Back to directory

Octocode

An agentic code-research platform, backed by a Rust engine, that lets an AI agent or developer search and read local code and GitHub repositories, pull requests and npm packages token-efficiently through one CLI or MCP toolset.

Octocode

Octocode researches local and external code alike, GitHub repositories, pull requests and npm packages, with one toolset combining ripgrep-style and AST search, directory trees, precise file reads and a language server, backed by a Rust engine for fast, token-efficient results across single files or very large repositories. It can be used as a CLI or as an MCP server, and every MCP tool is also a plain command that takes JSON input and returns compact YAML, so any coding agent can discover and drive it without an MCP client.

Running npx octocode prints self-describing usage and a full tool catalog for an agent to read, npx octocode tools lists every available tool, and a tool's schema can be inspected directly from the command line. GitHub authentication is optional but unlocks private repositories and higher API rate limits.

It requires Node.js 20.12 or newer and installs with npx, with a documented one-click install path for MCP clients including Claude Code, Windsurf, Kiro, Goose and LM Studio.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.