{"id":26228741,"url":"https://github.com/thibault-knobloch/codebase-intelligence","last_synced_at":"2025-04-19T17:46:33.178Z","repository":{"id":279446763,"uuid":"938772950","full_name":"Thibault-Knobloch/codebase-intelligence","owner":"Thibault-Knobloch","description":"🧩 Tibo – CLI tool for codebase indexing, embedding and natural language querying.","archived":false,"fork":false,"pushed_at":"2025-03-18T17:05:37.000Z","size":217,"stargazers_count":12,"open_issues_count":2,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-29T11:06:25.196Z","etag":null,"topics":["ast","call-graph","llm","rag","tree-sitter"],"latest_commit_sha":null,"homepage":"https://pypi.org/project/tibo/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Thibault-Knobloch.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-02-25T13:33:42.000Z","updated_at":"2025-03-25T23:40:10.000Z","dependencies_parsed_at":"2025-02-25T16:34:49.955Z","dependency_job_id":"7ca946b9-cbab-4930-bd0d-9d9a94ea3dc2","html_url":"https://github.com/Thibault-Knobloch/codebase-intelligence","commit_stats":null,"previous_names":["thibault-knobloch/codebase-intelligence"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Thibault-Knobloch%2Fcodebase-intelligence","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Thibault-Knobloch%2Fcodebase-intelligence/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Thibault-Knobloch%2Fcodebase-intelligence/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Thibault-Knobloch%2Fcodebase-intelligence/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Thibault-Knobloch","download_url":"https://codeload.github.com/Thibault-Knobloch/codebase-intelligence/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249752140,"owners_count":21320448,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ast","call-graph","llm","rag","tree-sitter"],"created_at":"2025-03-12T21:25:10.297Z","updated_at":"2025-04-19T17:46:33.162Z","avatar_url":"https://github.com/Thibault-Knobloch.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# codebase-intelligence\n🧩 **Tibo** – a powerful command-line tool designed to index your codebase, generate call graphs, and chunk code into a vector database. With **tibo**, you can query your codebase using natural language and retrieve contextually relevant files, functions, and code snippets effortlessly.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"759\" alt=\"Tibo Workflow\" src=\"https://github.com/user-attachments/assets/1475103e-9810-420f-8ec2-c25d905ea543\" /\u003e\n\u003c/p\u003e\n\n## Features\n- **Codebase Indexing**: Scans and organizes your project for easy querying.\n- **Call Graph Generation**: Maps relationships between functions and files.\n- **Vector Database**: Embeds code chunks for fast, intelligent retrieval.\n- **Natural Language Queries**: Ask questions about your code in plain English.\n- **Context-Aware Results**: Returns relevant files and snippets with added context from the call graph.\n  \n## Installation\nGet started with **tibo** by installing:\n```\npip install tibo\n```\nFind the latest version and additional details on the [PyPI project page](https://pypi.org/project/tibo/).\n\n## Usage\nFollow these steps to integrate **tibo** into your workflow:\n\n1. Configure the Tool - Set up **tibo** with your OpenAI API key:\n```\ntibo config\n```\n\nOPTIONAL: Configure a local LLM to use for on device ai processing:\n```\ntibo local\n```\nNOTE: need to provide model name and url, and ensure the local llm server is running on your device at that specified URL.\n\n\n2. Index Your Project - Navigate to your project directory and index your codebase:\n```\ncd /path/to/your/project\ntibo index\n```\nNote: This creates a .tibo folder in your project root to store indexed data, call graphs, and vector embeddings.\n\n\n3. Query Your Codebase - Fetch relevant context by asking questions in natural language:\n```\ntibo fetch \"my query to the codebase\"\n```\nResults include the most relevant file names and code chunks.\nFull output is saved in .tibo/query_output/query_output.json.\n\n\n4. NEW Interact with Tibo Agent - chat with the ai agent to understnad the codebase better and get help with implementing new features:\n```\ntibo agent\n```\nNOTE: requires running tibo config and adding ANTHROPIC_API_KEY when prompted.\nThe agent can use the tibo fetching tools if you have run 'tibo index' before.\nIn the shell:\n- type 'exit' or 'quit' to quit the agent shell\n- type '#' followed by a command to execute a command directly in your terminal\n- type 'reset' to reset the conversation history\n\nExtra tools:\n- agent can perform web searches (requires setting up OPENAI_API_KEY)\n- agent can get project structure details (requires running tibo index)\n- agent can read file contents when needed\nNOTE: Editing/creating/deleting files coming soon...\n\n\n## How It Works\n**Configuration**: Link Tibo to your OpenAI API for LLM-powered enhancements.\n\n**Indexing**: Processes codebase, builds call graph, chunks files, enhances with GPT-4o-mini, and stores vector embeddings locally.\n\n**Querying**: Enhances your query with an LLM, matches it to the top relevant chunks, and supplements results with call graph context.\n\n\n## Requirements\nPython 3.7+\nAn OpenAI API key (required for LLM functionality)\n\n## Contributing\nWe welcome contributions! Feel free to open issues or submit pull requests on our GitHub repository.\n\n## License\nMIT License\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthibault-knobloch%2Fcodebase-intelligence","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthibault-knobloch%2Fcodebase-intelligence","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthibault-knobloch%2Fcodebase-intelligence/lists"}