{"id":28770343,"url":"https://github.com/video-db/agent-toolkit","last_synced_at":"2026-02-12T16:10:50.536Z","repository":{"id":283613906,"uuid":"951147925","full_name":"video-db/agent-toolkit","owner":"video-db","description":"An open-source agent toolkit that auto-syncs SDK versions, docs, and examples—built for seamless integration with LLMs, and AI agents ( MCP compatible).","archived":false,"fork":false,"pushed_at":"2026-01-22T14:35:49.000Z","size":3169,"stargazers_count":45,"open_issues_count":4,"forks_count":9,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-01-23T07:27:55.519Z","etag":null,"topics":["agent","llm","llms-txt","mcp","mcpserver","videodb"],"latest_commit_sha":null,"homepage":"https://docs.videodb.io","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/video-db.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-03-19T08:30:36.000Z","updated_at":"2026-01-22T14:35:55.000Z","dependencies_parsed_at":"2025-03-21T07:22:43.364Z","dependency_job_id":"adea3c27-217f-426a-9cca-4ac9deb97c04","html_url":"https://github.com/video-db/agent-toolkit","commit_stats":null,"previous_names":["video-db/agent-toolkit"],"tags_count":45,"template":false,"template_full_name":null,"purl":"pkg:github/video-db/agent-toolkit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/video-db%2Fagent-toolkit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/video-db%2Fagent-toolkit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/video-db%2Fagent-toolkit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/video-db%2Fagent-toolkit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/video-db","download_url":"https://codeload.github.com/video-db/agent-toolkit/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/video-db%2Fagent-toolkit/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29371747,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-12T08:51:36.827Z","status":"ssl_error","status_checked_at":"2026-02-12T08:51:26.849Z","response_time":55,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["agent","llm","llms-txt","mcp","mcpserver","videodb"],"created_at":"2025-06-17T13:05:03.737Z","updated_at":"2026-02-12T16:10:50.530Z","avatar_url":"https://github.com/video-db.png","language":"Python","funding_links":[],"categories":["Media Processing","Content Creation","Code \u0026 Developer Tools"],"sub_categories":["Video"],"readme":"[![Latest Number][token-length-shield]][token-length-url]\n[![GitHub tag (latest SemVer)][tag-shield]][ tag-url]\n[![Stars][stars-shield]][stars-url]\n[![Issues][issues-shield]][issues-url]\n\n\u003c!-- PROJECT LOGO --\u003e\n\u003cbr /\u003e\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://videodb.io/\"\u003e\n    \u003cimg src=\"https://codaio.imgix.net/docs/_s5lUnUCIU/blobs/bl-RgjcFrrJjj/d3cbc44f8584ecd42f2a97d981a144dce6a66d83ddd5864f723b7808c7d1dfbc25034f2f25e1b2188e78f78f37bcb79d3c34ca937cbb08ca8b3da1526c29da9a897ab38eb39d084fd715028b7cc60eb595c68ecfa6fa0bb125ec2b09da65664a4f172c2f\" alt=\"Logo\" width=\"300\" height=\"\"\u003e\n  \u003c/a\u003e\n\n  \u003ch3 align=\"center\"\u003eVideoDB Agent Toolkit\u003c/h3\u003e\n\n  \u003cp align=\"center\"\u003e\n    AI Agent toolkit for VideoDB\n    \u003cbr /\u003e\n    \u003ca href=\"https://videodb.io/llms.txt\"\u003e\u003cstrong\u003ellms.txt \u003e\u003e\u003c/strong\u003e\u003c/a\u003e \n    \u003ca href=\"https://videodb.io/llms-full.txt\"\u003e\u003cstrong\u003ellms-full.txt\u003c/strong\u003e\u003c/a\u003e  \u003cbr /\u003e\n    \u003ca href=\"https://videodb.io/mcp\"\u003e\u003cstrong\u003eMCP\u003c/strong\u003e\u003c/a\u003e\n    \u003cbr /\u003e\n  \u003c/p\u003e\n\u003c/p\u003e\n\n# VideoDB Agent Toolkit\n\nThe VideoDB Agent Toolkit exposes VideoDB context to LLMs and agents. It enables integration to AI-driven IDEs like Cursor, chat agents like Claude Code etc. This toolkit automates context generation, maintenance, and discoverability. It auto-syncs SDK versions, docs, and examples and is distributed through MCP and `llms.txt` \n\n\n## 🚀 Quick Overview\n\nThe toolkit offers context files designed for use with LLMs, structured around key components:\n\n`llms-full.txt` — Comprehensive context for deep integration.