chap
View on GitHubCHAP, the Collaborative Human Agent Protocol, is a MCP/A2A-compatible runtime for auditable human-agent work: approvals, overrides, handoffs, escalation and verifiable evidence logs.
CHAP is an open protocol and runtime for auditable human-agent work: approvals, overrides, handoffs and escalations captured as hash-linked envelopes. It ships MCP and A2A servers plus Python/TypeScript reference coordinators with SQLite persistence and conformance vectors.
Use Cases
PR review approval and override of agent outputTicket triage with human escalationContract/settlement review sign-offCompliance-grade audit trail reconstructionMulti-human deliberation on agent proposalsShift handoff between human reviewersCapturing overrides as supervision training dataNon-repudiable signed decision logs
Built With
- Language
- HTML
- Frameworks
- Model Context Protocol (MCP) · A2A · JSON-RPC · SQLite · Node.js · Python · OIDC/OAuth2 · SCITT
Tags
human-in-the-loop · audit-trail · mcp · a2a · multi-agent · ai-governance · approvals · overrides · escalation · handoff · verifiable-logs · json-rpc · protocol · python · typescript · ed25519