--- title: "agents-from-scratch vs cortex-memory" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/pguso-agents-from-scratch-vs-skullfire07-cortex-memory" tools: ["pguso-agents-from-scratch", "skullfire07-cortex-memory"] --- # agents-from-scratch vs cortex-memory *GraphCanon updated Aug 12, 2026* ## Verdict 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; pick cortex-memory if cortex-memory is a TypeScript-based tool with an MIT license that provides persistent memory capabilities for Claude Code, Cursor & Cline through a VSCode. [agents-from-scratch](https://github.com/pguso/agents-from-scratch) reports 954 GitHub stars, 240 forks, and 3 open issues, last pushed Jul 25, 2026. [cortex-memory](https://marketplace.visualstudio.com/items?itemName=cortex-dev.cortex-ai-memory) has 7 stars, 1 forks, and 0 open issues, last pushed Mar 25, 2026. Figures are from public GitHub metadata via [agents-from-scratch's repository](https://github.com/pguso/agents-from-scratch) and [cortex-memory's repository](https://github.com/SKULLFIRE07/cortex-memory). | | [agents-from-scratch](/tools/pguso-agents-from-scratch.md) | [cortex-memory](/tools/skullfire07-cortex-memory.md) | | --- | --- | --- | | Tagline | Build AI agents locally without relying on frameworks or cloud APIs. | Persistent AI memory for Claude Code, Cursor & Cline with a VSCode extension and CLI. | | Stars | 954 | 7 | | Forks | 240 | 1 | | Open issues | 3 | 0 | | Language | Python | TypeScript | | 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. | cortex-memory is a TypeScript-based tool with an MIT license that provides persistent memory capabilities for Claude Code, Cursor & Cline through a VSCode extension and CLI. | | Persona | - | - | | Runtime | - | - | | License | MIT License: Permissive licensing allowing free use and distribution for both commercial and non-commercial purposes. | MIT | | Categories | AI Agents, Developer Tools | Data & Retrieval, Developer Tools | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [agents-from-scratch](/tools/pguso-agents-from-scratch.md) | [cortex-memory](/tools/skullfire07-cortex-memory.md) | | --- | --- | --- | | Maintenance | Active (82%) | Slowing (36%) | | Days since push | 18d | 128d | | Open issues (now) | 3 | 0 | | Full report | [trust report](/tools/pguso-agents-from-scratch/trust.md) | [trust report](/tools/skullfire07-cortex-memory/trust.md) | ## 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. ## Decision facts: cortex-memory - **Pricing:** freemium - Being open-source under the MIT license, cortex-memory is free for use, although specific pricing around value-added services or enterprise support are not detailed in the provided repository content. - **Adopt for:** cortex-memory is a TypeScript-based tool with an MIT license that provides persistent memory capabilities for Claude Code, Cursor & Cline through a VSCode extension and CLI. ## Choose when ### Choose agents-from-scratch if… - agents-from-scratch is primarily Python; cortex-memory is TypeScript. - 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, ai-agents, llm, local-llm. - Also covers AI Agents. - 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. ### Choose cortex-memory if… - cortex-memory is primarily TypeScript; agents-from-scratch is Python. - Pricing: Being open-source under the MIT license, cortex-memory is free for use, although specific pricing around value-added services or enterprise support are not detailed in the provided repository content.. - Tags unique to cortex-memory: ai, ai-coding-assistant, ai-memory, claude-code. - Also covers Data & Retrieval. - If you are working extensively with Claude Code, Cursor & Cline and want to automatically capture decisions, patterns, and context across sessions without configuration. ## 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. ## When NOT to use cortex-memory - If you prefer not using tools that integrate deeply with specific AI platforms like Claude Code, which may limit its usefulness in environments where multiple or different platforms are used. - In scenarios where custom configuration is required, as cortex-memory emphasizes zero-config setup which might not be adaptable to highly customized workflows. ## Common questions ### What is the difference between agents-from-scratch and cortex-memory? agents-from-scratch: Build AI agents locally without relying on frameworks or cloud APIs.. cortex-memory: Persistent AI memory for Claude Code, Cursor & Cline with a VSCode extension and CLI.. See the comparison table for live GitHub stats and shared categories. ### When should I choose agents-from-scratch over cortex-memory? Choose agents-from-scratch over cortex-memory when agents-from-scratch is primarily Python; cortex-memory is TypeScript; 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, ai-agents, llm, local-llm; Also covers AI Agents; 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 choose cortex-memory over agents-from-scratch? Choose cortex-memory over agents-from-scratch when cortex-memory is primarily TypeScript; agents-from-scratch is Python; Pricing: Being open-source under the MIT license, cortex-memory is free for use, although specific pricing around value-added services or enterprise support are not detailed in the provided repository content.; Tags unique to cortex-memory: ai, ai-coding-assistant, ai-memory, claude-code; Also covers Data & Retrieval; If you are working extensively with Claude Code, Cursor & Cline and want to automatically capture decisions, patterns, and context across sessions without configuration. ### 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. ### When should I avoid cortex-memory? If you prefer not using tools that integrate deeply with specific AI platforms like Claude Code, which may limit its usefulness in environments where multiple or different platforms are used. In scenarios where custom configuration is required, as cortex-memory emphasizes zero-config setup which might not be adaptable to highly customized workflows. ### Is agents-from-scratch or cortex-memory more popular on GitHub? agents-from-scratch has more GitHub stars (954 vs 7). Stars measure visibility, not whether either tool fits your constraints. ### Are agents-from-scratch and cortex-memory open source? Yes - both are open-source projects on GitHub (agents-from-scratch: MIT, cortex-memory: MIT). ### Where can I find alternatives to agents-from-scratch or cortex-memory? GraphCanon lists graph-backed alternatives at [agents-from-scratch alternatives](/tools/pguso-agents-from-scratch/alternatives) and [cortex-memory alternatives](/tools/skullfire07-cortex-memory/alternatives) ([agents-from-scratch markdown twin](/tools/pguso-agents-from-scratch/alternatives.md), [cortex-memory markdown twin](/tools/skullfire07-cortex-memory/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/pguso-agents-from-scratch-vs-skullfire07-cortex-memory.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agents-from-scratch or cortex-memory? agents-from-scratch: Active. cortex-memory: Slowing. 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 agents-from-scratch and cortex-memory? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agents-from-scratch trust report](/tools/pguso-agents-from-scratch/trust); [cortex-memory trust report](/tools/skullfire07-cortex-memory/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=pguso-agents-from-scratch`](/api/graphcanon/graph?tool=pguso-agents-from-scratch) - 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/_