How CortexIDE's agent loop avoids the three-tool early-stop trap
An honest postmortem of an agent loop bug we shipped, why heuristic completion detection fails, and the explicit attempt_completion tool that replaced it.
Read more →
CortexIDE Blog
Engineering notes, release walkthroughs, and design rationale from the team building CortexIDE.
Audit log and checkpoint rollback for AI edits
Two mechanisms in CortexIDE that make AI-driven edits reviewable: a JSONL audit trail of every agent action and per-step file checkpoints you can roll back to.
Read more →
Hybrid BM25 and vector codebase search inside the editor
How CortexIDE's repo indexer combines inverted-index BM25 scoring with optional vector embeddings to retrieve relevant code without sending your repo to a cloud service.
Read more →
Running coding agents fully offline with CortexIDE and Ollama
Walk through CortexIDE's local setup wizard, the curated model pack catalogue, and the hardware-aware recommendation that picks a model your machine can actually run.
Read more →