\n\n`llms.txt` — Lightweight metadata for quick discovery.\n\n`MCP (Model Context Protocol)` — A standardized protocol.\n\nThese components leverage automated workflows to ensure your AI applications always operate with accurate, up-to-date context.\n\n## 📦 Toolkit Components\n\n### 1. llms-full.txt ([View »](https://videodb.io/llms-full.txt))\n\n---\n\n`llms-full.txt` consolidates everything your LLM agent needs, including:\n\n- Comprehensive VideoDB overview.\n\n- Complete SDK usage instructions and documentation.\n\n- Detailed integration examples and best practices.\n\n**Real-world Examples:**\n\n- [VideoDB's Director](https://chat.videodb.io) `code-assistant` agent ([View Implementation ](https://github.com/video-db/Director/blob/main/backend/director/agents/code_assitant.py))\n- [VideoDB's Discord Bot](https://discord.com/invite/py9P639jGz) to power customer support and community help ([View Implementation ]())\n- Integrate `llms-full.txt` directly into your LLM-powered workflows, agent systems, or AI coding environments.\n\n### 2. llms.txt ([View »](https://videodb.io/llms.txt))\n\n---\n\nA streamlined file following the [Answer.AI llms.txt proposal](https://github.com/answerdotai/llms-txt). Ideal for quick metadata exposure and LLM discovery.\n\n\u003e **ℹ️ Recommendation**: Use `llms.txt` for lightweight discovery and metadata integration.  Use `llms-full.txt` for complete functionality.\n\n### 3. MCP (Model Context Protocol)\n\nThe VideoDB MCP Server connects with the Director backend framework, providing a single tool for many workflows. For development, it can be installed and used via uvx for isolated environments. For more details on MCPs, please visit [here](https://docs.videodb.io/add-videodb-mcp-server-in-clients-108)\n\n**Install `uv`**\n\nWe need to install uv first.\n\nFor macOS/Linux:\n```\ncurl -LsSf https://astral.sh/uv/install.sh | sh\n```\nFor Windows:\n\n```\npowershell -ExecutionPolicy ByPass -c \"irm https://astral.sh/uv/install.ps1 | iex\"\n```\n\nYou can also visit the installation steps of `uv` for more details [here](https://docs.astral.sh/uv/getting-started/installation)\n\n**Run the MCP Server**\n\nYou can run the MCP server using `uvx` using the following command\n\n```\nuvx videodb-director-mcp --api-key=VIDEODB_API_KEY\n```\n\n**Update VideoDB Director MCP package**\n\nTo ensure you're using the latest version of the MCP server with `uvx`, start by clearing the cache:\n\n```\nuv cache clean\n```\n\nThis command removes any outdated cached packages of `videodb-director-mcp`, allowing `uvx` to fetch the most recent version.\n\nIf you always want to use the latest version of the MCP server, update your command as follows:\n```\nuvx videodb-director-mcp@latest --api-key=\u003cVIDEODB_API_KEY\u003e\n```\n\n\u003cbr/\u003e\n       \n## 🧠 Anatomy of LLM Context Files\n\nLLM context files in VideoDB are modular, automatically generated, and continuously updated from multiple sources:\n\n### 🧩 Modular Structure:\n\n- **Instructions** — Best practices and prompt guidelines [View »](https://github.com/video-db/agent-toolkit/blob/main/context/instructions/prompt.md)\n\n- **SDK Context** — SDK structure, classes, and interface definitions [View »](https://github.com/video-db/agent-toolkit/blob/main/context/sdk/context/index.md)\n\n- **Docs Context** — Summarized product documentation [View »](https://github.com/video-db/agent-toolkit/blob/main/context/docs/docs_context.md)\n\n- **Examples Context** — Real-world notebook examples [View »](https://github.com/video-db/agent-toolkit/blob/main/context/examples/examples_context.md)\n\u003cimg src=\"./token_breakdown.png\" alt=\"Token Breakdown\" width=\"400\"/\u003e\n\n\n\n### Automated Maintenance:\n- Managed through GitHub Actions for automated updates.\n- Triggered by changes to SDK repositories, documentation, or examples.\n- Maintained centrally via a [`config.yaml`](https://github.com/video-db/agent-toolkit/blob/readme-refactor/config.yaml) file.\n\n---\n\n## 🛠️ Automation with GitHub Actions\n\nAutomatic context generation ensures your applications always have the latest information:\n\n### 🔹 SDK Context Workflow ([View](https://github.com/video-db/agent-toolkit/blob/main/.github/workflows/update_sdk_context.yml))\n- **Automatically generates documentation** from SDK repo updates.