Coding & Development

AI coding agent for software development: plan, build, and review code across the editor, terminal (CLI), Slack, and GitHub, with a choice of frontier models and codebase indexing.

GitHub and OpenAI's AI code completion and assistant, deeply integrated into mainstream editors.

An AI-powered code completion tool and copilot featuring a 1-million-token context window and editor integration.

Enterprise AI coding platform built around code privacy and zero data retention, with an enterprise context engine and flexible deployment (SaaS, VPC, on-prem, air-gapped). Offers completion, AI chat, and agentic workflows.

An AI pair programming tool that runs in the terminal, allowing developers to edit code in local git repositories using LLMs.

In-browser AI full-stack development agent that generates frontend, backend, database, and APIs from natural-language prompts, running and deploying apps directly in the browser via StackBlitz WebContainers.

Anthropic's terminal AI coding assistant that plans, edits, and verifies multi-step tasks inside a codebase.

Open-source autonomous coding agent (formerly Claude Dev) shipped as a VS Code extension, CLI, and SDK; BYOK for any LLM, with file editing, command execution, error fixing, and MCP support.

OpenAI's agentic coding assistant that reads, edits, and runs code in the terminal and IDE.

An autonomous AI software engineer designed to plan and execute complex engineering tasks, from code migrations to application development and bug fixing.

An IDE and command center designed to run, manage, and coordinate local and cloud-based coding agents.

AI-native vibe-coding platform that turns natural-language prompts into full-stack web apps (React frontend, Supabase backend, auth, payments).

Replit's AI app-building agent that turns natural language into web and mobile apps, dashboards, and workflows, with built-in database, auth, and 100+ integrations, deploying end-to-end in the cloud.

An AI-powered development tool by Vercel that plans, builds, and deploys full-stack web applications from text prompts, supporting repository syncing and visual design editing.

AI-native code editor from the former Codeium team, built around the agentic 'Cascade' that understands whole-project context, edits across files, and runs terminal commands.

An AI-powered code review platform that integrates into pull requests, IDEs, and CLIs, offering static analysis, 1-click commits, unit test generation, and customizable YAML-based rules.

Open-source framework that orchestrates multiple autonomous AI agents through role-playing collaboration, using intuitive crew/agent/task abstractions. CrewAI Cloud and Enterprise add hosting and operational tooling.

Declarative language and toolchain for AI agents: define agents, tools, and prompts in HCL, then compile to a framework or manage them with plan/apply semantics on a hosted platform. Billed as "Terraform for AI agents".

Low-level orchestration framework for stateful, long-running agents, built by LangChain. Provides state management, persistence, and controllable graph execution; used in production by Klarna, Replit, and Elastic. LangGraph Platform adds managed deployment.

Zero-trust pre-flight repo scanner for AI coding assistants: scans a codebase's instruction surface for prompt injection and supply-chain attacks before Claude Code, Cursor, Codex, or Gemini reads it. Ships with a false-negative ledger.

An automated security testing and evaluation tool designed to find and fix vulnerabilities, jailbreaks, data leaks, and model risks in LLM applications, agents, and RAG pipelines.

An application security platform that combines AI reasoning with rule-based static analysis to detect, triage, and remediate vulnerabilities, dependencies, and hardcoded secrets.

An AI-powered security platform that validates AI-generated code, governs development agents, and secures AI-native applications.

Agent-native analytics engineering toolkit: point it at your warehouse and dbt project and it learns the structure, writes transformations, and pinpoints exactly what to fix when schemas drift. Built for analytics and data engineers who want coding agents to do more of the data work.

An AI observability and evaluation platform designed to monitor, trace, and test AI products and agents at scale.

An enterprise-grade AI observability and evaluation platform for LLM applications, enabling developers to run offline evaluations, auto-tune metrics, and deploy optimized low-latency guardrails using compact Luna models.

An open-source AI engineering platform designed for LLM observability, tracing, prompt management, evaluation, and experiments.

An open-source, serverless, and scalable search infrastructure for AI products supporting vector, full-text, regex, and metadata search.

A fully managed vector database designed for building AI applications, agent memory, semantic search, and recommendation systems.

An open-source inference server designed to deploy AI models across major frameworks (TensorRT, PyTorch, ONNX, OpenVINO, Python, and RAPIDS FIL) on GPUs, CPUs, and accelerators.

A tool that enables running open large language models locally and scaling to the cloud.