# CodeAlive ## Docs - [Fetch artifacts](https://docs.codealive.ai/api-reference/toolapi/fetch-artifacts.md): Fetches full content for up to 50 known artifact identifiers (`repository::path` or `repository::path::symbol`) returned by `semantic_search`, `grep_search`, `read_file`, or `get_artifact_relationships`. This is the preferred way to read code once an identifier is known — do not split the identifier… - [Get artifact relationships](https://docs.codealive.ai/api-reference/toolapi/get-artifact-relationships.md): Traverses the code graph around one known artifact: callers, callees, inheritance, and references. Choose `profile` by the question: `calls_only` (default) for call edges of functions and methods, `inheritance_only` for base types and implementations, `references_only` for where-used checks on types… - [Get ArtifactQuery schema](https://docs.codealive.ai/api-reference/toolapi/get-artifactquery-schema.md): Returns the ArtifactQuery v1 catalog: queryable entities, fields, operators, relationships, limits, and example statements. Call it before composing a non-trivial `query_artifact_metadata` statement, or after a validation error, to get exact field names and supported operators. - [Get repository file tree](https://docs.codealive.ai/api-reference/toolapi/get-repository-file-tree.md): Returns a bounded directory tree for one repository, with short generated summaries for files and folders. Use it for structural orientation when you need to see how a repository (or one directory) is laid out; bound the response with `max_depth` and `max_nodes`. For concept questions prefer `semant… - [Get repository ontology](https://docs.codealive.ai/api-reference/toolapi/get-repository-ontology.md): Returns the generated high-level map (ontology) of one repository: its purpose, subsystems, key concepts, and how they relate. Use it to orient before focused searching when the repository is unfamiliar, or to decide which part of a large codebase a question lands in. Accepts exactly one repository… - [Grep search](https://docs.codealive.ai/api-reference/toolapi/grep-search.md): Searches indexed code for exact literal text or a regular expression (set `regex` to `true`). First choice when you already know an exact symbol name, string literal, error message, route, or configuration key, and for exhaustive "find every usage" sweeps. It complements `semantic_search`: embedding… - [List visible data sources](https://docs.codealive.ai/api-reference/toolapi/list-visible-data-sources.md): Lists the repositories and workspaces visible to the calling API key, including readiness state. Call this first: every other tool accepts the returned `name` values in its `data_sources`/`data_source` argument (use `id` only for automation or to disambiguate duplicate names). Pass an optional `quer… - [Query artifact metadata](https://docs.codealive.ai/api-reference/toolapi/query-artifact-metadata.md): Executes one bounded, read-only ArtifactQuery statement over indexed artifact metadata for repository-level analytics: language and file-type mix, lines, cognitive complexity, largest files, public API surface, relationship counts. Statements must end with LIMIT. Invalid statements are not executed… - [Read a repository file](https://docs.codealive.ai/api-reference/toolapi/read-a-repository-file.md): Reads one file by its exact repository-relative path, returning line-numbered content. This is the fallback reader: when a previous search already returned an artifact `identifier` for the file, prefer `fetch_artifacts`. Bound large files with `start_line`/`end_line`. When the path does not resolve,… - [Semantic search](https://docs.codealive.ai/api-reference/toolapi/semantic-search.md): Searches indexed code by meaning rather than by exact text. This is the default first tool for behaviour, intent, mechanism, and architecture questions. Phrase `question` as a full natural-language English sentence — "How does task execution work?", "Where is retry handling implemented?" — not as ba… - [Stateless chat](https://docs.codealive.ai/api-reference/toolapi/stateless-chat.md): Asks CodeAlive's built-in research agent a question and returns a synthesized, evidence-grounded answer. Each call is stateless: no conversation is stored, so include all relevant prior findings, artifact identifiers, constraints, and scope in `question`. This is the highest-latency, highest-cost to… - [Prepare your repository](https://docs.codealive.ai/code-preparation.md): Learn which files CodeAlive indexes and how to exclude content from repository processing. - [AI Code Review](https://docs.codealive.ai/features/ai-code-review.md): Automated intelligent code reviews for every pull request - [Codebase Chat](https://docs.codealive.ai/features/codebase-chat.md): Have AI-powered conversations with deep understanding of your code - [Multi-Repository & Workspaces](https://docs.codealive.ai/features/multi-repo.md): Search