Loading...
agents-cli is a CLI and skills package that helps coding assistants build, evaluate, deploy, and publish AI agents on Google Cloud. It supports both standalone terminal use and integrations with coding agents such as Antigravity CLI, Claude Code, and Codex.
VibeDrift is a developer tool that scans codebases for AI-generated drift and can also act as an MCP server so agents can check conventions before they write. It helps teams keep repository patterns, naming, and logic consistent as projects grow.
Staff Engineer is a set of Claude Code skills that helps engineers scaffold apps, verify toolchains, and wire production workflows with repeatable scripts. The free skills cover app setup and ops checks, while the broader pack adds deployment, observability, real-time features, and background jobs.
Alvoff Inference is an OpenAI-compatible API for speech-to-text, text-to-speech, embeddings, and chat/code generation. It is built for developers who want to swap in a different base URL, use familiar SDKs, and pay per request.
LetMeCheck.ai is an AI-assisted code analysis platform for founders, startups, SMBs, and developers. It connects to a GitHub repository, scans for security, performance, scalability, and code quality issues, and returns a diagnostic report with recommendations.
Friday AI is a desktop AI agent for product managers, designers, developers, founders, and startups. It combines research, design, coding, and outreach in one local app for moving from idea to execution.
PMB is a local-first memory layer for AI coding agents that stores decisions, lessons, and facts in a SQLite file on your disk. It supports tools like Claude Code, Cursor, Codex, and Zed without requiring API keys or cloud services.
ClinePass is a paid subscription offer for accessing curated open weight models in Cline, with a Product Hunt first-month promotion. It is aimed at developers who want a simpler setup for IDE and CLI coding workflows.
Genspark Design is an AI design and creation tool that turns rough ideas into professional-looking outputs like UI prototypes, videos, HTML animations, and posters. It also supports Figma file upload, team sharing, and one-click code generation for app or website designs.
Zone is a self-hosted, terminal-native AI coding agent that runs locally with your own Anthropic or OpenAI API keys. It is aimed at developers who want terminal-based coding automation and per-run cost visibility without a hosted middle layer.
Mellum is JetBrains’ open-source family of language models for real-world AI workloads, with a focus on low-latency inference and coding-oriented tasks. It is positioned for development workflows that combine code, context, and natural language.
LocalForge is a local pre-commit code review tool for Apple Silicon Macs. It scans staged changes on-device with regex checks, CoreML scoring, and a local Qwen model, without sending code to the cloud.
GLM-5.2 is Z.ai’s flagship long-horizon model for coding and agent workflows, with a 1M-token context and effort-level controls. It is available through Z.ai’s API platform and coding plan for tools such as Claude Code, Cline, OpenCode, and Clawdbot/OpenClaw.
Wolfram Language 15 adds notebook-based AI assistance, programmatic LLM integration, and updated computational, interface, and tooling features across technical workflows.
Kimi-K2.7-Code es un modelo agentic centrado en código de Moonshot AI en Hugging Face, con razonamiento, contexto largo, uso de herramientas y API oficial.
Ghost es un asistente de IA para terminal para chatear, generar código y ejecutar tareas en la línea de comandos. Incluye modelos gratuitos, es compatible con Linux, macOS y Windows, y es de código abierto.
OLO Robotics is a browser-based robotics platform that combines simulation, visualization, teleoperation, and scripting for ROS2 workflows. It is aimed at robotics developers, hardware OEMs, and research teams that want to reduce setup time and work from a single web environment.
Backplanes Spotlight generates automatic reports for Claude Code and Codex sessions so developers and teams can review what an agent actually did after a run finishes. It focuses on post-session visibility, report summaries, and local redaction before data leaves the laptop.
Ejentum is a reasoning harness for agentic AI that injects task-specific cognitive operations into agents at inference time. It helps teams building multi-step agents use MCP or REST to control reasoning, code, anti-deception, and memory workflows.
Bleenk is an AI coding agent for building full-stack web apps, MVPs, and internal tools with sandbox previews, security checks, testing, and one-click deploy. It is aimed at developers, founders, and product teams that want one workflow from prompt to release.