{"id":51706655,"url":"https://github.com/reory/smart_file_agent","last_synced_at":"2026-07-16T16:36:34.808Z","repository":{"id":369351565,"uuid":"1200415615","full_name":"reory/smart_file_agent","owner":"reory","description":"Smart File Agent is a tiny, self‑contained demonstration of an agentic  AI pipeline — built entirely in Python","archived":false,"fork":false,"pushed_at":"2026-07-04T20:11:05.000Z","size":575,"stargazers_count":1,"open_issues_count":1,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-07-04T22:06:57.628Z","etag":null,"topics":["agentic-workflow","agents","ai-pipeline","cli-tool","demo-project","educational-project","file-ingestion","logging-library","markdown-output","open-source","pure-python","python","rule-based-ai","text-processing"],"latest_commit_sha":null,"homepage":"https://www.linkedin.com/in/roy-p-74980b382/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/reory.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.md","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":"2026-04-03T11:40:27.000Z","updated_at":"2026-07-04T20:11:09.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/reory/smart_file_agent","commit_stats":null,"previous_names":["reory/smart_file_agent"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/reory/smart_file_agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reory%2Fsmart_file_agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reory%2Fsmart_file_agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reory%2Fsmart_file_agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reory%2Fsmart_file_agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/reory","download_url":"https://codeload.github.com/reory/smart_file_agent/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reory%2Fsmart_file_agent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35551282,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-16T02:00:06.687Z","response_time":83,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["agentic-workflow","agents","ai-pipeline","cli-tool","demo-project","educational-project","file-ingestion","logging-library","markdown-output","open-source","pure-python","python","rule-based-ai","text-processing"],"created_at":"2026-07-16T16:36:34.227Z","updated_at":"2026-07-16T16:36:34.804Z","avatar_url":"https://github.com/reory.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🗄️ Smart File Agent\n\n- A tiny, educational demonstration of an agentic AI pipeline — no LLMs, no APIs, just pure Python.\n\n![Last Commit](https://img.shields.io/github/last-commit/reory/smart_file_agent?cacheSeconds=60)\n![Repo Size](https://img.shields.io/github/repo-size/reory/smart_file_agent?cacheSeconds=60)\n![License](https://img.shields.io/badge/License-MIT-green)\n\n![Python](https://img.shields.io/badge/Python-3776AB?style=for-the-badge\u0026logo=python\u0026logoColor=white)\n![JavaScript](https://img.shields.io/badge/javascript-%23323330.svg?style=flat-square\u0026logo=javascript\u0026logoColor=%23F7DF1E)\n\n---\n\n# 🧠 Overview\n\nSmart File Agent is a tiny, self‑contained demonstration of an agentic \nAI pipeline — built entirely in Python\n\nIt mirrors the architecture shown in the “How Agentic AI Works” diagram:\n\n- Input Sources → file ingestion\n\n- AI Processing → request analysis + planning\n\n- Action Layer → tool execution (summarise, bulletify)\n\n- Output → clean Markdown summary\n\nThis project is intentionally small and easy to understand.\n\n---\n\n# 📸 Screenshots\n\n- Smart File Agent is a miniature implementation of the agentic‑AI pipeline shown below — it ingests a file, analyses the user’s request, plans the steps, executes tools, and produces a structured output exactly like the Input → Processing → Action → Output flow in the diagram.\n\n---\n\n![Logic flow of the file sorting system](smart_file_agent/agent/screenshots/agentic_system.png)\n\n---\n\n# 🏗️ Project Structure\n```\nsmart_file_agent/\n│\n├── smart_file_agent/\n│   ├── __init__.py\n│   ├── main.py\n│   ├── agent/\n│   │   ├── __init__.py\n│   │   ├── agent_core.py\n|   |   ├── logging_config.py\n│   │   ├── ingestion.py\n│   │   ├── processing.py\n│   │   ├── tools.py\n│   │   └── output.py\n├──tests/\n│   ├── test_agent_core.py\n│   ├── test_ingestion.py\n│   ├── test_logging_config.py\n│   ├── test_main.py\n│   ├── test_processing.py\n│   ├── test_tools_hypothesis.py\n│   ├── test_tools.py\n│   ├── test_output.py\n├── venv/\n├── README.md\n└── project_notes.txt\n└── requirements.txt\n```\n\n---\n\n# 🧩 How It Works (Mapped to Agentic AI Architecture)\n\n## Input Sources → ingestion.py\n- Loads the file text\n- Extracts metadata (name, size, extension)\n\n## AI Processing → processing.py\n- Analyses the user’s request\n- Chooses a mode (summary or bullet summary)\n- Plans the steps the agent should take\n\n## Action Layer → tools.py\n- Implements two tiny rule‑based tools:\n- summarise_text() → extracts first sentence, longest sentence, keywords\n- bulletify() → converts sentences into bullet points\n\n## Agent Orchestration → agent_core.py\n- Runs the pipeline and executes each planned step in order\n- Produces a structured result dictionary\n\n## Output Layer → output.py\n- Formats the final Markdown summary\n\n---\n\n# ▶️ Running the Agent\nFrom the project root:\n\n```Bash\npython -m smart_file_agent.main\n```\nYou’ll be prompted for:\n- File path\n- What you want the agent to do\n\n## Example:\nEnter file path: (**File path of any text document you have**)\nWhat would you like to do? **bulletify**\n\n## 💬 Supported Prompts\nYou can speak to the agent naturally.\nHere are some example prompts:\n\n## Summaries\n- summarise this\n- give me a summary\n- summarise the file\n- what is this file about\n\n## Bullet summaries\n- bulletify\n- give me bullet points\n- turn this into bullets\n- bullet summary please\n\nThe agent detects the intent and chooses the correct mode.\n\n## 🧪 Example Output\n\n- AGENT OUTPUT\n\n## Summary of project_notes.txt\n**Mode:** bullet_summary\n**Steps:** extract_text, summarise, bulletify\n\n- Summary:\n- Opening idea: ...\n- Key detail: ...\n- Keywords: ...\n\n---\n\n# 🎯 Why This Project Exists\nThis project demonstrates:\n\n- how agentic systems work internally\n\n- how to build a reasoning → planning → action pipeline\n\n- how to structure a Python agent project\n\n- how to simulate LLM behaviour without external dependencies\n\n- It’s intentionally tiny, readable, and educational.\n\n---\n\n# 🛣️ Roadmap Features\n\n- [ ] Add a reasoning trace (“Thought → Action → Result”)\n\n- [ ] Add a memory system\n\n- [ ] A reasoning trace (LLM‑style)\n\n- [ ] Add a tool registry\n\n- [ ] Add a FastAPI interface\n\n---\n\n# 📝 Notes \n- It was enjoyable to build this. If you have any ideas on how to collaborate and \nimprove this project please let me know.\n\n---\n\n* **Built by Roy Peters** 😁[![LinkedIn](https://img.shields.io/badge/LinkedIn-%230077B5.svg?style=for-the-badge\u0026logo=linkedin\u0026logoColor=white)](https://linkedin.com/in/roy-p-74980b382/)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freory%2Fsmart_file_agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Freory%2Fsmart_file_agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freory%2Fsmart_file_agent/lists"}