emiraksay

Keddy — Development skill for Claude Code

Development community

Session intelligence for your coding agent.

How to install Keddy

This entry records only its repository, not the path inside it, so there is no exact command to give. Open emiraksay/keddy and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Keddy does

Session intelligence for your coding agent.

Alternatives in Development

Notion Meeting Intelligence — Prep meetings by pulling Notion context and tailoring agendas 14.6k ★
Serena — Code Intelligence Advanced code navigation and semantic search 14k ★
/intel — Fetch actionable intelligence for a target 1.8k ★

README

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