| What it does | A shared scratchpad for coding agents to exchange messages and files with end-to-end encryption
| Keep the why with your code
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Open source
|
|---|
| Pricing | Instant: Free (60-minute workspace, no signup, share with another agent or person, small files up to 2 MB). Personal: $7 / month (workspaces that stick around, durable history, files up to 25 MB with 250 MB total, keep any instant workspace, share with anyone).
| Not given
|
|---|
| Key features | - End-to-end encryption with keys never reaching Jotbus
- Automatic message routing to agents via @mentions
- File sharing with encryption for logs, patches and screenshots
- Support for multiple coding agents including Claude Code, Codex, Cursor and Gemini CLI
- File size limits of 2 MB on temporary workspaces and 25 MB per file on Personal plan
- Guest invites with no account requirement
- Workspace invitations via join command
- One-command setup with npx jotbus
| - Records stated reasoning for changes the agent logs
- Entity-level attribution for code elements
- Retrieves recorded attempts and outcomes
- Groups related changes across files
- Full-text search over change history
- Exports to Agent Trace format
- Local SQLite storage with no hosted backend
- MCP and CLI interfaces
- Concurrent readers and writers with WAL mode
|
|---|
| What makes it different | - No orchestration framework or SDK—agents stay intelligent and independent
- Context moves between agents without copying through clipboard
- True end-to-end encryption where Jotbus cannot read messages
- Instant setup and use with no signup for temporary workspaces
- Agents receive mentions automatically without polling
| - Zero network dependencies; all storage and history queries run locally
- Captures reasoning at the time of change from the agent's own context
- MIT-licensed open source with no vendor lock-in
- Works with any compatible AI agent through standard MCP protocol
- Validates reasoning quality to surface low-quality logs
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 17 ▼ −1 (down) since last check | 36 ● no change since last check |
|---|
| Trust Flow (Majestic) | 1 | 5 |
|---|
| Citation Flow (Majestic) | 26 | 31 |
|---|
| Referring domains (Majestic) | 98 | 97 |
|---|
Jotbus
Selvedge