kurrent.io

# Kurrent Capacitor

> Kurrent Capacitor is an AI-native shared memory solution for coding agents. It records every coding-agent session a team runs — Claude Code, Codex, Gemini CLI, Pi, Copilot CLI, Cursor Agent, Kiro, OpenCode, and Antigravity — and makes that record searchable, shareable, and actionable across the team and across future agent runs. Built by Kurrent, the company behind KurrentDB, the event-native database.

Capacitor captures what agents tried, what teammates rejected, what finally passed, and why it mattered. Sessions are recorded automatically via lightweight hooks installed by the `kcap` CLI (npm: `@kurrent/kcap`) and streamed in real time to a team's Capacitor server (`https://<account>.kcap.ai`), where they can be replayed, recapped, handed to another agent, shared with teammates, scored against team rubrics, and used to review the pull requests they produced. Transcripts are queryable from the CLI, the dashboard, and from inside the agent itself via MCP tools.

Eight core capabilities: Multi-player (live shared sessions and handoffs with zero context loss), Multi-agent (switch coding agents without starting over — start in Claude Code, finish in Codex; failed hypotheses stay ruled out), PR review (review the reasoning, not just the diff — diffs show what, sessions show why), Evals (score sessions against team rubrics, emit judge facts, and promote durable findings into repo guidelines loaded at the next session start), Hosted agents (launch Claude Code or Codex from any browser in an isolated worktree; your device is a remote), Session recall (ask "have we worked on this before?" — the agent searches every session you can see and cites prior decisions instead of restarting the reasoning; decisions stay decided), Review flows (agent-to-agent review loop — your coding agent hands its diff to a separate reviewer, fixes what comes back, and re-submits round after round until it signs off), and Analytics (ask about token spend and usage in plain English; Capacitor answers with auditable tables and charts and never reads your transcripts).

Capacitor launched on June 4, 2026 and is generally available: a self-serve free tier (five seats, no credit card) created from the terminal with `kcap setup`, a paid Team tier, and a talk-to-us Enterprise tier. Kurrent Capacitor is unrelated to the Capacitor mobile framework by Ionic.

## Product

- [Capacitor home](https://www.kurrent.io/): Shared memory for your team's coding agents — overview of all eight capabilities
- [How it works](https://www.kurrent.io/how-it-works): The capture-to-recall loop end to end — how a session becomes searchable, shareable team memory
- [Multi-player](https://www.kurrent.io/multi-player): Share the session, then work together — Slack session links, shared hosted agents, and handoff recaps
- [Multi-agent](https://www.kurrent.io/multi-agent): Switch coding agents without starting over — cross-agent handoff with failed hypotheses ruled out
- [PR review](https://www.kurrent.io/pr-review): Review PRs with the reasoning, not just the diff — the review agent reads what your teammate tried before they wrote it
- [Review flows](https://www.kurrent.io/review-flows): Agent-to-agent review loop — your coding agent hands its diff to a separate reviewer and re-submits until it signs off
- [Evals](https://www.kurrent.io/evals): Stop teaching agents the same repo rules twice — rubric scoring, judge facts, and repo guidance for the next run
- [Hosted agents](https://www.kurrent.io/hosted-agents): Launch a coding agent from any browser in an isolated worktree — two teammates can drive the same agent
- [Session recall](https://www.kurrent.io/session-recall): Search every session your team can see and pull the exact turn where a decision was made
- [Analytics](https://www.kurrent.io/analytics): Ask about token spend and usage in plain English — auditable tables and charts, without reading your transcripts
- [Pricing](https://www.kurrent.io/pricing): Get started free, or talk to us about Enterprise
- [Enterprise](https://www.kurrent.io/enterprise): SSO and a managed rollout for larger teams
- [Get started](https://www.kurrent.io/get-started): Create a free workspace from the terminal with `kcap setup`
- [About](https://www.kurrent.io/about/): The team and the story behind Capacitor

