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.

BrightbeamAI/chap

View on GitHub ↗

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.

chap grew +1.7% in the last 30 days, ranks 1890th of 2,447 in Protocols (MCP / A2A), actively maintained, last commit yesterday.

Star trajectory

63 days tracked
2026-09-19123 stars today2026-11-22
Momentum

+1.7% in 30d, below the Protocols (MCP / A2A) median of +1.8%.

Maintenance

Last commit yesterday, fresher than the median of 12d.

How it compares in Protocols (MCP / A2A)

chap
123
stars
+1.7% 30d
commit yesterday
Protocols (MCP / A2A) median
223
stars
+1.8% 30d
commit ~12d ago
Leader · rea
473.2k
stars
+28.6% 30d
commit today

Ranked 1890th of 2,447 by stars.

Ranked by shared tags, then keywords, then stars
  1. Open protocol for AI agent work contracts and verifiable execution — authorization, evidence, and acceptance…

    -1 (-0.4%) in 30d · Committed 12d ago · Python · Apache-2.0

    Shares Protocols (MCP / A2A), Multi-Agent Orchestration, Evaluation & Guardrails

  2. Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency…

    +6 (+2.9%) in 30d · Committed today · Kotlin · MIT

    Shares Multi-Agent Orchestration, Protocols (MCP / A2A), Evaluation & Guardrails

  3. Top Open-Source AI Engineering Platform 2026 Qyvaria Kernel

    +0 (+0.0%) in 30d · Committed today · HTML

    Shares Multi-Agent Orchestration, Evaluation & Guardrails, Protocols (MCP / A2A)

  4. Open-source research assistant and MCP audit toolkit for systematic reviews: cited research reports, PRISMA…

    +22 (+25%) in 30d · Committed 2d ago · Python · MIT

    Shares Evaluation & Guardrails, Protocols (MCP / A2A), Multi-Agent Orchestration

  5. Auto researching harness that burns through everything.

    Committed 4d ago · TypeScript · Apache-2.0

    Shares Multi-Agent Orchestration, Evaluation & Guardrails, Protocols (MCP / A2A)

  6. AI agent runtime for Rust — type-safe state, multi-protocol serving, plugin extensibility.

    Committed today · Rust · Apache-2.0

    Shares Multi-Agent Orchestration, Protocols (MCP / A2A), Evaluation & Guardrails

  7. Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic…

    +3 (+2.3%) in 30d · Committed 18d ago · Rust · Unlicense

    Shares Multi-Agent Orchestration, Protocols (MCP / A2A), Evaluation & Guardrails

  8. HAR: open agent harness (CLI + MCP) for coding agents. Isolated worktrees, deterministic verify, software…

    +8 (+6.3%) in 30d · Committed yesterday · TypeScript · Apache-2.0

    Shares Multi-Agent Orchestration, Protocols (MCP / A2A), Evaluation & Guardrails

  9. One control plane for every AI asset — MCP servers, skills, agents, model gateways, AI apps, NAS. Self-hosted…

    Committed 4d ago · JavaScript · MIT

    Shares Multi-Agent Orchestration, Protocols (MCP / A2A), Evaluation & Guardrails

  10. AI agent identity, signed credentials, delegated authority and portable governance evidence. Python core and…

    -225 (-27%) in 30d · Committed today · Python · Apache-2.0

    Shares Protocols (MCP / A2A), Evaluation & Guardrails

Language
Python
License
Apache License 2.0
Contributors
10
Forks
14
Watchers
1
Open issues
0
Releases
15
Created
2026-05-17
Stars this week
+1

You've seen where chap stands today.

Get the moves before everyone else: the 5 Protocols (MCP / A2A) repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain chap?

Claim this page to add your own call-to-action.

Claim this page