BrightbeamAI / chap
CHAP, the Collaborative Human Agent Protocol, is a MCP/A2A-compatible runtime for auditable human-agent work: approvals, overrides, handoffs, escalation and verifiable evidence logs.
Why this job: says: agent protocol; topics: a2a, human-in-the-loop, multi-agent-systems, ai-agents
What it does
CHAP gives approvals, overrides, handoffs and escalations one shared, auditable shape across MCP and A2A.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit yesterday
- Stars
- 122
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.3.5
- Released yesterday
- Built with
- Python
- 30% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 98% closed
- 1 still open
- Pull requests
- 125 merged
- 0 waiting
- Releases
- 15
- 15 in the last year
More: languages, topics, project record and preview image
Languages
- Python 30%
- HTML 30%
- TypeScript 16%
- JavaScript 15%
Topics
- human-ai-collaboration
- human-computer-interaction
- human-in-the-loop
- human-robot-interaction
- a2a
- a2a-protocol
- ai-agents
- audit-trail
- mcp
- model-context-protocol
- multi-agent-systems
- python
Project record
- JobAgent frameworks
- StatusListed
- Commits428
- Forks14
- Watching1
- Stars in 28 days+14
- CreatedMay 17, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026