---
title: "surf vs agents-from-scratch"
type: "comparison"
canonical_url: "https://www.graphcanon.com/compare/e2b-dev-surf-vs-pguso-agents-from-scratch"
tools: ["e2b-dev-surf", "pguso-agents-from-scratch"]
---

# surf vs agents-from-scratch

*GraphCanon updated Sep 20, 2026*

## Verdict

Pick surf if surf is an AI agent that automates interaction within E2B's virtual desktop environment via natural language commands; 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.

[surf](https://surf.e2b.dev) reports 870 GitHub stars, 143 forks, and 8 open issues, last pushed Sep 9, 2026. [agents-from-scratch](https://github.com/pguso/agents-from-scratch) has 1.0k stars, 251 forks, and 4 open issues, last pushed Jul 25, 2026. Figures are from public GitHub metadata via [surf's repository](https://github.com/e2b-dev/surf) and [agents-from-scratch's repository](https://github.com/pguso/agents-from-scratch).

| | [surf](/tools/e2b-dev-surf.md) | [agents-from-scratch](/tools/pguso-agents-from-scratch.md) |
| --- | --- | --- |
| Tagline | AI agent powered by OpenAI for interacting with E2B's virtual desktop environment via natural language | Build AI agents locally without relying on frameworks or cloud APIs. |
| Stars | 870 | 1,017 |
| Forks | 143 | 251 |
| Open issues | 8 | 4 |
| Language | TypeScript | Python |
| Adopt for | Surf is an AI agent that automates interaction within E2B's virtual desktop environment via natural language commands. | 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 | Apache-2.0, providing free use, modification, and distribution with conditions that ensure legal use and attribution. | 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._

| | [surf](/tools/e2b-dev-surf.md) | [agents-from-scratch](/tools/pguso-agents-from-scratch.md) |
| --- | --- | --- |
| Maintenance | Active (82%) | Steady (60%) |
| Days since push | 10d | 56d |
| Open issues (now) | 8 | 4 |
| Stars delta | +27 (30d) | +63 (30d) |
| Open issues delta | 0 (30d) | +1 (30d) |
| Owner type | Organization | User |
| Full report | [trust report](/tools/e2b-dev-surf/trust.md) | [trust report](/tools/pguso-agents-from-scratch/trust.md) |

## Decision facts: surf

- **Pricing:** freemium - Free for usage under the Apache license; premium features or services may incur additional fees depending on OpenAI's and E2B’s policies.
- **Adopt for:** Surf is an AI agent that automates interaction within E2B's virtual desktop environment via natural language commands.
- **License detail:** Apache-2.0, providing free use, modification, and distribution with conditions that ensure legal use and attribution.

## 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 surf if…

- surf is primarily TypeScript; agents-from-scratch is Python.
- License: surf is Apache-2.0, agents-from-scratch is MIT.
- Pricing: Free for usage under the Apache license; premium features or services may incur additional fees depending on OpenAI's and E2B’s policies..
- Tags unique to surf: ai, automation, cua, desktop.
- When you need to interact with E2B’s specific virtual desktop environment and require seamless natural language understanding capabilities from OpenAI.

### Choose agents-from-scratch if…

- agents-from-scratch is primarily Python; surf is TypeScript.
- License: agents-from-scratch is MIT, surf is Apache-2.0.
- 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.
- 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 surf

- Avoid using Surf if your projects do not involve E2B’s virtual desktop environment or if you require integration with other specific virtual desktop software unsupported by this tool.
- Do not opt for Surf if you need direct control over the execution of tasks and prefer manual interaction rather than relying on AI to interpret commands.

## 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 surf and agents-from-scratch?

surf: AI agent powered by OpenAI for interacting with E2B's virtual desktop environment via natural language. 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 surf over agents-from-scratch?

Choose surf over agents-from-scratch when surf is primarily TypeScript; agents-from-scratch is Python; License: surf is Apache-2.0, agents-from-scratch is MIT; Pricing: Free for usage under the Apache license; premium features or services may incur additional fees depending on OpenAI's and E2B’s policies.; Tags unique to surf: ai, automation, cua, desktop; When you need to interact with E2B’s specific virtual desktop environment and require seamless natural language understanding capabilities from OpenAI.

### When should I choose agents-from-scratch over surf?

Choose agents-from-scratch over surf when agents-from-scratch is primarily Python; surf is TypeScript; License: agents-from-scratch is MIT, surf is Apache-2.0; 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; 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 surf?

Avoid using Surf if your projects do not involve E2B’s virtual desktop environment or if you require integration with other specific virtual desktop software unsupported by this tool. Do not opt for Surf if you need direct control over the execution of tasks and prefer manual interaction rather than relying on AI to interpret commands.

### 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 surf or agents-from-scratch more popular on GitHub?

agents-from-scratch has more GitHub stars (1,017 vs 870). Stars measure visibility, not whether either tool fits your constraints.

### Are surf and agents-from-scratch open source?

Yes - both are open-source projects on GitHub (surf: Apache-2.0, agents-from-scratch: MIT).

### Where can I find alternatives to surf or agents-from-scratch?

GraphCanon lists graph-backed alternatives at [surf alternatives](/tools/e2b-dev-surf/alternatives) and [agents-from-scratch alternatives](/tools/pguso-agents-from-scratch/alternatives) ([surf markdown twin](/tools/e2b-dev-surf/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/e2b-dev-surf-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, surf or agents-from-scratch?

surf: Active. agents-from-scratch: Steady. 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 surf and agents-from-scratch?

GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [surf trust report](/tools/e2b-dev-surf/trust); [agents-from-scratch trust report](/tools/pguso-agents-from-scratch/trust).

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/graph?tool=e2b-dev-surf`](/api/graphcanon/graph?tool=e2b-dev-surf)
- 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/_
