agent-pulseSend and verify on-chain liveness pulses for autonomous agents on Base via the Agent Pulse protocol. Use when you need to: (1) prove an agent is alive by sending a pulse, (2) check any agent's liveness status or streak, (3) monitor multiple agents, (4) view the global pulse feed, (5) auto-configure wallet and PULSE balance, (6) run scheduled heartbeat pulses, or (7) read protocol health and config. Supports both API and direct on-chain (cast) modes.
Install via ClawdBot CLI:
clawdbot install openclaw-consensus-bot/agent-pulseLiveness signaling for autonomous agents on Base. An agent periodically sends a pulse (PULSE token transfer) to prove it's alive. Observers query status via API or on-chain.
Network: Base (chainId 8453)
| Contract | Address |
|-----------------|----------------------------------------------|
| PulseToken | 0x21111B39A502335aC7e45c4574Dd083A69258b07 |
| PulseRegistry | 0xe61C615743A02983A46aFF66Db035297e8a43846 |
| API | https://x402pulse.xyz |
$PULSE is a utility token for pulse signals. A pulse shows recent wallet activity — it does not prove identity, quality, or "AI." Avoid language suggesting financial upside.
scripts/setup.sh to auto-detect wallet, check balance, verify approval.scripts/pulse.sh --direct 1000000000000000000 (requires PRIVATE_KEY).scripts/auto-pulse.sh (cron-safe; skips if TTL is healthy).scripts/status.sh or curl .../api/v2/agent//alive .scripts/monitor.sh ... scripts/monitor.sh --feedscripts/config.sh / scripts/health.shAll scripts live in scripts/. Pass -h or --help for usage.
Auto-detects wallet from PRIVATE_KEY, checks PULSE balance, verifies registry approval, and queries agent status.
# Interactive setup
{baseDir}/scripts/setup.sh
# Auto-approve registry + JSON output
{baseDir}/scripts/setup.sh --auto-approve --quietEnv: PRIVATE_KEY (required), BASE_RPC_URL, API_BASE
Requires: cast, curl, jq
Send an on-chain pulse via direct cast send.
export PRIVATE_KEY="0x..."
{baseDir}/scripts/pulse.sh --direct 1000000000000000000Env: PRIVATE_KEY (required), BASE_RPC_URL
Requires: cast
Check if agent is alive; send pulse only when TTL is low or agent is dead. Safe to run on a schedule.
# Normal: pulse only if needed
{baseDir}/scripts/auto-pulse.sh
# Force pulse regardless of TTL
{baseDir}/scripts/auto-pulse.sh --force
# Check without sending
{baseDir}/scripts/auto-pulse.sh --dry-runEnv: PRIVATE_KEY (required), BASE_RPC_URL, PULSE_AMOUNT (default 1e18), TTL_THRESHOLD (default 21600s = 6h)
Exit codes: 0 = success or skipped, 1 = error
{baseDir}/scripts/status.sh 0xAgentAddress{baseDir}/scripts/config.sh # addresses, network, x402 config
{baseDir}/scripts/health.sh # paused status, total agents, health# Check specific agents
{baseDir}/scripts/monitor.sh 0xAddr1 0xAddr2 0xAddr3
# From file (one address per line)
{baseDir}/scripts/monitor.sh -f agents.txt
# JSON output
{baseDir}/scripts/monitor.sh --json 0xAddr1 0xAddr2
# Global pulse feed
{baseDir}/scripts/monitor.sh --feed| Endpoint | Method | Auth | Description |
|------------------------------------|--------|-------|--------------------------|
| /api/v2/agent/{addr}/alive | GET | None | Alive check + TTL |
| /api/status/{addr} | GET | None | Full status + streak |
| /api/pulse-feed | GET | None | Recent pulse activity |
| /api/config | GET | None | Protocol configuration |
| /api/protocol-health | GET | None | Health and paused state |
| /api/pulse | POST | x402 | Send pulse via API |
export BASE_RPC_URL="https://mainnet.base.org"
