Back to directory

AIDE - AI Development Environment

A tool that adds persistent memory, tree-sitter code intelligence, and multi-agent orchestration to AI coding assistants such as Claude Code, OpenCode, and Codex CLI.

AIDE - AI Development Environment

AIDE augments AI coding assistants with capabilities they do not have on their own: a memory system that remembers preferences and context across sessions, a decisions log that records architectural choices and enforces them in later sessions, curated best-practice blueprints for languages such as Go and Rust and for GitHub Actions, a tree-sitter-based code index for fast symbol search, call graphs, and references, static analysis that detects complexity, coupling, secrets, and duplication, and a survey feature that maps a codebase's modules, entry points, tech stack, and churn hotspots.

It also includes 23 built-in workflow skills triggered by natural language and a swarm mode that runs parallel agents through full design, test, implement, verify, and document pipelines, all exposed to the host assistant through 34 MCP tools. It installs as a plugin for Claude Code, OpenCode, or Codex CLI, requires Bun as its runtime dependency, and downloads its Go binary automatically on install.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.