Kitaru Adds Replay and Comparative Experiments
strickvl · x · 2026-07-13
Kitaru has added a trace replay feature: you can resume execution from a checkpoint in an old trace, modify configurations at any step (like mocking tool calls or switching models), and compare the new and old execution results to see differences. The author also mentioned that Kitaru's capabilities are integrated with components like MCP, allowing an agent to drive these experiments directly. The project is free and open-source (including the UI) and supports a local mode via `kitaru login --local`.
More from coding & agent
- AI makes software easier to build, but it also lowers the floor on quality — paw_lean · 2026-07-21
- Fable coding run costs $6.69 for 67 lines of code in a 4-minute job — bytebot · 2026-07-21
- Cursor writes better code, but ChatGPT can still control the computer — vista8 · 2026-07-21
- Agents can remember facts, but still forget how to do the job — No_Advertising2536 · 2026-07-21
- Agent skills for project downgrade and troubleshooting tested in CLAD on LS 5.22 — stspanho · 2026-07-21
- Open-source B-roll skill turns scripts into 5-second vertical clips with Codex and Gemini — yangyi · 2026-07-21