#360 · Primary category: AI Coding Assistants

octocode

agent ai ai-agents ai-tools claude-ai code-intelligence code-search context cursor cursor-ai development github github-api llm mcp model-context-protocol modelcontextprotocol octocode semantic-search vibe-coding

Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI

Project last updated:08/25/26

GitHub Stars

920

Forks

75

Contributors

1

License

MIT

Why we included this project

Coding agents lose the plot fast when a question spans a large local repo and other GitHub projects at once. Octocode gives them a research tool they can call directly: it searches your local code plus external sources like GitHub repositories, PRs, and npm packages using ripgrep, structural AST matching, and language-server data, then returns compact, cited findings instead of raw output dumps. The same Rust engine runs as an MCP server for Cursor, Claude Code, or Windsurf, or as a standalone CLI that emits JSON for scripting. Setup is almost instant because there is no indexing or embedding step, and the token-conscious replies let an agent inspect a big file's shape without eating the whole context window. For PR review, cross-repo debugging, or bringing a new teammate up to speed in private repos, it turns scattered repository knowledge into evidence both the agent and its human reviewers can check.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category