Tag
Fillo is a product that helps integrate forms into applications using a coding agent, handling backend infrastructure like validation, uploads, responses, versions, and delivery.
SWE-bench Multimodal v2.0 is released, featuring 480 tasks where coding agents must interpret visual assets like screenshots and diagrams to diagnose and fix bugs in repositories.
This article provides an in-depth review of ZCode, a desktop coding agent by Z.ai powered by the GLM-5.3 model, evaluating its features, workflow, cost, and performance on real projects.
Muse Code is a coding agent for terminal and CI that can plan, edit, and run commands with built-in approvals and sandbox. Muse Spark, an AI model, is now available on Meta Model API and integrated into Muse Code.
This article describes OpenAI's Codex CLI, a locally running coding agent that can be installed on various platforms and integrated with ChatGPT plans for AI-assisted development.
fx version 0.0.7 is released with hugely improved MCP support, enhanced shell execution, and a minimalist design for CLI agents.
This tweet announces the integration of Synterai into AmpCode, enhancing its AI harness with marketing skills and promoting a directory of agent skills for various industries.
A user complains about hitting usage limits quickly and experiencing performance degradation with Claude Code on the MAX 200 plan, comparing it unfavorably to other coding agents like Codex.
A developer shares their experience using local GLM 5.3 Flash for product development and mentions OpenAI ending its partnership with Cursor.
Staats is an agent-native, cookieless site analytics product that enables coding agents to measure deployments, flag changes, and provide evidence-based recommendations without dashboards or charts.
This paper investigates how changing the harness configuration in a coding agent impacts performance on coding benchmarks when the model remains fixed. The study shows that a treatment harness, which shortens older tool results to manage context, improves task completion rates, especially under tight context constraints.
Freebuff introduces a suite of free coding agent tools, including desktop, CLI, web, and cloud versions, supported by developer ads to replace paid alternatives like Cursor and Claude Code.
OpenAI Codex CLI is a local coding agent tool that can be installed via package managers or command line, integrated with IDEs, and used with ChatGPT plans.
This article presents a custom MCP setup that enables offloading coding tasks from Anthropic's Claude models to local Qwen3.8-27B models within the same session, using tools like llama.cpp.
OpenWiki 0.4.0 adds coding agent integrations with Claude, Codex, and OpenCode, simplifying setup for developers.
The author introduces Capstan, a lightweight coding agent with a C core and hot-reloadable Lua plugins, designed for efficiency and extensibility in development workflows.
The article describes a cost-efficient setup for AI coding agents by routing Claude Code through DeepSeek's API, leveraging prompt caching to significantly reduce token costs while maintaining high reasoning capabilities.
A heavily quantized Qwen3.8-27B model running on a 16 GB Quadro GPU successfully implemented a correct multilayer transfer-matrix method from scratch, despite extensive reasoning and debugging over 100 minutes.
The paper introduces Code World Model, a framework that combines language models for reasoning and coding with video models for visual rendering to simulate persistent world evolution in an open-ended manner.
Orbs are remote coding agents from Amp that allow users to run cloud-based development environments with features like portals, multiplayer collaboration, and scheduled execution.