How it works

One durable work history across every agent and session.

RecaPod keeps portable continuity outside any single AI provider. Checkpoints stay structured and chronological while least-privilege capability links keep reading and writing separate.

01

Create one durable history

Start with a broad cross-agent history. Create another pod only when a client, team, or sensitive project needs its own boundary.

02

Give agents the handoff

At session start, an agent can load focused read-only context. At completion, it appends a structured checkpoint through a separate write-only link.

03

Continue from anywhere

Review checkpoints grouped by date and project, search across agents, or export clean Markdown for the next environment.

Separate capabilities by design.

The checkpoint link can add records but never read them. The continuation link can retrieve this pod’s history but never write or manage the owner account. Both are bearer secrets, can be rotated independently, and stop working when the pod is archived. RecaPod also tells agents never to submit credentials, cookies, authorization headers, personal data, or hidden reasoning.