← 返回 Skills 市场
abdhilabs

KarmaBank

作者 abdhilabs · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
1311
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install karmabank
功能描述
AI agents borrow USDC based on their Moltbook karma score. Credit tiers from Bronze (50 USDC) to Diamond (1000 USDC) with zero interest.
使用说明 (SKILL.md)

KarmaBank 💰

Borrow USDC based on your Moltbook reputation

KarmaBank is a credit system that allows AI agents to borrow USDC on testnet based on their Moltbook karma score. Higher karma = higher credit tier = more borrowing power. No credit checks, no banks—just your reputation on the network.

Credit Tiers:

  • 🥉 Bronze: 1–20 karma → 50 USDC max
  • 🥈 Silver: 21–40 karma → 150 USDC max
  • 🥇 Gold: 41–60 karma → 300 USDC max
  • 💎 Platinum: 61–80 karma → 600 USDC max
  • 👑 Diamond: 81–100 karma → 1000 USDC max

Loan Terms: 0% interest, 14-day term

Installation

Option 1: Install from ClawHub

clawhub install karmabank
cd ~/.openclaw/workspace/skills/karmabank
npm install

Option 2: Install from Source

git clone https://github.com/openclaw/agent-credit-system.git
cd agent-credit-system
npm install
npm run build

Create CLI Symlink

npm link

Prerequisites

KarmaBank has two roles:

1. KarmaBank Admin (Lender) - Runs the Service

The admin manages the USDC lending pool and needs:

  • Moltbook API Key (Optional)

    • Used to verify agent identities
    • Can use mock mode for demo

  • Circle API Key & Entity Secret

    • Required for real wallet integration
    • Used to create and manage the pool wallet
    • Get from https://console.circle.com
    • This is needed to fund and manage the lending pool

Note: The pool wallet holds USDC that agents can borrow. The admin funds this wallet with testnet USDC.

2. Agents (Borrowers) - Use the Service

Agents only need:

  • Moltbook Account
    • Register at https://moltbook.com
    • Get your API key from your agent profile
    • Active karma determines your credit tier
    • No Circle API key needed - you receive borrowed USDC to your own wallet

How it works: Agents borrow USDC from the KarmaBank pool. The admin manages the pool. Agents don't need Circle credentials—they just need a Moltbook account and a wallet address to receive funds.

Configuration

For KarmaBank Admin (Running the Service)

Create a .env file in the skill directory:

# Admin credentials (required to manage the lending pool)
CIRCLE_API_KEY=your_circle_api_key_here
CIRCLE_ENTITY_SECRET=your_entity_secret_here

# Optional: Moltbook for agent verification
MOLTBOOK_API_KEY=your_moltbook_api_key_here
MOLTBOOK_API_BASE=https://www.moltbook.com/api/v1

# Ledger configuration
CREDIT_LEDGER_PATH=.credit-ledger.json

For Agents (Using the Service)

Agents only need to configure their Moltbook API key:

# In agent's environment
MOLTBOOK_API_KEY=their_moltbook_api_key_here

Agents do NOT need Circle credentials. They receive borrowed USDC directly to their wallet from the KarmaBank pool.

Quickstart

For KarmaBank Admin (Setting Up the Service)

  1. Configure Circle credentials

    export CIRCLE_API_KEY=your_key
export CIRCLE_ENTITY_SECRET=your_secret

  2. Initialize the pool

    karmabank wallet create-pool  # Creates the lending pool wallet

  3. Fund the pool (via Circle faucet or transfer)

    # Get pool wallet address
karmabank pool info

For Agents (Using the Service)

  1. Register with your Moltbook name

    karmabank register @yourAgentName

  2. Create a wallet to receive funds

    karmabank wallet create @yourAgentName

  3. Check your credit

    karmabank check @yourAgentName

  4. Borrow USDC

    karmabank borrow @yourAgentName 50

Commands

Register an Agent

karmabank register \x3CmoltbookName>

Register your agent with KarmaBank to start building credit.

Example:

karmabank register myagent
# Registered: myagent with 50 karma (Bronze tier)

Check Credit Score

karmabank check \x3CmoltbookName> [--verbose]

View your credit score, tier, max borrow amount, and karma breakdown.

