Software Digital Twin
Indexes files, symbols, dependencies and references using Tree-sitter, with SHA-256-backed incremental updates and impact analysis.
Build a persistent Software Digital Twin of your repository, trace dependencies, review security and quality findings, and approve verified repairs. Your source stays on your device.
CodeTwin connects indexed files, dependency graphs, findings, test evidence and approved repairs inside one software digital twin.
Indexes files, symbols, dependencies and references using Tree-sitter, with SHA-256-backed incremental updates and impact analysis.
Highlights credential-like literals (redacted), dangerous execution patterns, weak hashes and cross-language risk signals without running the project.
Reviews dependency risks using OSV data and reports evidence and uncertainty rather than turning incomplete checks into passes.
Discovers test configuration separately from execution; Windows can run explicitly selected tests in a restricted sandbox.
Guided scope-limited assessments for sites you own or are permitted to test, with operator approval and source-linked findings.
Review an exact patch, approve it, apply with backups, re-index and retest. A fix is not marked verified without successful retesting.
Uncertain results are not silently reported as passes. A generated patch is never automatically a verified fix.
Select a local project. CodeTwin indexes supported source files, maps symbols and records dependency evidence without running the project.
Inspect quality, security, database, runtime and QA evidence. Review what is confirmed, missing, skipped or inconclusive.
Review bounded patches and exact diffs. Approve changes, retain backups and require post-change retests before calling a finding fixed.
Source indexing and analysis run locally. Active website assessments require authorization and bounded scope; local AI is optional and needs a separately installed compatible model.
Local indexing, static analysis and on-device ML work on your machine. Optional online lookup features, such as a dependency database check, may require network access; inspect each enabled integration before use.
The published v1.0.0 binary release contains Windows x64 EXE and MSI installers. Linux .sh and macOS .command files are launch scripts, not native application installers.
No. On-device AI features require a separately installed, integrity-checked compatible ONNX or GGUF model.
Repair workflows require explicit review and approval of the exact patch before applying it. Source-hash checks, backups and follow-up verification provide additional safeguards.
No. Active website testing is for properties you own or have explicit permission to test, with a bounded scope and approval steps.
No. Test discovery does not mean execution. A pass/fail verdict requires a completed and interpretable test run; inconclusive outcomes remain inconclusive.
Get installer files only from the OpenMind AI Technologies Limited GitHub release. Current stable: v1.0.0.
Recommended for a standard desktop installation.
Download EXE ↗Alternative installer for managed Windows environments.
Download MSI ↗Verify installer integrity using the official SHA256SUMS.txt file. Compare its hash to your downloaded installer.