AI Dev Radar

Factory Droids are AI software-engineering agents from Factory that help teams plan, implement, review, test, and maintain code across the development lifecycle.

SWE-agent is an open-source framework for turning language models into software engineering agents that can inspect repositories, edit code, run tests, and attempt to resolve GitHub issues or benchmar

Windsurf Cascade is an agentic AI coding assistant integrated into the Windsurf developer environment that can understand a codebase, propose changes, edit files, and help developers complete multi-st

Cursor Agent is the agentic coding mode inside the Cursor AI-powered IDE that can understand a codebase, edit multiple files, run terminal commands, and help developers implement changes end-to-end.

Replit Agent is an AI-powered software-building assistant inside Replit that can turn natural-language prompts into working applications by writing code, configuring environments, installing dependenc

Google Jules is an asynchronous AI coding agent from Google that connects to GitHub repositories, plans code changes, edits files in a cloud environment, runs tests, and prepares pull requests.

Amazon Q Developer is AWS's AI coding assistant for IDEs, terminals, and AWS workflows that helps developers write, understand, transform, secure, and operate code and cloud applications.

Continue is an open-source AI coding assistant extension for VS Code and JetBrains IDEs that lets developers use customizable LLM-powered chat, autocomplete, code editing, and agent workflows with loc

Cline is an open-source AI coding agent for VS Code that can read and edit files, run terminal commands, inspect browser output, and complete multi-step development tasks with human approval.

Windsurf is an AI-powered coding IDE from the Codeium team that combines code editing, autocomplete, chat, and agentic workflows for navigating and modifying software projects.

An open-source VS Code extension enabling local LLM integration for code completion, chat, and custom AI workflows without vendor lock-in or data sent to external APIs.

An AI-powered development environment with Flow Mode that combines autocomplete, chat, and autonomous agent capabilities. It provides context-aware suggestions across your entire codebase.

Anthropic Claude Tool Use and Computer Use let Claude call external functions, APIs, and computer-interface actions to gather information, take actions, and complete multi-step workflows beyond text g

Vercel AI SDK is a TypeScript toolkit for building AI-powered applications with unified model access, streaming UI primitives, tool calling, and Model Context Protocol integration.

Google Agent-to-Agent Protocol (A2A) is an open protocol for enabling independent AI agents to discover, communicate, delegate tasks, and exchange results across organizational and framework boundarie

OpenAI Apps SDK is a framework for building interactive ChatGPT apps that expose tools through MCP and render custom UI components inside ChatGPT.

The OpenAI Responses API is OpenAI’s unified interface for generating model outputs and orchestrating tool use, including built-in tools, function calling, and integrations such as MCP-based tools.

Glama MCP Server Directory is a searchable catalog for discovering Model Context Protocol servers and the tools, resources, and integrations they expose.

Strands Agents is an open-source, model-driven framework for building AI agents with Python by combining an LLM, tools, and optional instructions into a lightweight agent loop.

AG2 is an open-source Python framework for building, orchestrating, and experimenting with multi-agent AI applications using conversational agents, tool use, human-in-the-loop workflows, and group cha

Haystack is an open-source Python framework by deepset for building production-ready LLM applications, retrieval-augmented generation systems, semantic search, question answering, and AI agents.

Pydantic AI is a Python framework from the Pydantic team for building type-safe, production-oriented AI agents using structured outputs, dependency injection, and model-agnostic LLM integrations.

Mastra is a TypeScript framework for building production-oriented AI agents, workflows, tools, memory, and RAG applications.

Semantic Kernel Agent Framework is Microsoft's agent orchestration layer within Semantic Kernel for building AI agents that use LLMs, tools, memory, plugins, and multi-agent collaboration across .NET,

AutoAWQ is a Python framework for quantizing and running large language models using Activation-aware Weight Quantization, typically reducing models to efficient 4-bit weights for local inference.

Unsloth is an open-source framework for faster, memory-efficient fine-tuning of local large language models, especially using LoRA and QLoRA.

Open WebUI is a self-hosted, extensible web interface for running and managing local or remote LLMs through Ollama and OpenAI-compatible APIs.

KoboldCpp is a portable local LLM runtime and server for running GGUF/GGML-style language models with a KoboldAI-compatible web UI and API.

text-generation-webui is a popular Gradio-based web interface for running, chatting with, and experimenting with local large language models.