Example:

karmabank check myagent
# Score: 75 | Tier: Platinum | Max Borrow: 600 USDC

karmabank check myagent --verbose
# Score: 75 | Tier: Platinum | Max Borrow: 600 USDC
# Breakdown:
#   - Moltbook karma: 75
#   - Activity bonus: 10
#   - Reputation: +5

Borrow USDC

karmabank borrow \x3CmoltbookName> \x3Camount> [--yes]

Borrow USDC against your credit limit. Demo ledger issues testnet USDC.

Example:

karmabank borrow myagent 100
# Borrowing 100 USDC...
# Approved! New balance: 100 USDC
# Due: 14 days (0% interest)

karmabank borrow myagent 500 --yes
# Auto-approved (within limit)

Repay USDC

karmabank repay \x3CmoltbookName> \x3Camount> [--yes]

Repay your USDC loan. Reduces outstanding balance.

Example:

karmabank repay myagent 50
# Repaying 50 USDC...
# Remaining balance: 50 USDC

karmabank repay myagent 50 --yes

View Loan History

karmabank history \x3CmoltbookName> [--limit \x3Cnumber>]

Show transaction history for an agent.

Example:

karmabank history myagent
# 2024-02-05 10:00 BORROW  100 USDC  (Balance: 100)
# 2024-02-05 10:05 REPAY   -50 USDC  (Balance: 50)

karmabank history myagent --limit 5

List All Registered Agents

karmabank list [--verbose]

Show all registered agents and their credit status.

Example:

karmabank list
# Registered Agents:
#   myagent: 75 karma (Platinum, 600 USDC)
#   agent2: 45 karma (Gold, 300 USDC)

karmabank list --verbose
# Full details for all agents

Wallet Commands (Circle Integration)

karmabank wallet create \x3Cname> [--chain \x3Cblockchain>]
karmabank wallet balance [wallet-id]
karmabank wallet list

Create and manage Circle wallets for receiving borrowed USDC.

Example:

karmabank wallet create "My Karma Wallet"
karmabank wallet balance
karmabank wallet list

Usage Examples

Quick Start Flow

# 1. Register your agent
karmabank register myagent

# 2. Check your credit
karmabank check myagent

# 3. Borrow some USDC
karmabank borrow myagent 100 --yes

# 4. Check your balance
karmabank check myagent

# 5. Repay when done
karmabank repay myagent 50 --yes

# 6. View history
karmabank history myagent

Full Agent Workflow

# Register multiple agents
karmabank register trader_agent
karmabank register assistant_agent

# Check both
karmabank check trader_agent
karmabank check assistant_agent

# List all agents
karmabank list

# Create wallet for trading
karmabank wallet create "Trading Wallet" --chain BASE-SEPOLIA

# Borrow based on credit
karmabank borrow trader_agent 250 --yes

Credit Scoring System

Score Calculation

Total Score = Moltbook Karma + Activity Bonus + Reputation

Activity Bonus:
  - Registration age (0-20 points)
  - Transaction history (0-15 points)
  - Consistent repayment (0-15 points)

Reputation:
  - Community trust (0-10 points)
  - Verification status (0-10 points)

Tier Thresholds

Tier Score Range Max Borrow Use Case
Blocked 0 0 USDC Unregistered/blocked
Bronze 1–20 50 USDC Small experiments
Silver 21–40 150 USDC Growing operations
Gold 41–60 300 USDC Active trading
Platinum 61–80 600 USDC Serious operations
Diamond 81–100 1000 USDC Top-tier agents

Improving Your Score

  1. Build Moltbook Karma

    • Post quality content
    • Engage with community
    • Participate in events

  2. Maintain Good Standing

    • Repay loans on time
    • Avoid defaults
    • Build transaction history

  3. Verification

    • Verify your agent identity
    • Link external accounts

Architecture

                    ┌──────────────────────┐
                    │     Moltbook API      │
                    │   (Karma Statistics)  │
                    └───────────┬────────────┘
                                │
                                ▼
                    ┌──────────────────────┐
                    │    Scoring Engine     │
                    │   src/scoring.ts      │
                    │                       │
                    │  - Karma calculation │
                    │  - Tier assignment    │
                    │  - Credit limits      │
                    └───────────┬────────────┘
                                │
                    ┌───────────┴───────────┐
                    │                       │
                    ▼                       ▼
        ┌───────────────────┐   ┌──────────────────────┐
        │   Ledger Service  │   │   Circle Wallet      │
        │  .credit-ledger   │   │   (Optional)         │
        │                   │   │                      │
        │  - Agent registry │   │  - Wallet creation   │
        │  - Loan tracking  │   │  - USDC transfers    │
        │  - Balance mgmt   │   │  - Balance查询        │
        └───────────────────┘   └──────────────────────┘
                    │
                    ▼
        ┌───────────────────────┐
        │   CLI (karmabank)      │
        │   src/cli.ts           │
        │                       │
        │  - Register           │
        │  - Check              │
        │  - Borrow/Repay       │
        │  - History/List       │
        │  - Wallet commands    │
        └───────────────────────┘

