Qarinah is an open-source project-memory layer for coding agents. It records evidence-linked project events, builds compact verifiable read models, and retrieves cited context so agents can resume work without replaying an entire history. It ships as an npm package, CLI, MCP server, public schemas, local dashboard, and adapters for major coding-agent workflows.
Evidence-linked append-only project ledger
Compact, cited context retrieval
CLI and native MCP transport
Local dashboard and linked project graph
Cross-agent import and export adapters
Reproducible public evaluations
Resume a coding project with durable decisions and evidence
Share project context across coding-agent tools
Audit why an agent made a change
Build compact handoff packs for new sessions
Keep local project memory under operator control

I built Qarinah after watching coding agents repeatedly lose decisions, replay huge project histories, and hand work between tools without durable evidence. Qarinah keeps a local, verifiable project memory so a fresh agent can recover cited context instead of starting from zero. I would love feedback from maintainers using multiple coding agents.

I built Qarinah after watching coding agents repeatedly lose decisions, replay huge project histories, and hand work between tools without durable evidence. Qarinah keeps a local, verifiable project memory so a fresh agent can recover cited context instead of starting from zero. I would love feedback from maintainers using multiple coding agents.
Find your next favorite product or submit your own. Made by @FalakDigital.
Copyright ©2025. All Rights Reserved