Kedu keeps a written history of your AI coding sessions as plain files you own — so the next agent picks up where the last one left off.
The problem
You explain the architecture, the decisions, the dead ends, what's half-finished. Then the session ends — and all of that understanding evaporates. Next time, you start over.
Close the chat or hit the context limit, and the shared understanding is simply gone.
Switch from Claude Code to Cursor — or hand off to a teammate — and the new agent knows nothing.
Platform "memory" lives on someone else's servers. You can't read it, edit it, or take it with you.
Long sessions are compacted into lossy recaps — and the detail you needed is the first thing dropped.
The idea
You direct the agent; it takes the notes. Nothing is logged silently in the background — you decide what gets recorded.
Record a whole session, or point at the specific things worth keeping. The agent drafts the note; you stay in control of what's saved.
Kedu keeps the record as-is — it won't evict or compress it the way a context window does.
Deterministic keyword and regex search across every record — no embeddings, no fuzzy guessing.
Claude, Codex, Kiro, Cursor — or whatever comes next — starts from the same written record of what happened.
The model reasons from real records you can open, diff, and audit — not memory it invented.
Cross-agent continuity
Kedu doesn't try to become the agent. It gives whatever tool you're using the same durable handoff record — stored in your repo and your home directory.
What Kedu is not
Try it in five minutes
Install from source, wire it into your agent, log a decision — then open a different agent in the same repo and watch it recover the thread.
Records live under your project and ~/.kedu. Read, diff, edit, back up, redact.
Once saved, a record is preserved — not repeatedly summarized down into a lossy recap.
Scrub secrets at write-time or after the fact. Uninstall never deletes your records.
刻牍 · to inscribe records