Coding Agents

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agent...

DeepSeek R1 0528 NVFP4 V2 — a text-generation model by undefined on HuggingFace. 1,651,442 downloads, 23 likes.

AI data analyst. Upload CSV, Excel, SQL databases — get visualizations, insights, and statistical analysis in plain English. No coding required.

Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality ...

Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and o...

DeepSeek's open reasoning model that rivalled o3 at <10% the cost. MIT licensed. 671B MoE. Distilled versions (7B-70B) run on consumer hardware.

StackBlitz's browser AI that generates, runs, and deploys full-stack web apps in seconds. Prompts go straight to production code — no local setup required.

Open-source AI code assistant for VS Code and JetBrains. Bring your own model (Ollama, OpenAI, Anthropic, Gemini). 2.5M installs, completely customizable.

Run any open-source LLM locally on macOS, Linux, or Windows with a single command. 300+ models. No API key, no cloud. Privacy-first local AI infrastructure.

Open-source AI pair programmer in your terminal. Edit whole codebases, auto-commit changes with git, and use any LLM including local models. 20K+ GitHub stars.

Kimi K2 Instruct 0905 — a text-generation model by undefined on HuggingFace. 1,750,197 downloads, 711 likes.

AI-native code editor acquired by Cognition AI (Devin) for $250M. Cascade agentic AI with full codebase awareness, background agents via git worktrees, and Memories for context persistence.

Multi-agent software company simulator. GPT agents as CEO, PM, and engineer collaborate to build full software projects from one prompt.

Vercel's AI UI generator. Describe a component, get production-ready React + Tailwind + shadcn/ui code. Used by 2M+ developers to scaffold interfaces instantly.

Replit's browser-based AI that builds, runs, and deploys full-stack apps from a prompt. 30M+ developers. Ghostwriter AI completes, explains, and transforms c...

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimi...

KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS inte...

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video...

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around m...

China Unicom's Yuanjing Wanwu Agent Platform is an enterprise-grade, multi-tenant AI agent development platform. It helps users build applications such as in...

AI-first code editor with credit-based pricing. Composer for multi-file edits, background agents, and the fastest autocomplete (Supermaven). Built on VS Code, used by 360K+ paying developers.

GitHub's AI pair programmer integrated into VS Code, JetBrains, and Neovim. Agent mode for multi-file edits, Copilot Workspace for issue-to-PR workflows. Powered by GPT-5 and Claude Sonnet 4.6.

NocoBase is the most extensible AI-powered no-code/low-code platform for building business applications and enterprise solutions.

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, ...

No-code predictive AI. Connect any data source, train an ML model in 2 minutes, and get predictions on churn, sales, fraud, and pricing without any code.

Open-source AI coding extension with 5M VS Code installs. BYOM at provider rates — zero markup. Plan + Act modes. Samsung Electronics rolling out org-wide.

Google's async AI coding agent that works directly in GitHub. Assigns issues, clones repos, writes code, runs tests, and opens PRs — all without human interv...

Mistral's dedicated coding model. 80B parameters, trained on 80+ programming languages. Fill-in-the-middle, instruction following, and test generation. Free ...

Fulling is an AI-powered Full-stack Engineer Agent. Built with Next.js, Claude, shadcn/ui, and PostgreSQL. Use kubernetes as infra.

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, a...

The simplest desktop client for OpenClaw 🦞 — bridge your Agent to WeChat, Feishu, Slack & Discord in one click. Works with Claude Code, Codex & any LLM. BYO...

《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站：

🇨🇳 OpenClaw中文用例大全 | 49个真实场景 | 国内特色 + 海外案例的国内适配 | 自动化办公·内容创作·运维·AI助理·知识管理 | 新手友好 | Chinese guide for OpenClaw AI agent use cases

Zero-Config Code Flow for Claude code & Codex

Open-source, secure environment with real-world tools for enterprise-grade agents.

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you l...

The Frontend Stack for Agents & Generative UI. React + Angular. Makers of the AG-UI Protocol

"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"

MiMo-V2-Omni is a frontier omni-modal model that natively processes image, video, and audio inputs within a unified architecture. It combines strong multimod...

Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and...

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability an...

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration....

[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2....

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni ...

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular...

Qwen2.5 Coder 14B Instruct AWQ — a text-generation model by undefined on HuggingFace. 1,805,446 downloads, 19 likes.

Lovable (formerly GPT Engineer) turns natural language into full-stack web apps. Edit live in browser, connect Supabase, and deploy with one click.

Single API for 200+ AI models from every major provider. One key, one format, automatic routing to cheapest/fastest model. 500K+ developers.