Keddy

Session Intelligence for your coding agent.

Every plan your agent drafted, every change you rejected, the full thread. Plus full-text search across every past session.

---

Every agentic session leaves a JSONL trail. Endless possibilities inside each exchange. You *can* dig through it. It costs hours, burns tokens, and the answer usually isn't right. Keddy turns every session into structured history you and your agent can pull from.

• Your agent reaches back in through MCP tools — any past session, plan, or file history, pulled on demand without re-explaining.
• You reach back through a local dashboard — timelines, plan versions, and milestones, all in your browser at localhost:3737.
• Nothing leaves your machine. No telemetry, no cloud sync; optional AI agents use your own API key.

https://github.com/user-attachments/assets/649874d9-cc1f-401a-9d6a-e6f22e5742f4

"Keddy is the single most impactful memory tool I've integrated."

From Opus 4.7, after using Keddy across multi-project sessions. [Full evaluation ↓](#the-agents-perspective)

How Keddy Works

Four Claude Code hooks feed a local session reader that parses the transcript and writes to a SQLite database on your machine. The database serves two surfaces: MCP tools Claude can call to pull context, and a dashboard you open in your browser to review sessions visually. See [`doc