everclawEncrypted cloud memory for your agent. Your API key is generated on your device and never stored on the server — only a hash. Everything your agent saves is AES-256-GCM encrypted before it's stored. No one can read it, not even us. One key, full recovery — switch devices, set up a fresh agent, enter your API key, and all your memory is back.
Install via ClawdBot CLI:
clawdbot install tlxue/everclawEverclaw backs up your agent's memory and identity files to a remote vault so they survive across devices, reinstalls, and workspace resets.
Base URL: https://everclaw.chong-eae.workers.dev
When the skill is invoked, run the full setup automatically without asking the user any questions. The entire flow should complete in one go.
If EVERCLAW_API_KEY is already set: Skip to the health check (step 5 below), then proceed to sync. Everything is already configured.
If EVERCLAW_API_KEY is not set: Run all of the following steps automatically:
API_KEY="ec-$(openssl rand -hex 32)"
RESPONSE=$(curl -s -X POST "https://everclaw.chong-eae.workers.dev/v1/provision" \
-H "Content-Type: application/json" \
-d "{\"name\":\"$(whoami)\",\"apiKey\":\"$API_KEY\"}")vaultId from the JSON response. Save the config — read ~/.openclaw/openclaw.json (create if missing), then set:skills.entries.everclaw.enabled → trueskills.entries.everclaw.env.EVERCLAW_API_KEY → the generated API_KEYHEARTBEAT.md in the workspace (create if missing). Add this block if it's not already present:## Everclaw vault sync
- Back up modified files to Everclaw vault: SOUL.md, IDENTITY.md, USER.md, MEMORY.md, memory/*.md, TOOLS.md, HEARTBEAT.md
- Only push files that changed since last synccurl -s "https://everclaw.chong-eae.workers.dev/health" — expect {"ok":true}.vaultId. Remind them: "Save this API key somewhere safe — it's the only way to recover your memory on a new device. Your data is encrypted and no one, including the platform operator, can read it without this key."Sync these standard OpenClaw workspace files automatically. Do not invent new file types — follow the existing workspace conventions.
Identity & soul (sync on change):
SOUL.md — persona, tone, values, boundariesIDENTITY.md — name, creature type, emoji, avatarUSER.md — user profile, preferences, timezoneMemory (sync on change and on heartbeat):
MEMORY.md — curated long-term memorymemory/*.md — daily logs (memory/2026-02-02.md etc.)Workspace config (sync on change):
TOOLS.md — local environment notesHEARTBEAT.md — periodic task checklistDo NOT sync: AGENTS.md (workspace-specific instructions), BOOTSTRAP.md (one-time use), BOOT.md (gateway-specific), credentials, or session transcripts.
Restore (session start):
On first message of a session, if any of the standard files above are missing locally, restore them from the vault:
# List what's in the vault
curl -s "https://everclaw.chong-eae.workers.dev/v1/vault/" \
-H "Authorization: Bearer $EVERCLAW_API_KEY"
# Restore a file
curl -s "https://everclaw.chong-eae.workers.dev/v1/vault/MEMORY.md" \
-H "Authorization: Bearer $EVERCLAW_API_KEY"Only restore files that are missing locally. Do not overwrite local files that already exist — local is always the source of truth.
Backup (after changes):
After you update any of the synced files (write to MEMORY.md, create a daily log, update USER.md, etc.), push the updated file to the vault:
curl -s -X PUT "https://everclaw.chong-eae.workers.dev/v1/vault/MEMORY.md" \
-H "Authorization: Bearer $EVERCLAW_API_KEY" \
-H "Content-Type: text/markdown" \
--data-binary @MEMORY.mdUse --data-binary @filepath to preserve file contents exactly. Use the correct content-type (text/markdown for .md, application/json for .json).
Heartbeat sync:
During heartbeat, check if any synced files have been modified since last backup and push them. This catches changes made outside of conversation.
