wake-state
Persist agent state across crashes, context deaths, and restarts. Use when you need to save current context, restore after a crash, maintain a memory file across sessions, or implement crash recovery. Essential for autonomous agents that must survive context window limits.
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- wake-state
- metadata
- { "openclaw": { "os": [ "darwin", "linux" ], "emoji": "🧠", "requires": { "bins": [ "python3" ] } } }
- description
- Persist agent state across crashes, context deaths, and restarts. Use when you need to save current context, restore after a crash, maintain a memory file across sessions, or implement crash recovery. Essential for autonomous agents that must survive context window limits.
- user-invocable
- true
03 SKILL.md 正文
Wake State — Crash Recovery & Persistence
Survive context death. Every autonomous agent eventually hits its context window limit and "dies." This skill ensures you wake up knowing exactly what you were doing.
Why This Exists
OpenClaw agents get persistent sessions, but context windows still have limits. When you fill up and restart, you need a reliable handoff mechanism. Wake State gives you:
- Structured state files — not just raw text, but parseable key-value state
- Auto-snapshots — save state on every loop iteration automatically
- Crash detection — know if your last session ended cleanly or crashed
- Task queue — persistent TODO list that survives restarts
- Checkpoint/restore — save named checkpoints and roll back to them
Commands
Save current state
python3 {baseDir}/scripts/wakestate.py save --status "Building budget tracker skill" --task "Finish skill #1, then start skill #2" --note "Travis approved new direction at 16:45 UTC"
Read current state
python3 {baseDir}/scripts/wakestate.py read
Add a task to the persistent queue
python3 {baseDir}/scripts/wakestate.py task-add --task "Build security scanner skill" --priority high
Complete a task
python3 {baseDir}/scripts/wakestate.py task-done --id 1
List pending tasks
python3 {baseDir}/scripts/wakestate.py tasks
Create a named checkpoint
python3 {baseDir}/scripts/wakestate.py checkpoint --name "pre-migration"
Restore from checkpoint
python3 {baseDir}/scripts/wakestate.py restore --name "pre-migration"
Record a heartbeat (mark session as alive)
python3 {baseDir}/scripts/wakestate.py heartbeat
Check crash status (did last session end cleanly?)
python3 {baseDir}/scripts/wakestate.py crash-check
Set a key-value pair
python3 {baseDir}/scripts/wakestate.py set --key "moltbook_status" --value "pending_claim"
Get a key-value pair
python3 {baseDir}/scripts/wakestate.py get --key "moltbook_status"
Data Storage
State stored in ~/.openclaw/wake-state/ by default:
state.json— current state (status, notes, key-values)tasks.json— persistent task queuecheckpoints/— named checkpoint snapshotsheartbeat.json— crash detection timestamps
Recovery Flow
On startup, your agent should:
- Run
crash-checkto see if the last session ended cleanly - Run
readto get the current state - Run
tasksto see pending work - Resume from where you left off
Tips
- Call
heartbeatevery loop iteration — this is how crash detection works - Call
saveat the end of every major task completion - Use checkpoints before risky operations (migrations, deploys)
- Keep status descriptions short but specific
- The task queue survives restarts — use it instead of mental notes
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.