and analyze across multiple repositories and workspaces - [Semantic Code Search](https://docs.codealive.ai/features/semantic-search.md): Find code by meaning and intent across your entire codebase - [CodeAlive & 1С](https://docs.codealive.ai/guides/1c-agents.md): Особенности инструктирования кодовых агентов для проектов 1С:Предприятие (BSL): дихотомия «метаданных», формулировка запросов, готовое правило - [Build a Code Research Agent](https://docs.codealive.ai/guides/build-code-research-agent.md): Reference architecture and an example system prompt for building your own agent on top of the CodeAlive Tool API - [Instructing Coding Agents](https://docs.codealive.ai/guides/instructing-agents.md): How to make Claude Code, Cursor, and Codex actually use CodeAlive tools instead of their built-in search - [Welcome to CodeAlive](https://docs.codealive.ai/index.md): Context Engine for AI-powered Code Review & Codebase Deep Research - [Installation](https://docs.codealive.ai/installation.md): Install CodeAlive to your AI coding agents with one command - [Model Context Protocol (MCP)](https://docs.codealive.ai/integrations/mcp.md): Connect CodeAlive to AI assistants via Model Context Protocol for deep codebase understanding - [Amazon Q Developer](https://docs.codealive.ai/integrations/mcp/amazon-q.md): Connect CodeAlive with Amazon Q Developer CLI and IDE - [ChatGPT](https://docs.codealive.ai/integrations/mcp/chatgpt.md): Connect CodeAlive with ChatGPT using a custom MCP app - [Claude Code Integration](https://docs.codealive.ai/integrations/mcp/claude-code.md): Connect CodeAlive with Claude Code for enhanced AI-powered development - [Claude Desktop](https://docs.codealive.ai/integrations/mcp/claude-desktop.md): Connect CodeAlive with Claude Desktop application - [Cline](https://docs.codealive.ai/integrations/mcp/cline.md): Connect CodeAlive with Cline autonomous coding agent - [Codex](https://docs.codealive.ai/integrations/mcp/codex.md): Connect CodeAlive with OpenAI Codex CLI, Desktop App, and IDE Extension - [Continue](https://docs.codealive.ai/integrations/mcp/continue.md): Connect CodeAlive with Continue open-source AI code assistant - [Cursor](https://docs.codealive.ai/integrations/mcp/cursor.md): Integrate CodeAlive with Cursor IDE for AI-powered development - [Gemini CLI](https://docs.codealive.ai/integrations/mcp/gemini-cli.md): Connect CodeAlive with Google Gemini CLI - [Migrate to MCP v3](https://docs.codealive.ai/integrations/mcp/migrate-to-v3.md): Upgrade a CodeAlive MCP v1 or v2 integration to the eleven-tool MCP v3 contract - [OpenClaw](https://docs.codealive.ai/integrations/mcp/openclaw.md): Connect CodeAlive with OpenClaw for semantic code search and codebase intelligence - [OpenCode](https://docs.codealive.ai/integrations/mcp/opencode.md): Connect CodeAlive with OpenCode AI terminal assistant - [Other Agents](https://docs.codealive.ai/integrations/mcp/other-agents.md): Connect CodeAlive with Roo Code, KodaCode, GigaCode, Goose, and more - [Self-Hosting Guide](https://docs.codealive.ai/integrations/mcp/self-hosting.md): Deploy CodeAlive MCP server on your own infrastructure - [SourceCraft](https://docs.codealive.ai/integrations/mcp/sourcecraft.md): Connect CodeAlive with SourceCraft Code Assistant and SourceCraft CLI - [VS Code + GitHub Copilot](https://docs.codealive.ai/integrations/mcp/vscode.md): Connect CodeAlive with GitHub Copilot in VS Code using native MCP support - [Windsurf](https://docs.codealive.ai/integrations/mcp/windsurf.md): Connect CodeAlive with Windsurf AI coding assistant - [Zed](https://docs.codealive.ai/integrations/mcp/zed.md): Connect CodeAlive with the Zed Agent using remote MCP - [Claude Code Plugin](https://docs.codealive.ai/integrations/plugin-claude-code.md): Install the CodeAlive plugin for Claude Code — includes skill, subagent, and authentication hooks - [Share the plugin with Codex CLI](https://docs.codealive.ai/integrations/share-plugin-with-codex.md): Reuse the Claude Code plugin's skill from Codex CLI and other skill-aware agents, with a launchd agent that follows every plugin update. - [Agent Skills & Plugins](https://docs.codealive.ai/integrations/skills.md): Install CodeAlive skills for intelligent codebase exploration patterns - [Quickstart](https://docs.codealive.ai/quickstart.md): Get started with CodeAlive in minutes - [Tips & Tricks](https://docs.codealive.ai/tips-and-tricks.md): Get the most out of CodeAlive with these practical tips - [Troubleshooting](https://docs.codealive.ai/troubleshooting.md): Solutions for common issues with CodeAlive - [Example Workflows](https://docs.codealive.ai/workflows.md): Real-world patterns for using CodeAlive with AI coding agents ## OpenAPI Specs - [openapi-tool-api-v3](https://docs.codealive.ai/openapi-tool-api-v3.json) ## Optional - [GitHub](https://github.com/CodeAlive-AI) - [Dashboard](https://app.codealive.ai)