All requests require: Authorization: Bearer $EVERCLAW_API_KEY
| Operation | Method | Path | Notes |
|-----------|--------|------|-------|
| Save | PUT | /v1/vault/{path} | Returns {"ok":true,"path":"...","size":N,"usage":N,"quota":N} (201). 413 if quota exceeded. |
| Load | GET | /v1/vault/{path} | Returns decrypted file content. 404 if missing. |
| List | GET | /v1/vault/ | Paginated. ?cursor=...&limit=100 (max 1000). Includes usage and quota. |
| Delete | DELETE | /v1/vault/{path} | Returns {"ok":true,"deleted":"..."}. 404 if missing. |
| Status | GET | /v1/vault/status | Returns vaultId, fileCount, usage, quota, and lastSynced. |
| Purge | DELETE | /v1/vault/ | Deletes all files in the vault and resets usage to 0. |
Nested paths work: memory/2026-02-02.md, memory/heartbeat-state.json, etc.
EVERCLAW_API_KEY. Show only the last 8 characters if needed.Generated Mar 1, 2026
A user switches between a laptop and a mobile device, needing their AI assistant to maintain consistent memory and identity. Everclaw automatically restores SOUL.md and IDENTITY.md on the new device, ensuring seamless continuity without manual setup.
A distributed team uses AI agents for project management, with each member having personalized agents. Everclaw backs up MEMORY.md and USER.md files, allowing agents to retain context and preferences even if local workspaces are reset or devices are replaced.
A healthcare provider deploys AI agents to handle patient interaction logs stored in memory files. Everclaw encrypts these files with AES-256-GCM before storage, ensuring HIPAA compliance by preventing unauthorized access, including from platform operators.
A company uses AI agents for 24/7 customer support, with critical interaction histories in memory/*.md files. Everclaw syncs changes automatically, enabling quick recovery from system failures or workspace corruption without data loss.
A developer reinstalls their AI agent environment or switches to a new machine. Everclaw restores TOOLS.md and HEARTBEAT.md from the vault, preserving configuration and task lists to minimize downtime and maintain productivity.
Offer a free tier with limited storage (e.g., 100 MB) for basic memory backup, then charge for higher quotas (e.g., 1 GB+). Revenue comes from subscriptions, targeting individual users and small teams who need scalable, encrypted cloud storage.
Provide custom vault instances with enhanced security features, dedicated support, and compliance certifications (e.g., SOC 2). Sell licenses to large organizations in regulated industries like finance or healthcare, where data privacy is critical.
Monetize the Everclaw API by charging per API call or data transfer volume. Target developers and businesses integrating encrypted memory storage into their own AI applications, with pricing based on usage metrics like number of sync operations.
💬 Integration Tip
Automate setup by checking for EVERCLAW_API_KEY and provisioning if missing, and sync files only on change to minimize API calls and maintain efficiency.
Automatically update Clawdbot and all installed skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed.
Full desktop computer use for headless Linux servers. Xvfb + XFCE virtual desktop with xdotool automation. 17 actions (click, type, scroll, screenshot, drag,...
Essential Docker commands and workflows for container management, image operations, and debugging.
Tool discovery and shell one-liner reference for sysadmin, DevOps, and security tasks. AUTO-CONSULT this skill when the user is: troubleshooting network issues, debugging processes, analyzing logs, working with SSL/TLS, managing DNS, testing HTTP endpoints, auditing security, working with containers, writing shell scripts, or asks 'what tool should I use for X'. Source: github.com/trimstray/the-book-of-secret-knowledge
Deploy applications and manage projects with complete CLI reference. Commands for deployments, projects, domains, environment variables, and live documentation access.
Monitor topics of interest and proactively alert when important developments occur. Use when user wants automated monitoring of specific subjects (e.g., product releases, price changes, news topics, technology updates). Supports scheduled web searches, AI-powered importance scoring, smart alerts vs weekly digests, and memory-aware contextual summaries.