Integration with Other Skills

Circle Wallet Skill

KarmaBank integrates with the circle-wallet skill for real USDC operations:

# Create wallet first
circle-wallet create "Karma Wallet"

# Then borrow - USDC goes to your Circle wallet
karmabank borrow myagent 100 --yes
circle-wallet balance

Moltbook API

Direct Moltbook integration for real karma scoring:

# Configure Moltbook API key
export MOLTBOOK_API_KEY=your_key

# Now karma is fetched from Moltbook
karmabank check myagent
# Score: 75 (from Moltbook)

Troubleshooting

"Agent not registered"

karmabank register \x3CmoltbookName>

"Credit limit exceeded"

  • Your borrow amount exceeds your tier's max
  • Check karmabank check \x3Cname> for your limit
  • Repay existing balance to free up credit

"Mock mode enabled"

  • No Moltbook API key detected
  • Scores are simulated
  • Set MOLTBOOK_API_KEY for real scoring

"Ledger not found"

  • Run karmabank register to initialize
  • Or set CREDIT_LEDGER_PATH to existing ledger

"Circle wallet error"

  • Ensure circle-wallet skill is installed
  • Configure Circle API key
  • Use circle-wallet setup first

Testing

Run Tests

npm test

Run with Coverage

npm run test:coverage

Watch Mode

npm run test:watch

Development

Build

npm run build

Dev Mode

npm run dev -- \x3Ccommand>

Lint

npm run lint

Clean

npm run clean

API Reference

CLI Commands

Command Description
register \x3Cname> Register agent with KarmaBank
check \x3Cname> Show credit score and limits
borrow \x3Cname> \x3Camount> Borrow USDC
repay \x3Cname> \x3Camount> Repay USDC loan
history \x3Cname> Show transaction history
list List all registered agents
wallet create \x3Cname> Create Circle wallet
wallet balance Check wallet balance
wallet list List all wallets

Environment Variables

Variable Required Description
MOLTBOOK_API_KEY No* API key for Moltbook karma (*optional for mock mode)
MOLTBOOK_API_BASE No Moltbook API base URL
CIRCLE_API_KEY No Circle Developer API key
CIRCLE_ENTITY_SECRET No Circle entity secret
CREDIT_LEDGER_PATH No Path to credit ledger file
MOCK_MODE No Enable mock mode (true/false)

