--- title: "planning-with-files vs agents-from-scratch" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/othmanadi-planning-with-files-vs-pguso-agents-from-scratch" tools: ["othmanadi-planning-with-files", "pguso-agents-from-scratch"] --- # planning-with-files vs agents-from-scratch *GraphCanon updated Aug 19, 2026* ## Verdict Pick planning-with-files if a tool designed for providing persistent file-based planning in long-running AI coding tasks; pick agents-from-scratch if 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. [planning-with-files](https://www.skills.sh/othmanadi/planning-with-files/planning-with-files) reports 26k GitHub stars, 2.2k forks, and 9 open issues, last pushed Aug 19, 2026. [agents-from-scratch](https://github.com/pguso/agents-from-scratch) has 954 stars, 240 forks, and 3 open issues, last pushed Jul 25, 2026. Figures are from public GitHub metadata via [planning-with-files's repository](https://github.com/OthmanAdi/planning-with-files) and [agents-from-scratch's repository](https://github.com/pguso/agents-from-scratch). | | [planning-with-files](/tools/othmanadi-planning-with-files.md) | [agents-from-scratch](/tools/pguso-agents-from-scratch.md) | | --- | --- | --- | | Tagline | Persistent file-based planning for AI coding agents | Build AI agents locally without relying on frameworks or cloud APIs. | | Stars | 26,250 | 954 | | Forks | 2,199 | 240 | | Open issues | 9 | 3 | | Language | Shell | Python | | Adopt for | A tool designed for providing persistent file-based planning in long-running AI coding tasks. | 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. | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT License: Permissive licensing allowing free use and distribution for both commercial and non-commercial purposes. | | Categories | AI Agents, Developer Tools | AI Agents, Developer Tools | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [planning-with-files](/tools/othmanadi-planning-with-files.md) | [agents-from-scratch](/tools/pguso-agents-from-scratch.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Active (82%) | | Days since push | 0d | 18d | | Open issues (now) | 9 | 3 | | Stars delta | +691 (30d) | Unknown | | Open issues delta | +4 (30d) | Unknown | | Full report | [trust report](/tools/othmanadi-planning-with-files/trust.md) | [trust report](/tools/pguso-agents-from-scratch/trust.md) | ## Decision facts: planning-with-files - **Pricing:** freemium - Freely available under MIT License; community-supported. - **Adopt for:** A tool designed for providing persistent file-based planning in long-running AI coding tasks. ## Decision facts: agents-from-scratch - **Requirements:** Min 8 GB RAM; Local large language model availability is critical as the tool does not utilize any cloud APIs. - **Adopt for:** 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. - **License detail:** MIT License: Permissive licensing allowing free use and distribution for both commercial and non-commercial purposes. ## Choose when ### Choose planning-with-files if… - planning-with-files is primarily Shell; agents-from-scratch is Python. - Pricing: Freely available under MIT License; community-supported.. - Tags unique to planning-with-files: agent-skills, claude-code, codex, coding-agent. - - When your coding agent needs to retain plans across sessions without context loss. ### Choose agents-from-scratch if… - agents-from-scratch is primarily Python; planning-with-files is Shell. - Requirements: Min 8 GB RAM; Local large language model availability is critical as the tool does not utilize any cloud APIs.. - Tags unique to agents-from-scratch: agent-architecture, llm, local-llm, no-framework. - 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. ## When NOT to use planning-with-files - - When you do not need persistent storage for plans, such as short tasks where context is unlikely to be lost. - - For projects that strictly prohibit the use of external file storage for tracking progress due to security concerns. - - If your workflow heavily relies on in-memory planning strategies that are more suitable than disk-based solutions. ## When NOT to use agents-from-scratch - 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. ## Common questions ### What is the difference between planning-with-files and agents-from-scratch? planning-with-files: Persistent file-based planning for AI coding agents. agents-from-scratch: Build AI agents locally without relying on frameworks or cloud APIs.. See the comparison table for live GitHub stats and shared categories. ### When should I choose planning-with-files over agents-from-scratch? Choose planning-with-files over agents-from-scratch when planning-with-files is primarily Shell; agents-from-scratch is Python; Pricing: Freely available under MIT License; community-supported.; Tags unique to planning-with-files: agent-skills, claude-code, codex, coding-agent; - When your coding agent needs to retain plans across sessions without context loss. ### When should I choose agents-from-scratch over planning-with-files? Choose agents-from-scratch over planning-with-files when agents-from-scratch is primarily Python; planning-with-files is Shell; Requirements: Min 8 GB RAM; Local large language model availability is critical as the tool does not utilize any cloud APIs.; Tags unique to agents-from-scratch: agent-architecture, llm, local-llm, no-framework; 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. ### When should I avoid planning-with-files? - When you do not need persistent storage for plans, such as short tasks where context is unlikely to be lost. - For projects that strictly prohibit the use of external file storage for tracking progress due to security concerns. - If your workflow heavily relies on in-memory planning strategies that are more suitable than disk-based solutions. ### When should I avoid agents-from-scratch? 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. ### Is planning-with-files or agents-from-scratch more popular on GitHub? planning-with-files has more GitHub stars (26,250 vs 954). Stars measure visibility, not whether either tool fits your constraints. ### Are planning-with-files and agents-from-scratch open source? Yes - both are open-source projects on GitHub (planning-with-files: MIT, agents-from-scratch: MIT). ### Where can I find alternatives to planning-with-files or agents-from-scratch? GraphCanon lists graph-backed alternatives at [planning-with-files alternatives](/tools/othmanadi-planning-with-files/alternatives) and [agents-from-scratch alternatives](/tools/pguso-agents-from-scratch/alternatives) ([planning-with-files markdown twin](/tools/othmanadi-planning-with-files/alternatives.md), [agents-from-scratch markdown twin](/tools/pguso-agents-from-scratch/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/othmanadi-planning-with-files-vs-pguso-agents-from-scratch.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, planning-with-files or agents-from-scratch? planning-with-files: Very active. agents-from-scratch: Active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for planning-with-files and agents-from-scratch? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [planning-with-files trust report](/tools/othmanadi-planning-with-files/trust); [agents-from-scratch trust report](/tools/pguso-agents-from-scratch/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=othmanadi-planning-with-files`](/api/graphcanon/graph?tool=othmanadi-planning-with-files) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_