working-across-computers
This skill enables agents to coordinate work across multiple computers, including Cloud and local machines.
Identity proven by GitHub's verified organisation badge (letta-ai)
- Agents
- Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, claude.ai and API
- License
- Apache-2.0 (permissive)
- Pin
- c1033d9pinned Oct 9, 2026
- Context cost
- about 1,300 tokenswhen the skill loads
- GitHub stars
- 3,549on letta-ai/letta-code
- Scripts
- None found
What it does
“Guides work across Cloud, local, and other available computers, including teleporting conversations, running remote subagents, and transferring files. Load when a request needs the user's laptop or another machine's files, apps, or tools; when connecting a computer; or when moving or delegating work between local and Cloud in either direction, including running Cloud subagents from local.”
Generated summary from the skill's own text
This skill enables agents to coordinate work across multiple computers, including Cloud and local machines. It provides commands to teleport conversations between systems, delegate tasks to remote subagents, and transfer files between computers while managing workspace separation.
When to use it
- User needs to access files or tools on their local machine from Cloud
- Work must move from one computer to another mid-conversation
- A task requires delegating to a subagent on a different computer
- Connecting a previously unavailable local machine for remote access
When not to
- Work stays on a single computer throughout
- User needs arbitrary remote filesystem access beyond Cloud sandboxes
Install
These commands install from the publisher's repository and need no account.
skills CLI
npx skills add letta-ai/letta-code --skill working-across-computersInstalls from the repository's default branch, which may have changed since the commit we checked.
GitHub CLI 2.90 or later
gh skill install letta-ai/letta-code working-across-computers@c1033d9f7e8863a869cd2031805cfd2c66c165b9Installs the commit we checked (c1033d9).
Copy by hand
Download the folder at c1033d9 and put it in .claude/skills/working-across-computers for Claude Code and in .agents/skills/working-across-computers for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.
Copy for your agent
A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.
Prompt
Install the agent skill "working-across-computers" by Letta. Source, pinned to commit c1033d9f7e8863a869cd2031805cfd2c66c165b9: https://github.com/letta-ai/letta-code/tree/c1033d9f7e8863a869cd2031805cfd2c66c165b9/src/skills/builtin/working-across-computers 1. Download that folder at exactly this commit. Do not use the default branch. 2. Copy every file unchanged, keeping the folder structure, into .claude/skills/working-across-computers/ for Claude Code and .agents/skills/working-across-computers/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist. 3. Do not edit the files, and do not run any script in the folder unless I ask you to. 4. When you are done, list the files you copied and where you put them. Listing and checks: https://www.agentnative.dev/skills/letta/working-across-computers
SKILL.md at the pin
---
name: working-across-computers
description: Guides work across Cloud, local, and other available computers, including teleporting conversations, running remote subagents, and transferring files. Load when a request needs the user's laptop or another machine's files, apps, or tools; when connecting a computer; or when moving or delegating work between local and Cloud in either direction, including running Cloud subagents from local.
---
# Working Across Computers
## Discover access before declaring a limitation
The current filesystem is not the full set of computers you can use. When a request needs another computer, run `letta teleport list`. If a suitable computer is available, delegate there; otherwise follow the [connection instructions](references/connect-a-computer-for-remote-access.md). Do not infer that another computer is inaccessible merely because you are running in Cloud.
## Choose where to work
- When running in Cloud, prefer staying there and delegating local work to subagents on the relevant computer.
- If the user explicitly asks to move this conversation locally or elsewhere, teleport it.
- Moving a conversation that started locally into Cloud is a normal workflow: transfer needed files first, then teleport.
| Intent | Mechanism |
|---|---|
| Run work elsewhere while staying here | `Agent` |
| Bring a remote file into a Cloud conversation | Remote agent: `sandbox upload` |
| Put a Cloud file onto another computer | Remote agent: `sandbox download` |
| Continue this conversation elsewhere | `teleport` |
Conversation history and agent memory follow the conversation. Files, working directories, installed tools, credentials, and running services belong to each computer; teleporting does not copy the workspace.
For remote subagents, set `computer` and pass source paths and destination conversation IDs explicitly. Use the `Agent` tool definition for invocation and resume options.
If the user wants to connect a new computer, `letta teleport list` has no suitable target, or the requested local machine is missing or unreachable, read [Connect a computer for remote access](references/connect-a-computer-for-remote-access.md).
## Move this conversation
**Run the teleport handoff alone as the final tool call.** After success, do not poll or run more source-side tools; the same conversation resumes at the destination automatically. Set the working directory and check required setup there. If teleport fails, stay on the source and resolve the error before retrying. The Cloud sandbox remains available while you work elsewhere.
### Local → Cloud
Upload any files needed in Cloud:
```bash
letta sandbox upload <local-path>
```
Keep the returned paths, repository/branch, and next action in context, then create or resume this conversation's Cloud sandbox:
```bash
letta teleport cloud
```
### Cloud → other computers
List available computers:
```bash
letta teleport list
```
Have a remote subagent download any needed files and verify completion before moving. Use a returned computer name, device ID, or connection ID:
```bash
letta teleport <computer>
```
With exactly one online Desktop, open with Remote Access enabled, you can use the shortcut:
```bash
letta teleport local
```
## Transfer files to or from Cloud
Run upload where the local file exists; run download where the local copy should be saved.
