Codebase AI AI Codebase Knowledge & Generation
Tools for understanding large repositories or generating SDKs/APIs.
11 tools · 11 with full reviews · 5 free or open source · Updated
Greptile Freemium
Greptile Greptile is an AI-powered code review platform that builds a semantic graph of your entire repository to catch complex, cross-file, and logical bugs that diff-only tools often miss. It uses a swarm of specialized agents to analyze pull requests and adapts to your team's unique coding standards over time. Fern Freemium
Fern Fern is an API-first developer experience platform that generates documentation sites, idiomatic SDKs, and CLIs from a single API specification. It uses a docs-as-code approach, allowing teams to manage content in Git while providing a browser-based editor and AI-powered tools for all team members. Remio Freemium
Remio remio is a local-first AI knowledge hub that automatically captures files, meetings, emails, and web pages to create a private, searchable personal intelligence source. It uses agentic workflows to synthesize your data into reports, presentations, and insights, operating locally to ensure data privacy. ContextStream Freemium
ContextStream ContextStream provides a persistent memory layer for AI coding agents by unifying code, documentation, and project history into a queryable intelligence graph. It integrates via the Model Context Protocol (MCP) to allow assistants like Cursor, Claude Code, and Cline to retain context across different tools and sessions. OKF Agent Memory Open Source
okf-memory A Git-native persistent memory layer for AI coding agents that stores knowledge as structured Markdown files within the repository. It uses in-memory BM25 search and progressive disclosure to provide fast, auditable, and context-efficient memory without external database dependencies. Tseha Freemium
Tseha Tseha is a governed development-context platform that allows engineering teams to define coding standards, component rules, and design tokens centrally. It exposes this knowledge to AI coding agents via the Model Context Protocol (MCP), ensuring agents follow team-specific conventions and architecture consistently across projects. Brain Scanner Free
Kevin Lozada Santos (submitted by his authorized AI assistant) Brain Scanner is a development tool that helps users understand projects built by coding agents by providing project graphs, recorded agent context, and change history. It integrates with agent workflows via the Model Context Protocol (MCP) to provide a unified workspace for reviewing agent-driven development. codebase-memory-mcp Open Source
DeusData codebase-memory-mcp is a high-performance code intelligence MCP server that indexes a repository into a persistent knowledge graph using tree-sitter across 162 languages, with hybrid LSP type resolution for major languages. Coding agents query the graph through 17 MCP tools — search, call tracing, architecture overviews, impact analysis, dead-code detection, Cypher queries — replacing dozens of grep/read cycles with a few structural queries. Gortex Open Source
zzet Gortex is a local code-intelligence engine for AI coding agents. It indexes symbols, calls, dependencies and cross-repository API contracts into a persistent graph, then serves structural context and change-impact queries through a CLI, MCP server and web UI. Agents can inspect callers and blast radius before editing rather than loading entire files into context. GitDiagram Freemium
Ahmed Khaleel GitDiagram turns any public or private GitHub repository into an interactive, AI-generated architecture diagram with a streamed explanation. Replace `hub` with `diagram` in any GitHub URL (or paste the repo on gitdiagram.com) and you get a Mermaid system diagram where clicking a component jumps straight to the linked file or directory; diagrams export as PNG or raw Mermaid source. A newer explainer mode renders a roughly one-minute narrated video of the codebase — what the project is for, how its main parts fit together and one decision under the hood — downloadable as MP4 in landscape or 9:16 with burned-in captions. It is built with Next.js, React, TypeScript, Tailwind and Mermaid, uses Claude or GPT for scripts and scenes and OpenRouter TTS for voice, and can be self-hosted with your own keys. jevgrep Open Source
David Zhang (dzhng) jevgrep is a research CLI that helps AI coding agents find relevant code by asking what it does. The `jg` command uses TypeSafe's Jev model to judge relevance across folders, files and declarations, then returns relevant files, reading leads and verbatim source excerpts in a single stdout response. A bundled agent skill teaches Claude Code, Codex and other agents to use it for context gathering before they implement changes. FAQ
What are the best Codebase AI tools?
The most complete Codebase AI listings on ai.dosa.dev include Greptile, Fern, Remio. Every tool has a detail page with pricing, key features, and a verdict - see the full list of 11 tools below.
Are Codebase AI tools free?
5 of the 11 Codebase AI tools listed here are free or open source. Others offer freemium or paid plans - check each tool's detail page for current pricing.
How is this list curated?
ai.dosa.dev is manually curated from community submissions and editorial review. Entries are enriched with pricing, features, and reviewer notes, and the directory is updated continuously.