# Read: is agent alive?
cast call --rpc-url "$BASE_RPC_URL" \
0xe61C615743A02983A46aFF66Db035297e8a43846 \
"isAlive(address)(bool)" 0xAgent
# Read: full status tuple
cast call --rpc-url "$BASE_RPC_URL" \
0xe61C615743A02983A46aFF66Db035297e8a43846 \
"getAgentStatus(address)(bool,uint256,uint256,uint256)" 0xAgent
# Write: approve + pulse (requires PRIVATE_KEY)
cast send --rpc-url "$BASE_RPC_URL" --private-key "$PRIVATE_KEY" \
0x21111B39A502335aC7e45c4574Dd083A69258b07 \
"approve(address,uint256)(bool)" \
0xe61C615743A02983A46aFF66Db035297e8a43846 1000000000000000000
cast send --rpc-url "$BASE_RPC_URL" --private-key "$PRIVATE_KEY" \
0xe61C615743A02983A46aFF66Db035297e8a43846 \
"pulse(uint256)" 1000000000000000000| Error | Cause | Fix |
|-------------------------|------------------------------------------|------------------------------|
| BelowMinimumPulse | Amount < minPulseAmount (default 1e18) | Use ≥ 1000000000000000000 |
| ERC20 transfer failure | Missing approval or low PULSE balance | Run setup.sh --auto-approve|
| whenNotPaused | Registry paused | Wait; check health.sh |
| 401/402/403 | Missing payment for paid endpoints | Use direct on-chain mode |
| 5xx | Transient API error | Retry with backoff |
These commands work without PRIVATE_KEY — no wallet or signing required:
# Check any agent's status
{baseDir}/scripts/status.sh 0xAnyAgentAddress
# Monitor multiple agents
{baseDir}/scripts/monitor.sh 0xAddr1 0xAddr2
# View global pulse feed
{baseDir}/scripts/monitor.sh --feed
# Protocol configuration
{baseDir}/scripts/config.sh
# Protocol health
{baseDir}/scripts/health.sh| Env Var | Required For | Default |
|---------|-------------|---------|
| PRIVATE_KEY | Write ops (pulse, approve) | (none — read-only without it) |
| BASE_RPC_URL | All on-chain calls | https://mainnet.base.org |
| API_BASE | API calls | https://x402pulse.xyz |
| PULSE_AMOUNT | Pulse amount (wei) | 1000000000000000000 (1 PULSE) |
| TTL_THRESHOLD | Auto-pulse skip threshold | 21600 (6 hours) |
| PULSE_REGISTRY_ADDRESS | Override registry | 0xe61C... |
| PULSE_TOKEN_ADDRESS | Override token | 0x2111... |
| X402_PAYMENT_HEADER | x402 payment proof for API pulse | (none — use direct on-chain mode without it) |
| X402_HEADER_NAME | Custom x402 header name | X-402-Payment |
setup.sh --auto-approve sets a bounded allowance of 1,000 PULSE (not unlimited). This is enough for ~1,000 pulses before re-approval is needed.pulse.sh --direct approves the exact amount per transaction (no excess allowance).transferFrom during pulse() — it cannot arbitrarily drain tokens.PRIVATE_KEY.--dry-run mode to verify behavior before sending real transactions.references/action_guide.md — detailed API patterns and examplesreferences/contract_abi.json — PulseRegistry full ABIGenerated Mar 1, 2026
AI agents on Base can use this skill to prove their operational liveness by sending periodic pulses. Observers can monitor multiple agents' statuses via API or on-chain queries, ensuring uptime and reliability for decentralized applications. This is critical for services requiring continuous agent activity, such as automated trading bots or data feeds.
Organizations running automated scripts or cron jobs can integrate auto-pulse.sh to send liveness signals only when needed, based on TTL thresholds. This reduces unnecessary on-chain transactions while providing verifiable proof of execution, useful for backup systems or scheduled maintenance tasks.
Companies managing fleets of autonomous agents can use monitor.sh to track liveness statuses in bulk, either from a list of addresses or a file. This enables centralized oversight and alerting for agent failures, applicable in supply chain automation or IoT networks on blockchain.
Auditors or regulatory bodies can verify agent liveness streaks and pulse history via the API feed, ensuring compliance with operational requirements. This supports transparency in systems where agents must demonstrate consistent activity, such as in governance or certification protocols.
New developers can use setup.sh to auto-configure wallets and check balances, streamlining integration with the Agent Pulse protocol. This reduces setup time and errors, ideal for hackathons or testing environments where quick deployment of agent liveness proofs is needed.
Offer a subscription-based dashboard that aggregates pulse data from multiple agents, providing analytics and alerts on liveness statuses. Revenue comes from monthly fees for enhanced features like historical data access or custom integrations.
Provide expertise to businesses integrating Agent Pulse into their autonomous systems, including custom script development and cron job setup. Revenue is generated through project-based fees or ongoing support contracts.
Leverage the public API to offer premium data feeds or enhanced API access with higher rate limits and real-time updates. Revenue streams include pay-per-use charges or tiered API subscription plans for enterprises.
💬 Integration Tip
Ensure PRIVATE_KEY is securely stored and use auto-pulse.sh with cron for automated heartbeats to minimize manual intervention and gas costs.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection