Coding Agents

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

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

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.

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.

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.

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.

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.

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.

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.

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

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

The fastest LLM inference API on earth. LPU (Language Processing Unit) hardware runs Llama 4, DeepSeek R1, Gemma 3, and Mixtral at 1000+ tokens/second.

Anthropic's agentic coding tool for terminal and IDE. Understands full codebases, executes commands, handles git workflows. Uses Claude Opus 4.6 for complex multi-file reasoning.

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...

Most autonomous AI software engineer. Assigns tasks, writes code, runs tests, opens PRs. Repriced to $20/mo Core + $2.25/ACU. 67% PR merge rate on defined tasks.

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

Enterprise AI code assistant with zero data retention. 1M+ developers. Private deployment options on-premises or VPC. GDPR, SOC 2, and HIPAA compliant.

AWS's AI coding assistant. Generates, debugs, tests, and documents code. Security scanning, codebase transformation, and AWS console question answering.

The fastest AI code autocomplete. 1M-token context window, sub-100ms latency predictions. Used in Cursor's autocomplete engine. VS Code and JetBrains.

Enterprise AI coding agent (Auggie). Highest SWE-bench score using Claude Opus 4.5. Context Engine indexes your entire codebase and org knowledge.

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

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

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...

#24

ai-marketing-agent

by enji

10

score

Search Enji’s blog, Q&A, and help center to find grounded, source-backed answers to small-business marketing questions. Generate customer personas, brand voice summaries, and tailored social and blog ideas to plan content faster. Access free resources and tools to stay consistent

ADHDev — Agent Dashboard Hub for Dev. Remote-control AI coding agents from anywhere.

Fast-mode variant of [Opus 4.6](/anthropic/claude-opus-4.6) - identical capabilities with higher output speed at premium 6x pricing. Learn more in Anthropic...

Detect if code is running in an AI agent or automated development environment

Glin-Profanity is a lightweight and efficient npm package designed to detect and filter profane language in text inputs across multiple languages. Whether yo...

Browser-compatible PQC encryption SDK for QNSP. Client-side encryption, signing, and key encapsulation using NIST FIPS 203/204/205 standards via @noble/post-...

Coding agent CLI with read, bash, edit, write tools and session management

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token ...

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window...

Beads issue tracker - lightweight memory system for coding agents with native binary support

nlux is JavaScript and React library for building conversational AI interfaces, with support for OpenAI, Hugging Face, and more.

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

Unified LLM API with automatic model discovery and provider configuration

AI context infrastructure for coding agents — keeps CLAUDE.md, Cursor rules, and skills in sync as your codebase evolves

Themes and CSS files for nlux, the JavaScript and React library for building conversational AI interfaces.

Terminal-first coding agent — runs locally with Ollama, DeepSeek, OpenAI, or any OpenAI-compatible endpoint

Plannotator plugin for OpenCode - interactive plan review with visual annotation

nlux React is a library for building conversational AI interfaces, with support for OpenAI, HuggingFace, and more.

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...

NVIDIA Nemotron 3 Nano 30B A3B BF16 — a text-generation model by undefined on HuggingFace. 1,382,040 downloads, 707 likes.

#44

Next.js Tailwind Assistant

by CaullenOmdahl

8

score

Your comprehensive AI companion for building modern Next.js applications with React and Tailwind CSS. This MCP server provides instant access to complete doc...

#45

Transcriptor

by samson-art

8

score

An MCP server that fetches video transcripts/subtitles via yt-dlp, with pagination for large responses. Supports YouTube, Twitter/X, Instagram, TikTok, Twitc...

#46

Icons8 MCP Server

by icons8community

8

score

🚀 Access MCP server SVG and PNG icons for your vibe-coding projects! 🎨 Icon Packs * 40,000+ icons * Endless creative possibilities! 🤖 Seamless Integrati...

#47

SecDim Secure Coding Labs

by pi3ch

8

score

Find hands-on secure coding labs for vulnerabilities like XSS, SQL Injection, and OWASP Top 10 topics. Get a personalized learning pathway based on your GitH...

#48

NGSS Standards Explorer

by Sallvainian

8

score

Search and retrieve NGSS standards by code, domain, or topic. Explore three-dimensional components (SEPs, DCIs, and CCCs) and discover related standards by s...