Evaluation report

• Repository is reachable

  https://github.com/open-multi-agent/open-multi-agent @ 05d028d — ★ 6,412 · TypeScript · MIT · last push today

• Manifest detected

  kind=mcp slug=open-multi-agent-core · path=packages/core · source=package.json

• Slug is URL-safe

  "open-multi-agent-core" matches /^[a-z0-9][a-z0-9-]{0,62}$/

• Slug is unique within kind

  No collision found for mcp/open-multi-agent-core

• Version is semver

  1.8.0

• Description quality

  24 words · 176 chars — "TypeScript multi-agent framework: one runTeam() call from goal to result. Auto t…"

• README is present and substantial

  10,864 chars · 8 sections · 5 code blocks

• Tags / topics declared

  24 total — ai, agent, multi-agent, orchestration, llm, claude (+18)

• README has usage / example sections

  no labeled section but 5 code blocks document usage

• Homepage / docs URL declared

  https://github.com/open-multi-agent/open-multi-agent#readme

• Dependencies: known vulnerabilities

  OSV.dev clean — 0 high/critical across 3 deps

• LICENSE file at repo root

  LICENSE

• No sensitive files in the repo

  scanned for .env, credentials.json, *.pem, .ssh/, AWS / GCP configs — none found

• MCP: launch path

  bin: oma

• MCP: @modelcontextprotocol/sdk in dependencies

  pinned at "^1.18.0"

• MCP: SDK version pinned

  pinned at "^1.18.0"

• MCP: ESM package

  "type": "module"

• MCP: server surface

  0 tools

• Recent activity

  last push today

• Tests detected

  2 test directories · 75 test files

• CI configuration detected

  GitHub Actions (1 workflows)

This artifact hasn't produced behavioral results yet: the evaluation sandbox couldn't run it (it may need credentials we don't provide, or a build our environment doesn't support). That's a limitation of our environment, not a verdict on the artifact.