\n- Uses [Sphinx](https://www.sphinx-doc.org/en/master/) for Python SDKs.\n\n### 🔹 Docs Context Workflow ([View](https://github.com/video-db/agent-toolkit/blob/main/.github/workflows/update_docs_context.yml))\n- **Scrapes and summarizes documentation** using [FireCrawl](https://www.firecrawl.dev/) and LLM-powered summarization.\n\n### 🔹 Examples Context Workflow ([View](https://github.com/video-db/agent-toolkit/blob/main/.github/workflows/update_examples_context.yml))\n- Converts and summarizes notebooks into practical context examples.\n\n### 🔹 Master Context Workflow ([View](https://github.com/video-db/agent-toolkit/blob/main/.github/workflows/update_master_context.yml))\n- Combines all sub-components into unified `llms-full.txt`.\n- Generates standards-compliant `llms.txt`.\n- Updates documentation with token statistics for transparency.\n\n---\n\n\n## 🛠️ Customization via `config.yaml`\n\nThe [`config.yaml`](https://github.com/video-db/agent-toolkit/blob/readme-refactor/config.yaml) file centralizes all configurations, allowing easy customization:\n\n- **Inclusion \u0026 Exclusion Patterns** for documentation and notebook processing\n- **Custom LLM Prompts** for precise summarization tailored to each document type\n- **Layout Configuration** for combining context components seamlessly\n\n`config.yaml` \u003e `llms_full_txt_file` defines how `llms-full.txt` is assembled:\n\n```yaml\nllms_full_txt_file:\n  input_files:\n    - name: Instructions\n      file_path: \"context/instructions/prompt.md\"\n    - name: SDK Context\n      file_path: \"context/sdk/context/index.md\"\n    - name: Docs Context\n      file_path: \"context/docs/docs_context.md\"\n    - name: Examples Context\n      file_path: \"context/examples/examples_context.md\"\n  output_files:\n    - name: llms_full_txt\n      file_path: \"context/llms-full.txt\"\n    - name: llms_full_md\n      file_path: \"context/llms-full.md\"\n  layout: |\n    {{FILE1}}\n\n    {{FILE2}}\n\n    {{FILE3}}\n\n    {{FILE4}}\n\n  ```\n\n## 💡 Best Practices for Context-Driven Development\n\n- **Automate Context Updates:** Leverage GitHub Actions to maintain accuracy.\n- **Tailored Summaries:** Use custom LLM prompts to ensure context relevance.\n- **Seamless Integration:** Continuously integrate with existing LLM agents or IDEs.\n\nBy following these practices, you ensure your AI applications have reliable, relevant, and up-to-date context—critical for effective agent performance and developer productivity.\n\n---\n\n## 🚀 Get Started\n\nClone the toolkit repository and follow the setup instructions in [`config.yaml`](https://github.com/video-db/agent-toolkit/blob/readme-refactor/config.yaml) to start integrating VideoDB contexts into your LLM-powered applications today.\n\n**Explore further:**\n- [VideoDB SDK](https://github.com/video-db/videodb-python)\n- [Documentation](https://docs.videodb.io)\n- [Cookbook Examples](https://github.com/video-db/videodb-cookbook)\n\n---\n\u003c!-- MARKDOWN LINKS \u0026 IMAGES --\u003e\n\u003c!-- https://www.markdownguide.org/basic-syntax/#reference-style-links --\u003e\n\n[token-length-shield]: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/video-db/agent-toolkit/refs/heads/main/readme_shields.json\u0026style=for-the-badge\n[token-length-url]: https://github.com/video-db/agent-toolkit/blob/main/token_breakdown.png\n[tag-shield]: https://img.shields.io/github/v/tag/video-db/agent-toolkit?style=for-the-badge\n[tag-url]: https://github.com/video-db/agent-toolkit/tags\n[stars-shield]: https://img.shields.io/github/stars/video-db/agent-toolkit.svg?style=for-the-badge\n[stars-url]: https://github.com/video-db/agent-toolkit/stargazers\n[issues-shield]: https://img.shields.io/github/issues/video-db/agent-toolkit.svg?style=for-the-badge\n[issues-url]: https://github.com/video-db/agent-toolkit/issues\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvideo-db%2Fagent-toolkit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvideo-db%2Fagent-toolkit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvideo-db%2Fagent-toolkit/lists"}