Comparison
agents-from-scratch vs cortex-memory
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 zero-config VSCode extension, CLI, and MCP server that provides persistent AI memory for coding sessions, auto-capturing decisions and context for.
Markdown twin · agents-from-scratch alternatives · cortex-memory alternatives
GraphCanon updated Sep 20, 2026
9views this month
vs
Trust & integrity
| Signal | agents-from-scratch | cortex-memory |
|---|---|---|
| Maintenance | Steady (56d since push) As of Sep 20, 2026 · github_public_v1 | Slowing (176d since push) As of Sep 18, 2026 · github_public_v1 |
| Provenance | Not a fork · Personal account As of Sep 20, 2026 · github_public_v1 | Not a fork · Personal account As of Sep 18, 2026 · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of Jul 15, 2026 · osv@v1 | Published findings As of Sep 18, 2026 · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- agents-from-scratch
- Build AI agents locally without relying on frameworks or cloud APIs.
- cortex-memory
- Persistent AI memory for coding sessions, auto-capturing decisions and context.
Stars
- agents-from-scratch
- 1.0k
- cortex-memory
- 8
Forks
- agents-from-scratch
- 251
- cortex-memory
- 2
Open issues
- agents-from-scratch
- 4
- cortex-memory
- 0
Language
- agents-from-scratch
- Python
- cortex-memory
- TypeScript
Adopt for
- agents-from-scratch
- 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
- cortex-memory is a zero-config VSCode extension, CLI, and MCP server that provides persistent AI memory for coding sessions, auto-capturing decisions and context for tools like Claude Code, Cursor, and Cline.
Persona
- agents-from-scratch
- -
- cortex-memory
- -
Runtime
- agents-from-scratch
- -
- cortex-memory
- -
License
- agents-from-scratch
- MIT License: Permissive licensing allowing free use and distribution for both commercial and non-commercial purposes.
- cortex-memory
- MIT License
Last pushed
- agents-from-scratch
- Jul 25, 2026
- cortex-memory
- Mar 25, 2026
Categories
- agents-from-scratch
- AI Agents, Developer Tools
- cortex-memory
- Data & Retrieval, Developer Tools
Trust and health
Maintenance
- agents-from-scratch
- Steady (60%)
- cortex-memory
- Slowing (36%)
Days since push
- agents-from-scratch
- 56d
- cortex-memory
- 176d
Open issues (now)
- agents-from-scratch
- 4
- cortex-memory
- 0
Stars delta
- agents-from-scratch
- +63 (30d)
- cortex-memory
- +1 (30d)
Open issues delta
- agents-from-scratch
- +1 (30d)
- cortex-memory
- 0 (30d)
OSV dependency advisories
- agents-from-scratch
- No lockfile (source not queried)
- cortex-memory
- Published findings
Full report
- agents-from-scratch
- Trust report
- cortex-memory
- Trust report
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.
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.
Choose cortex-memory if…
- cortex-memory is primarily TypeScript; agents-from-scratch is Python.
- Pricing: The tool is open-source under the MIT License, making it free to use, but additional features or services may come at a cost..
- Requirements: Min 2 GB RAM; Requires a compatible AI coding assistant like Claude Code, Cursor, or Cline.; Works best with VSCode, but also supports CLI and MCP server..
- Tags unique to cortex-memory: ai, ai-coding-assistant, ai-memory, claude.
- Also covers Data & Retrieval.
- When you are working with specific AI coding assistants like Claude Code, Cursor, or Cline and need persistent memory across coding sessions.
When NOT to use cortex-memory
- If you are not using AI coding assistants like Claude Code, Cursor, or Cline, as cortex-memory is specifically designed to work with these tools.
- When you prefer a tool that does not automatically capture decisions and context, and you want full control over what is stored and retrieved.
- If you are working in an environment where zero-configuration tools are not suitable, and you require extensive customization options.
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (pguso/agents-from-scratch) · observed Sep 20, 2026
- GitHub forks (pguso/agents-from-scratch) · observed Sep 20, 2026
- Last push (pguso/agents-from-scratch) · observed Jul 25, 2026
- License file (MIT) · observed Sep 20, 2026
- Decision facts (enrichment) · observed Jul 17, 2026
- Trust scan (lockfile / OSV) · observed Jul 15, 2026
- GitHub stars (SKULLFIRE07/cortex-memory) · observed Sep 20, 2026
- GitHub forks (SKULLFIRE07/cortex-memory) · observed Sep 20, 2026
- Last push (SKULLFIRE07/cortex-memory) · observed Mar 25, 2026
- License file (MIT) · observed Sep 20, 2026
- Decision facts (enrichment) · observed Sep 18, 2026
- Trust scan (lockfile / OSV) · observed Sep 18, 2026
GitHub stars on cards: agents-from-scratch 1.0k · cortex-memory 8 (synced Sep 20, 2026).
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 coding sessions, auto-capturing decisions and context.. 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: The tool is open-source under the MIT License, making it free to use, but additional features or services may come at a cost.; Requirements: Min 2 GB RAM; Requires a compatible AI coding assistant like Claude Code, Cursor, or Cline.; Works best with VSCode, but also supports CLI and MCP server.; Tags unique to cortex-memory: ai, ai-coding-assistant, ai-memory, claude; Also covers Data & Retrieval; When you are working with specific AI coding assistants like Claude Code, Cursor, or Cline and need persistent memory across coding sessions.
- 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 are not using AI coding assistants like Claude Code, Cursor, or Cline, as cortex-memory is specifically designed to work with these tools. When you prefer a tool that does not automatically capture decisions and context, and you want full control over what is stored and retrieved. If you are working in an environment where zero-configuration tools are not suitable, and you require extensive customization options.
- Is agents-from-scratch or cortex-memory more popular on GitHub?
- agents-from-scratch has more GitHub stars (1,017 vs 8). 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 and cortex-memory alternatives (agents-from-scratch markdown twin, cortex-memory markdown twin), 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 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: Steady. 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; cortex-memory trust report.