang Z…
Cosyncing, a new open-source tool, lets users synchronize and control coding agents such as DeepSeek Harness and Claude Code from a phone or desktop via a local broker, with no hosted service. The bro…
A documentation census of 17 coding agents and harnesses, published on August 17, 2026, found that all 17 transmit code off the local machine in at least one common configuration, and 8 of 17 rows are…
A developer has documented a workaround for running Kimi Code's K3 model inside Anthropic's Claude Code terminal tool, addressing configuration pitfalls including a misleading model ID and authenticat…
Maestro, a new desktop app for Windows, Linux, and macOS, lets developers run Claude Code, Codex, Cursor, OpenCode, and Kimi Code side by side in separate git worktrees, with a rail showing who's work…
Kimi K3, an AI coding model from Moonshot AI, built a playable first-person 3D browser game from a single prompt, but the game had bugs that only surfaced during human play, such as a drone clipping t…
Kota, an open-source tool that enables AI agent CLIs to collaborate in a shared workspace, was released by its creator after months of personal use. It supports Codex, Claude Code, Pi, OpenCode, Gemin…
A developer reports that the gap between AI models and their agentic performance is often determined by the harness—the system around the model—rather than the model itself. Evidence from Moonshot's K…