{"data":{"slug":"pguso-agents-from-scratch","name":"agents-from-scratch","tagline":"Build AI agents locally without relying on frameworks or cloud APIs.","github_url":"https://github.com/pguso/agents-from-scratch","owner":"pguso","repo":"agents-from-scratch","owner_avatar_url":"https://avatars.githubusercontent.com/u/4007140?v=4","primary_language":"Python","stars":1017,"forks":251,"topics":["agent-architecture","ai-agents","ai-education","ai-from-scratch","artificial-intelligence","llama","llm","local-llm","machine-learning","no-framework","open-source-education","prompt-engineering","python"],"archived":false,"github_pushed_at":"2026-07-25T15:42:36+00:00","maintenance_label":"Steady","stars_delta_30d":63,"url":"https://www.graphcanon.com/tools/pguso-agents-from-scratch","markdown_url":"https://www.graphcanon.com/tools/pguso-agents-from-scratch.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pguso-agents-from-scratch","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pguso-agents-from-scratch","description":"Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.","homepage_url":null,"license":"MIT","open_issues":4,"watchers":13,"ai_summary":"A project that guides users in constructing artificial intelligence agents from the ground up using only local large language models and Python, emphasizing transparency and understanding of the underlying principles of agent architecture.","readme_excerpt":"## Quick Start\n\n**For detailed setup instructions, see [QUICKSTART.md](QUICKSTART.md)**\n\nIn short:\n1. Install dependencies: `pip install -r requirements.txt`\n2. Download a GGUF model to the `models/` folder\n3. Run: `python complete_example.py`\n\n**Note:** The `complete_example.py` file contains executable code examples demonstrating all 12 lessons. You can use it as a reference to see how all the concepts fit together.\n\n---\n\n## License\n\nMIT License - see LICENSE file","github_created_at":"2025-12-22T09:09:42+00:00","created_at":"2026-07-15T10:58:41.301851+00:00","updated_at":"2026-09-20T05:00:36.217444+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"}],"tags":[{"slug":"agent-architecture","name":"agent-architecture"},{"slug":"ai-agents","name":"ai-agents"},{"slug":"llm","name":"llm"},{"slug":"local-llm","name":"local-llm"},{"slug":"no-framework","name":"no-framework"},{"slug":"prompt-engineering","name":"prompt-engineering"},{"slug":"python","name":"python"}],"trust":{"provenance":{"is_fork":false,"github_id":1120991338,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T05:00:33.509Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":56,"last_release_at":null,"stars_delta_30d":63,"open_issues_delta_30d":1},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:58:42.498Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T05:00:34.599Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-20T05:00:34.599Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T05:00:34.599Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Local large language model availability is critical as the tool does not utilize any cloud APIs."],"min_ram_gb":8,"requires_docker":false},"constraints":{"min_ram_gb":8,"requires_docker":false},"when_to_use":["You plan to teach yourself or others about the fundamentals of creating AI agents from ground zero with complete transparency into each layer of architecture.","Your project requires a local-only setup absent any internet connections for data processing, thus eliminating outside variables and ensuring privacy."],"when_not_to_use":["You are working on an application that needs to be deployed quickly. The tool's approach from first principles can be time-consuming compared to using established frameworks.","If you need scalability or cloud capabilities such as easy scaling with demand, this tool will not provide these features since it strictly operates on local infrastructure."],"source":"enrich:decision_facts","observed_at":"2026-07-17T10:16:48.326Z"},"constraint_facets":{"min_ram_gb":8,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Min 8 GB RAM; Local large language model availability is critical as the tool does not utilize any cloud APIs."},{"label":"Adopt for","value":"agents-from-scratch is for those who want absolute control over their AI agent development using only local resources and Python, focusing on deep learning without relying on external frameworks or cloud dependencies."},{"label":"License detail","value":"MIT License: Permissive licensing allowing free use and distribution for both commercial and non-commercial purposes."}]}}