Show HN: Smriti: Shared Reasoning State for Claude Code and Codex
Smriti Code introduces a version control system for project reasoning states, allowing multiple coding agents to collaborate without overwriting each other's work. It provides structured, versioned snapshots of decisions and current tasks, enhancing coordination among agents. Unlike traditional markdown notes, Smriti offers features like active claims and task IDs for better management of collaborative coding efforts.
- ▪Smriti is designed for multi-agent reasoning, providing structured snapshots of project decisions.
- ▪It allows agents to coordinate effectively without duplicating efforts or losing track of changes.
- ▪The system includes unique features like active claims and freshness checks that traditional markdown cannot provide.
Opening excerpt (first ~120 words) tap to expand
Smriti Code has Git. Multi-agent reasoning does not. Smriti is version control for project reasoning state — versioned, structured, branchable snapshots of what was decided, what's still open, and what each agent is doing right now. So multiple coding agents can coordinate on the same codebase without overwriting each other's thinking. When you run multiple coding agents on the same project — Claude Code and Codex, or two Claude Code sessions — they share no state. Each agent starts from scratch, re-discovers decisions already made, and occasionally duplicates work another agent is already doing. The standard workaround is HANDOFF.md / NOTES.md. That works until reasoning needs to branch, be compared, be restored, or be validated against the actual repo.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.