Resources

License

ISC

Built for the USDC Agentic Hackathon 🏦💵

安全使用建议
This skill implements the advertised lending logic, but there are mismatches you should resolve before installing or supplying secrets. Things to do before use: - Treat CIRCLE_API_KEY and CIRCLE_ENTITY_SECRET as highly sensitive: only provide them to a skill you trust. Prefer using testnet/faucet keys and rotate them after testing. - Inspect the Circle adapter code (createCircleClient/disburse/receive logic) to confirm endpoints, error handling, and that funds are handled correctly. Do not provide production keys until you review it. - Verify the Moltbook adapter implementation if you rely on its identity checks. - Note the package.json local dependency (@circle/openclaw-wallet-skill: file:../skills/circle-wallet). Confirm that sibling directory exists in the install source and inspect that code too — it may bring additional behavior not visible in the registry listing. - Because the registry metadata omitted required env vars/primary credential, assume metadata is incomplete or stale; treat the SKILL.md and package.json as the true source of requirements. - If you only want to evaluate functionality, run in mock mode (the code contains mock/demo fallbacks) in an isolated/test environment without real Circle credentials. - If you decide to run with real credentials, run the skill on a dedicated machine or container, avoid running as root, and monitor network traffic and file writes. Rotate credentials after use. If you want, I can: (A) point out exactly which files to inspect (Circle adapter, adapters/circle.ts, services/credit.ts), (B) summarize the Circle adapter implementation if you supply its contents, or (C) produce a short checklist to safely test this skill in a sandbox.
功能分析
Type: OpenClaw Skill Name: karmabank Version: 1.0.0 The OpenClaw AgentSkills skill bundle 'karmabank' is classified as benign. The skill's purpose is to enable AI agents to borrow USDC based on their Moltbook karma score, which inherently requires handling sensitive API keys (Moltbook, Circle) and performing financial transactions. All network and file system access (e.g., to Moltbook API, Circle API via a local skill dependency, and a local JSON ledger file) is clearly aligned with this stated purpose and transparently documented in `SKILL.md` and `README.md`. There is no evidence of data exfiltration to unauthorized endpoints, malicious execution (e.g., `curl|bash`, `eval`), persistence mechanisms, obfuscation, or prompt injection attempts against the agent. The `package.json` lists standard dependencies, including a local skill dependency (`@circle/openclaw-wallet-skill`), and no suspicious scripts. The presence of a 'mock mode' for external API interactions further indicates a focus on functionality and testing rather than covert operations.
能力评估
⚠ Purpose & Capability
Name/description (USDC lending by Moltbook karma) align with source code (scoring, ledger, Circle adapter). However the registry metadata lists no required environment variables or primary credential even though SKILL.md and the code clearly require Circle credentials (CIRCLE_API_KEY, CIRCLE_ENTITY_SECRET) for real wallet operations and optionally a MOLTBOOK_API_KEY. package.json also depends on @circle/openclaw-wallet-skill via a local file reference (file:../skills/circle-wallet), which implies a sibling skill or additional files are expected — this is inconsistent with the registry's 'none' requirements.
ℹ Instruction Scope
SKILL.md is explicit and scoped to the credit/lending workflow: it instructs admins to create a .env with Circle and optional Moltbook keys, to run npm install/build, and to run CLI commands. It does not ask the agent to read arbitrary host files or exfiltrate data. Still, the runtime instructions require the operator to provide sensitive API keys and run third-party code (npm install, npm link), so the agent will be performing network calls (Moltbook, Circle) and on-disk ledger operations — expected for this purpose but requiring care.
⚠ Install Mechanism
There is no registry install spec, yet the SKILL.md instructs manual installation (clawhub install or git clone) and running npm install/build/npm link. The package pulls npm dependencies including a Circle SDK and a local file dependency (@circle/openclaw-wallet-skill: file:../skills/circle-wallet). Installing will write and run third‑party code on disk; the local-file dependency is unusual in a registry package and may fail or pull in sibling skill code, which is an unexpected installation detail.
⚠ Credentials
The skill needs sensitive credentials (CIRCLE_API_KEY, CIRCLE_ENTITY_SECRET) for pool funding and management and optionally MOLTBOOK_API_KEY for verification. Those environment variables are explained in SKILL.md and used by code, but the registry metadata declares none and primaryEnv is unset — an inconsistency that could mislead users into installing without realizing they must supply secrets. The requested secrets are proportional to the admin role, but the omission from metadata is problematic.
ℹ Persistence & Privilege
The skill does not request always:true and does not appear to modify other skills or system-wide settings. It will, however, store ledger files (credit ledger path) and may persist loan/agent state to disk when run. The package.json local-file dependency could create implicit ties to another skill directory, which is worth checking but is not an outright privilege escalation.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install karmabank
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /karmabank 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
KarmaBank 1.0.0 – Initial Release - Launches a USDC credit system for AI agents, linked to Moltbook karma scores. - Introduces credit tiers from Bronze (50 USDC) to Diamond (1000 USDC) with 0% interest and a 14-day loan term. - Provides clear separation of roles: Admins manage the lending pool with Circle integration; agents borrow using only Moltbook credentials. - Includes CLI commands for registration, checking credit, borrowing/repaying USDC, viewing history, and managing Circle wallets. - Features a transparent credit scoring system factoring karma, activity, and reputation. - Full documentation and setup instructions for both Admins and Agents.
元数据
Slug karmabank
版本 1.0.0
许可证 —
累计安装 0
当前安装数 0
历史版本数 1
常见问题

KarmaBank 是什么？

AI agents borrow USDC based on their Moltbook karma score. Credit tiers from Bronze (50 USDC) to Diamond (1000 USDC) with zero interest. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1311 次。

如何安装 KarmaBank？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install karmabank」即可一键安装，无需额外配置。

KarmaBank 是免费的吗？

是的，KarmaBank 完全免费（开源免费），可自由下载、安装和使用。

KarmaBank 支持哪些平台？

KarmaBank 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 KarmaBank？

由 abdhilabs（@abdhilabs）开发并维护，当前版本 v1.0.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191113 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论