GPT4All is an open-source ecosystem for running large language models locally on consumer hardware, with desktop apps, Python bindings, and model management tools.

StarCoder2 is an open family of code-focused large language models from the BigCode ecosystem designed for code generation, completion, and developer-assistance workflows.

Mistral Devstral is an open-weight coding-focused model from Mistral AI designed for agentic software engineering tasks such as navigating repositories, editing code, and solving GitHub-style issues.

Mistral Codestral is a code-focused large language model from Mistral AI designed for code generation, completion, fill-in-the-middle editing, and developer-assistant workflows across many programming

Qwen3-Coder is Alibaba Qwen’s code-focused large language model family designed for agentic software engineering, long-context code understanding, tool use, and automated coding workflows.

Qwen2.5-Coder is Alibaba Qwen's open-weight family of code-focused large language models for code generation, completion, reasoning, debugging, and developer-agent workflows.

DeepSeek-Coder-V2 is an open-weight mixture-of-experts coding language model family from DeepSeek designed for code generation, code understanding, debugging, and long-context software engineering tas

OSWorld is a benchmark for evaluating multimodal AI agents on real operating-system tasks in a virtual desktop environment.

CodeElo is a coding benchmark that evaluates large language models on competitive-programming-style problems and reports ability using an Elo-like rating scale.

Multi-SWE-bench is a benchmark for evaluating AI coding agents on real-world software engineering tasks across multiple programming languages and repositories.

SWE-gym is a benchmark and training environment for evaluating and improving AI agents on real-world repository-level software engineering tasks.

SWE-smith is a framework from the SWE-bench ecosystem for generating SWE-bench-style software engineering tasks and benchmarks from real code repositories.

RE-Bench, or Research Engineering Benchmark, is a METR benchmark for evaluating how well AI agents can perform realistic AI R&D and machine-learning research engineering tasks.

Aider Repo Map is Aider's automatic repository summarization system that gives an LLM a compact, token-efficient map of relevant files, symbols, and relationships in a codebase.

Cursor Rules and Codebase Indexing are Cursor IDE features for steering AI behavior with project-specific instructions and giving the AI semantic awareness of a repository.

Axolotl is an open-source framework for fine-tuning large language models using configurable training recipes for LoRA, QLoRA, full fine-tuning, preference tuning, and related workflows.

OpenAI Responses API is OpenAI's unified API for building model-powered applications that combine text generation, multimodal inputs, tool use, structured outputs, and conversational context managemen

Prompt caching is a context-engineering technique that reuses previously processed prompt prefixes to reduce latency and cost for repeated or long-context AI requests.

Ragas is an open-source Python framework for evaluating, monitoring, and improving retrieval-augmented generation and other LLM applications using automated metrics and test datasets.

KitOps is an open-source tool for packaging, versioning, and sharing AI/ML models, datasets, code, and configuration as OCI-compatible artifacts called ModelKits.

Dagger is an open-source programmable CI/CD and workflow engine that runs pipelines as portable containerized functions across local machines, CI systems, and self-hosted infrastructure.

Dokploy is an open-source, self-hosted platform-as-a-service for deploying applications, databases, and Docker-based services on your own servers.

Runpod is a cloud GPU platform for renting GPU instances and deploying serverless AI workloads, commonly used for model training, fine-tuning, and inference.

Modal is a serverless cloud platform for running AI, ML, data, and compute-heavy Python workloads without managing infrastructure.

BentoML is an open-source framework for packaging, serving, and deploying machine learning and AI applications as production-ready services.

Persistent Developer Memory and Personalized Context is the emerging practice of AI coding tools remembering a developer’s preferences, projects, coding style, architecture, and prior interactions acr

Prompt-to-app and full-stack generation platforms let users describe an application in natural language and automatically generate working frontends, backends, databases, integrations, and deployment

AI Code Review and Pull Request Automation uses large language models and static analysis to review code changes, summarize pull requests, suggest fixes, and streamline software delivery workflows.

Local, private, and enterprise-controlled coding models are AI coding assistants run on developer machines, private servers, or controlled cloud environments to improve code generation while preservin

Multi-agent software development workflows use multiple AI agents with specialized roles to plan, write, review, test, and maintain software collaboratively.

Sandboxed execution environments for coding agents are isolated runtimes that let AI systems safely write, run, test, and debug code without exposing the host machine, user data, or production infrast