## Documentation

- [Quickstart](https://www.kurrent.io/docs/capacitor/getting-started/quickstart/): One session through the whole Capacitor loop — install, import, hand off, share, and review a PR
- [What is Capacitor](https://www.kurrent.io/docs/capacitor/getting-started/what-is-capacitor/): Concepts and architecture overview
- [System architecture](https://www.kurrent.io/docs/capacitor/getting-started/system-architecture/): How the CLI, hooks, server, and dashboard fit together — and what Capacitor captures
- [Setup Server](https://www.kurrent.io/docs/capacitor/getting-started/setup-server/): One-time admin setup for a team's Capacitor server
- [Setup CLI](https://www.kurrent.io/docs/capacitor/getting-started/setup-cli/): Install `@kurrent/kcap` and run the setup wizard that installs hooks for every supported agent
- [Your first session](https://www.kurrent.io/docs/capacitor/getting-started/your-first-session/): Run and capture a first agent session
- [Import your history](https://www.kurrent.io/docs/capacitor/getting-started/import-your-history/): Bring past coding-agent sessions into Capacitor
- [The dashboard](https://www.kurrent.io/docs/capacitor/using/dashboard/): Sessions, events, traces, token costs, and analytics
- [Analytics](https://www.kurrent.io/docs/capacitor/using/analytics/): Plain-English questions over session usage and token spend
- [Visibility & sharing](https://www.kurrent.io/docs/capacitor/using/visibility-and-sharing/): Control who sees a session
- [Session recap](https://www.kurrent.io/docs/capacitor/using/recap/): Recaps in the terminal and the in-agent skill
- [Session recall](https://www.kurrent.io/docs/capacitor/using/session-recall/): Search every session from inside your agent
- [PR review](https://www.kurrent.io/docs/capacitor/using/pr-review/): The MCP tools behind reviewing a pull request with session context
- [Review flows](https://www.kurrent.io/docs/capacitor/using/review-flows/): The agent-to-agent review loop and its rounds
- [Evaluations](https://www.kurrent.io/docs/capacitor/using/evaluations/): Scoring sessions against team-defined rubrics
- [Facts & curation](https://www.kurrent.io/docs/capacitor/using/facts-and-curation/): How judge facts become durable repo guidelines
- [Curation write-back](https://www.kurrent.io/docs/capacitor/using/curate/): Automatically updating agent guidance files
- [Hosted agents](https://www.kurrent.io/docs/capacitor/using/hosted-agents/): Launching and co-driving agents from the dashboard
- [CLI commands](https://www.kurrent.io/docs/capacitor/cli/commands/): The full `kcap` command surface

## Company & ecosystem

- [Kurrent](https://kurrentdb.kurrent.io/): The company behind Capacitor and KurrentDB, the event-native database (formerly Event Store)
- [kcap-cli on GitHub](https://github.com/kurrent-io/kcap-cli): Kurrent Capacitor CLI — collaboration for the agentic coding era
- [Community Discord](https://discord.gg/9xfcPdTGyq): Talk to the team and other Capacitor users
- [Launch press release](https://www.businesswire.com/news/home/20260604607217/en/Kurrent-Launches-Capacitor-a-First-of-Its-Kind-Solution-for-Humans-and-Coding-Agents-Building-Software-Together): Kurrent launches Capacitor, June 4, 2026

## Optional

- [Administration](https://www.kurrent.io/docs/capacitor/admin/administration/): Server administration
- [Plans & seats](https://www.kurrent.io/docs/capacitor/admin/plans-and-seats/): Managing plans and seats
- [Members & invitations](https://www.kurrent.io/docs/capacitor/admin/members-and-invitations/): Adding teammates to an organization
- [Teams](https://www.kurrent.io/docs/capacitor/admin/teams/): Organizing members into teams
- [Integrations](https://www.kurrent.io/docs/capacitor/admin/integrations/): Connecting external tools
- [AI providers](https://www.kurrent.io/docs/capacitor/admin/ai-providers/): Configuring model providers for evals and assistants
- [Evals admin](https://www.kurrent.io/docs/capacitor/admin/evals/): Administering evaluation runs
- [Eval catalog](https://www.kurrent.io/docs/capacitor/admin/eval-catalog/): The catalog of available evaluations
- [CLI configuration & profiles](https://www.kurrent.io/docs/capacitor/cli/configuration-and-profiles/): Configuring the kcap CLI
- [Terms](https://www.kurrent.io/terms/): Terms of service
- [Privacy](https://www.kurrent.io/privacy/): Privacy policy
- [Cookies](https://www.kurrent.io/cookies/): Cookie policy