Awesome AI Agents › IDE Integrations
LMQL is a specialized programming language designed for efficient and constraint-guided interaction with large language models (LLMs). It extends Python syntax to seamlessly integrate LLM calls within traditional programming logic, enabling developers to write programs that combine algorithmic control flow with natural language model prompting. LMQL programs use a unique query string format where template variables are automatically completed by the model, allowing for dynamic and context-aware text generation. The language supports advanced features such as multi-variable templates, conditional distributions, and expressive constraints that guide the model's output through logit masking and datatype specifications. This constraint system enhances control over the generated text, including token length, stopping phrases, and character-level restrictions. LMQL also offers sophisticated decoding algorithms like beam search and best_k, which improve the quality and diversity of model outputs. It optimizes runtime performance through speculative execution, constraint short-circuiting, and tree-based caching, making inference faster and more efficient. The language supports both synchronous and asynchronous APIs, enabling parallel execution and cross-query batching for large-scale applications. The project is compatible with multiple LLM providers, including OpenAI, Azure OpenAI, and Hugging Face Transformers, allowing users to leverage a wide range of models. LMQL is designed for extensibility and integration, with support for popular libraries like LangChain and LlamaIndex. It also provides a rich development environment featuring an interactive browser-based playground IDE, a Visual Studio Code extension, and output streaming capabilities via WebSocket, REST, or Server-Sent Events. LMQL is suitable for advanced applications such as schema-safe JSON decoding, algorithmic prompting, interactive chat interfaces, and inline tool use. It aims to empower developers to harness the full potential of LLMs by combining traditional programming paradigms with powerful language model capabilities in a unified framework.
https://github.com/eth-sri/lmql
Continue is an open-source platform that enables developers to create, share, and use custom AI code assistants within popular IDEs, enhancing coding productivity and collaboration through features like Chat, Autocomplete, Edit, and Agent.
Coder is a platform for creating secure, self-hosted cloud development environments that streamline developer onboarding and optimize resource usage through automation and integrations.
Sweep is an AI-powered coding assistant plugin designed to enhance productivity and coding efficiency within JetBrains IDEs.
Claude Code plugin that distills reusable skills from real coding sessions, merges same-scenario skills instead of duplicating them, and prunes skills that stop being used.
Aide is a Visual Studio Code extension that leverages AI to provide one-click code conversion, commenting, optimization, and batch processing features to enhance developer productivity.
Plugin marketplace and shared configuration for Claude Code, Codex CLI, Cursor and Gemini CLI, bundling skills, slash commands, hooks, subagents and MCP servers.
VS Code extension that runs twelve AI coding agents in one chat interface, with a brainstorm mode where two agents collaborate, selectable personas, permission controls and at-mention routing.
MCP LLMS-TXT Documentation Server is an open-source MCP server that exposes llms.txt files to IDEs and applications, providing controlled, auditable access to LLM documentation for enhanced development workflows.