The definitive CLI for validating A2A (Agent-to-Agent) protocol agent cards. Validates cryptographic trust, schema compliance, and live endpoint functionality.
capiscio-node is an early-stage TypeScript project in the AI payments / x402 ecosystem, focused on a2a-protocol, agent-to-agent, ai-agents, cli. It currently has 4 GitHub stars and 1 forks, and sits alongside related tools like summoner-agents, openclaw-a2a-plugins, fastapi-a2a, capiscio-python, a2a-server, a2a-demos.
The official command-line interface for CapiscIO, the Agent-to-Agent (A2A) validation platform.
This package provides a convenient Node.js distribution for the CapiscIO CLI. It acts as a smart wrapper that automatically manages the underlying capiscio-core binary (written in Go), ensuring you always have the correct executable for your operating system and architecture.
Note: This is a wrapper. The core logic resides in capiscio-core.
npm install -g capiscio
Once installed, the capiscio command is available in your terminal. It passes all arguments directly to the core binary.
# Validate an agent card
capiscio validate ./agent-card.json
# Validate with JSON output
capiscio validate https://my-agent.example.com --json
# Issue a self-signed badge (development)
capiscio badge issue --self-sign --sub did:web:example.com:agents:my-agent
# Verify a badge (offline mode)
capiscio badge verify "eyJhbGciOiJFZERTQSJ9..." --offline
# Check version
capiscio --version
# Get help
capiscio --help
The Node.js wrapper includes specific commands to manage the binary:
| Command | Description |
|---|---|
capiscio --wrapper-version |
Display the version of this Node.js wrapper package. |
capiscio --wrapper-clean |
Remove the cached capiscio-core binary (forces re-download on next run). |
capiscio, the script detects your OS (Linux, macOS, Windows) and Architecture (AMD64, ARM64).capiscio-core binary is present:<package>/bin/capiscio (alongside node_modules)~/.capiscio/bin/capiscio (if package dir is read-only)%USERPROFILE%\.capiscio\bin| Variable | Description |
|---|---|
CAPISCIO_CORE_VERSION |
Override the default core binary version (e.g., v1.0.2) |
CAPISCIO_CORE_PATH |
Use a specific binary path instead of auto-downloading |
On first run, the wrapper downloads the capiscio-core binary and verifies its SHA-256 checksum
against the published checksums.txt from the GitHub release.
If verification fails or the checksums file is unavailable:
# Temporary bypass (not recommended for production)
export CAPISCIO_SKIP_CHECKSUM=true
"Permission denied" errors: Ensure your user has write access to the cache directory. You can reset the cache by running:
capiscio --wrapper-clean
"Binary not found" or download errors:
If you are behind a corporate firewall, ensure you can access github.com.
Checksum verification failures: If you see "Checksum verification failed", the binary integrity could not be confirmed. This can happen with pre-release versions or network issues. See the Binary Integrity Verification section above.
Apache-2.0
A collection of Summoner clients and agents featuring example implementations and reusable templates
OpenClaw plugins that add A2A compatibility and enable communication with other A2A-compatible agents.
A zero-friction FastAPI plugin that turns any existing app into a fully compliant Agent-to-Agent (A2A) node — expose your routes as discoverable skills and delegate tasks to remote agents with a single decorator.
🚀 Access and manage the CapiscIO CLI easily with this Python wrapper, ensuring optimal performance across your system and architecture.
Production-ready A2A Protocol Server with dual protocol support (HTTP REST + JSON-RPC 2.0). Built on SceneGraphManager v2.0.0 for JSON-driven AI workflow orchestration with LangGraph.
Demo agents showcasing CapiscIO Agent Guard and MCP Guard — trust badges, identity verification, and tool-level authorization for A2A and MCP protocols
The agent-native LLM router for autonomous agents. 55+ models (8 free), <1ms local routing, USDC payments on Base & Solana via x402.
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
Self-healing infrastructure for AI agent payments. 90.3% auto-recovery.
The AI agent with a wallet — spends USDC autonomously to get real work done. Apache-2.0, TypeScript.
Daydreams is a set of tools for building agents for commerce
Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments.