Claude Code From Scratch AI Agent
by Windy3f3f3f3fBuild your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码，读不动？用 ~5000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓
Claude Code From Scratch is an open-source ai agent by Windy3f3f3f3f, written mainly in Python, with 2,806 GitHub stars and the MIT license. Its code was last updated Jul 9, 2026.
Scan summary: scanned Nov 5, 2026 at commit 0b45236. Seen able to run shell commands. Scan policy
ScannedScanned. The automated checks below ran on the commit shown. Read each line for what was and was not covered.
Full scan at
0b45236 · Nov 5, 2026 ScannedStatic, secrets and dependency checks completed with no critical findings. BuildsIt installed from a fresh machine.
Warning. This check found something worth reading in the findings below. It is not proof of a problem.Static code scanwarnWarning. This check found something worth reading in the findings below. It is not proof of a problem.
Passed. This check ran and found nothing it flags.Secrets scanpassPassed. This check ran and found nothing it flags.
Warning. This check found something worth reading in the findings below. It is not proof of a problem.Dependency audit9 known vulnerabilitieswarnWarning. This check found something worth reading in the findings below. It is not proof of a problem.
Warning. This check found something worth reading in the findings below. It is not proof of a problem.ManifestnonewarnWarning. This check found something worth reading in the findings below. It is not proof of a problem.
Passed. This check ran and found nothing it flags.BuildpassPassed. This check ran and found nothing it flags.
Not applicable. This check does not apply to this kind of project, or it was not run in this scan.Boot & handshaken/aNot applicable. This check does not apply to this kind of project, or it was not run in this scan.
Not applicable. This check does not apply to this kind of project, or it was not run in this scan.Network egressn/aNot applicable. This check does not apply to this kind of project, or it was not run in this scan.
Not applicable. This check does not apply to this kind of project, or it was not run in this scan.Reproducible (×3)n/aNot applicable. This check does not apply to this kind of project, or it was not run in this scan.
Findings (13)
- mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
python/mini_claude/tools.py:428 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
src/prompt.ts:104 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
src/prompt.ts:105 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
src/prompt.ts:106 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
src/tools.ts:500 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
steps/canonical/py/tools.py:209 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
steps/canonical/ts/prompt.ts:36 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
steps/canonical/ts/tools.ts:209 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.brace-expansion@5.0.5: 7 known vulnerabilitiesGHSA-3jxr-9vmj-r5cp, GHSA-6j4f-fj2g-mc7p, GHSA-jxxr-4gwj-5jf2, GHSA-mh99-v99m-4gvg, GHSA-q2hr-2g5m-vwhr +2 more
package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
en/docs/14-testing.md:51 - lowLow. Minor, or common in normal tools. Shown for information.glob@11.1.0: 1 known vulnerabilityGHSA-3g3m-2fjr-6pw4
package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.minimatch@10.2.5: 1 known vulnerabilityGHSA-g3hv-75wg-m249
package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.No manifest declaring network access and environment variables (agent.json)
Network activity
During install
registry.npmjs.org
While running
Not run — the code wasn't started in this scan
Automated result for the commit shown. See our scan policy. View the scan log
Maintainers can claim the listing to rescan, or dispute a result.
Claude Code From Scratch alternatives
View more →Similar ai agents in Coding Agents, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.
| Name | Stars | Licence | Last updated | Scan |
|---|---|---|---|---|
| Claude Code From Scratch (this page) Windy3f3f3f3f | 2.8k | MIT | Jul 9, 2026 | Scanned, no flagged issues |
| AutoGPT Significant-Gravitas | 188k | None found | Nov 1, 2026 | Not scanned yet |
| Langchain langchain-ai | 149k | MIT | Nov 1, 2026 | Scanned, no flagged issues |
| Gemini CLI google-gemini | 109k | Apache-2.0 | Nov 1, 2026 | Scanned, no flagged issues |
| MetaGPT FoundationAgents | 71k | MIT | Jan 21, 2026 | Scanned, no flagged issues |
| Oh My Openagent code-yeongyu | 71k | None found | Nov 1, 2026 | Not scanned yet |