Awesome AI Agents › IDE Integrations
AgentSys, published from the awesome-slash repository, is an orchestration system for coding agents that targets the work surrounding code generation rather than code generation itself: task selection, branch management, review, artifact cleanup, CI handling, pull request comments and deployment. The project ships 24 plugins, 49 agents (39 file-based plus 10 role-based specialists inside an audit-project plugin) and 44 skills. Each agent is defined with a single responsibility, an explicit model assignment and declared inputs and outputs, so agents compose into structured pipelines. Pipelines enforce phase gates that prevent agents from skipping steps, and run state is persisted so an interrupted session can be resumed later. The design principle stated in the documentation is that deterministic code performs detection through regular expressions, AST parsing and static analysis, while LLM calls are reserved for synthesis, planning and review. Findings are graded by certainty into HIGH, MEDIUM and LOW levels, which decide whether a fix can be applied automatically, needs additional context, or requires a human decision; the authors report that this grading came out of testing across more than a thousand repositories. Distribution is federated: every plugin lives in its own standalone repository under the agent-sh organisation, and agentsys itself acts as the marketplace and installer that resolves and fetches them. Installation happens either through the plugin marketplace of the host tool or through an npm installer, and the same plugin set runs on Claude Code, OpenCode, Codex CLI, Cursor and Kiro. The repository also publishes benchmark numbers comparing structured prompts plus enriched context against a larger raw model on real tasks. It is aimed at developers who already use an agentic coding CLI and want repeatable, gated workflows instead of ad hoc prompting.
https://github.com/avifenesh/awesome-slash
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.
LMQL is a Python-superset programming language designed for constraint-guided and efficient interaction with large language models, enabling advanced control flow, decoding, and integration with multiple LLM providers.
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.