```bash
# Use the executing conversation's Cloud sandbox
letta sandbox upload <local-path>
letta sandbox download <sandbox-path> --to <local-path>
# Explicit Cloud conversation (sandboxes are per-conversation)
letta sandbox upload <local-path> --conversation <destination-conversation-id>
letta sandbox download <sandbox-path> \
--conversation <source-conversation-id> --to <local-path>
# An agent's main/default conversation
letta sandbox upload <local-path> --agent <agent-id>
letta sandbox download <sandbox-path> --agent <agent-id> --to <local-path>
```
- `--agent` alone selects that agent's main/default conversation. Concrete `--conversation` IDs resolve their owning agent.
- Target flags override the executing session without changing its identity. Do not replace the subagent's identity environment variables with the parent's.
- The executing computer's credentials must authorize access to the target.
- Commands return JSON. Use the exact upload path returned; never reconstruct it from the filename.
- Download sources must be under `/root/downloads`; `--to` selects the destination path on the receiving computer. Without `--to`, download saves under the source file's basename.
- Transfer files directly, not as base64 or file contents through model messages. Return the path and destination IDs; verify received contents or checksums.
- These commands transfer files to/from Cloud sandboxes, not arbitrary remote filesystems. No sandbox ID or separate wake command is needed.
## Share a live view of a Cloud sandbox desktop
When someone outside chat (Slack, email, a teammate) needs to watch or drive the sandbox desktop, mint a viewer link:
```bash
letta sandbox desktop-link # this conversation's sandbox
letta sandbox desktop-link --conversation <conv-id> # another Cloud conversation
```
It prints `{ url, expiresAt }`. The URL opens the desktop in a browser tab with no sign-in. Anyone holding it can view and control the desktop until `expiresAt` (about one hour), so hand it to the person who asked, in a private message or thread, and say when it expires. Mint a new one if it lapses. The sandbox must be a ready Linux VM with desktop support; the command reports the server's error otherwise.
From letta-ai/letta-code at c1033d9, shown as plain text under its license: Apache-2.0 (permissive). The license text is in LICENSE.
View SKILL.md on GitHub at c1033d9Files
- SKILL.md5.6 KB · 52885fc01980
- assets/
- allow-remote-access-from-desktop.png90 KB · 426717e00821
- references/
- connect-a-computer-for-remote-access.md4.0 KB · 69f497b3cc0c
3 files, 99 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.
Skill folder on GitHub at c1033d9More from Letta
acquiring-skills
Enables the agent to discover and install skills from multiple registries including Hermes Skills Hub, ClawHub, GitHub, and community repositories.
Agents not labelled yet · about 3.1K tokens · pinned 7 days ago
browser-use
Control a real browser using Chrome DevTools Protocol over WebSocket to navigate pages, interact with UI, fill forms, scrape sites, and capture screenshots or…
Claude Code, Codex, Cursor +4 · about 3.2K tokens · pinned 7 days ago
Context Doctor
Context Doctor investigates and repairs an agent's context including memory, system prompt, and skills by analyzing observed behavior as evidence.
Claude Code, Codex, Cursor +3 · about 1K tokens · pinned 7 days ago
creating-mods
This skill creates and edits mod files that extend local Letta instances with tools, slash commands, event handlers, custom model providers, permissions, and…
Claude Code, Codex, Cursor +4 · about 2.4K tokens · pinned 7 days ago
creating-skills
This skill guides developers in creating modular packages that extend Letta Code agent capabilities with specialized knowledge, workflows, tool integrations…
Contains scripts
Claude Code, Codex, Cursor +3 · about 4.5K tokens · pinned 7 days ago
curating-memory-palace
This skill lets the agent maintain a Memory Palace, a structured dashboard view that shows the user what the agent is working on, what it could do next, and…
Agents not labelled yet · about 3.1K tokens · pinned 7 days ago
Related in Cloud and DevOps
n8n-cli
This skill enables agents to manage n8n workflows, credentials, executions, and instance resources via the n8n CLI command-line tool.
by n8nOfficial publisher
Claude Code, Codex, Cursor +4 · about 2.9K tokens · pinned 7 days ago
managing-streamlit-apps
Manage Streamlit apps running in PostHog sandboxes through the full lifecycle: create, set or edit source code, start and stop the sandbox, poll status, and…
by PostHogOfficial publisher
Claude Code, Codex, Cursor +4 · about 1.4K tokens · pinned 7 days ago
release-candidate-prep
Prepares a local Python SDK release candidate in a dedicated Git worktree when explicitly invoked with a version number.
by OpenAIOfficial publisher
Contains scripts
Claude Code, Codex, Cursor +3 · about 4.8K tokens · pinned 7 days ago
cloud-run-basics
Deploys and manages Google Cloud Run services, jobs, and worker pools for running containerized applications or source code.
by GoogleOfficial publisher
Claude Code, Codex, Cursor +4 · about 3.9K tokens · pinned 7 days ago
debug-openshell-cluster
Diagnoses OpenShell gateway deployment problems across Docker, Podman, Kubernetes, and VM compute platforms.
by NVIDIAOfficial publisher
Claude Code, Codex, Cursor +4 · about 19.1K tokens · pinned 7 days ago
hf-cloud-aws-context-discovery
This skill reads the user's local AWS configuration to discover their active profile, region, account ID, and caller identity before any AWS work begins.
by Hugging FaceOfficial publisher
Claude Code, Codex, Cursor +4 · about 830 tokens · pinned 7 days ago
Open roles at Letta
4 open roles on the jobs board
- Research Engineer / Scientist, Post-Training
San Francisco, California, United States (On-site)
- Research Engineer / Scientist, Self-Improvement
San Francisco, California, United States (On-site)
- Software Engineer, Agent Harness
San Francisco, California, United States (On-site)
- Research Engineer / Scientist, Memory
San Francisco, California, United States (On-site)