Reef AI Agent
Infrastructure for continually self‑improving agents
Reef is an open-source ai agent by Human-Agent-Society, written mainly in Python, with 7,783 GitHub stars and the Apache-2.0 license. Its code was last updated Nov 1, 2026.
Scan summary: scanned Nov 5, 2026 at commit 911a91c. Seen able to run dynamic code, connect to the internet. Scan policy
ScannedScanned. The automated checks below ran on the commit shown. Read each line for what was and was not covered.
Full scan at
911a91c · Nov 5, 2026 ScannedStatic, secrets and dependency checks completed with no critical findings. BuildsIt installed from a fresh machine.
Warning. This check found something worth reading in the findings below. It is not proof of a problem.Static code scanwarnWarning. This check found something worth reading in the findings below. It is not proof of a problem.
Passed. This check ran and found nothing it flags.Secrets scanpassPassed. This check ran and found nothing it flags.
Warning. This check found something worth reading in the findings below. It is not proof of a problem.Dependency audit7 known vulnerabilitieswarnWarning. This check found something worth reading in the findings below. It is not proof of a problem.
Warning. This check found something worth reading in the findings below. It is not proof of a problem.ManifestnonewarnWarning. This check found something worth reading in the findings below. It is not proof of a problem.
Passed. This check ran and found nothing it flags.BuildpassPassed. This check ran and found nothing it flags.
Not applicable. This check does not apply to this kind of project, or it was not run in this scan.Boot & handshaken/aNot applicable. This check does not apply to this kind of project, or it was not run in this scan.
Warning. This check found something worth reading in the findings below. It is not proof of a problem.Network egresswarnWarning. This check found something worth reading in the findings below. It is not proof of a problem.
Not applicable. This check does not apply to this kind of project, or it was not run in this scan.Reproducible (×3)n/aNot applicable. This check does not apply to this kind of project, or it was not run in this scan.
Findings (20)
- mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
reef/execution/executor/multiproc.py:53 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
reef/execution/executor/multiproc.py:72 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
reef/execution/executor/multiproc.py:119 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.zod@4.4.3: 1 known vulnerabilityGHSA-mrhx-c7xc-m3w5
docs/site/package-lock.json - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.accelerate@1.14.0: 1 known vulnerabilityPYSEC-2026-3804
uv.lock - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.transformers@5.5.4: 2 known vulnerabilitiesPYSEC-2026-3929, PYSEC-2026-4174
uv.lock - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Install contacted hosts other than package registriesreleases.astral.sh
- lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Deserializes data with pickle/marshal, which can execute code.
recipes/tttd/examples/tttd/harness/sandbox.py:121 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: curl-auth-header2 matches in this file
docs/user-guide/evolve-your-model.rst:164 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: curl-auth-header3 matches in this file
docs/getting-started/quickstart.rst:77 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: curl-auth-header
docs/user-guide/recipes/tttd.rst:232 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: curl-auth-header
docs/user-guide/recipes/sao.rst:151 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: curl-auth-header
recipes/sao/examples/imo_answerbench/README.md:210 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key2 matches in this file
tests/evaluation/test_harness_tasks.py:32 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key2 matches in this file
tests/harness/test_native_loop.py:113 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
tests/reef_service/test_harness_recipe.py:1330 - lowLow. Minor, or common in normal tools. Shown for information.katex@0.16.47: 1 known vulnerabilityGHSA-238p-pmpm-9mq7
docs/site/package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.minimatch@10.2.6: 1 known vulnerabilityGHSA-g3hv-75wg-m249
docs/site/package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.setuptools@84.0.0: 1 known vulnerabilityGHSA-xmj3-9gf7-h52w
uv.lock - lowLow. Minor, or common in normal tools. Shown for information.No manifest declaring network access and environment variables (agent.json)
Network activity
During install
files.pythonhosted.orgpypi.orgreleases.astral.sh
While running
Not run — the code wasn't started in this scan
Automated result for the commit shown. See our scan policy. View the scan log
Maintainers can claim the listing to rescan, or dispute a result.
Reef alternatives
View more →Similar ai agents in Deployment & DevOps, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.
| Name | Stars | Licence | Last updated | Scan |
|---|---|---|---|---|
| Reef (this page) Human-Agent-Society | 7.8k | Apache-2.0 | Nov 1, 2026 | Scanned, no flagged issues |
| Langflow langflow-ai | 156k | MIT | Nov 1, 2026 | Scanned, no flagged issues |
| Novu novuhq | 40k | None found | Nov 1, 2026 | Not scanned yet |
| QwenPaw agentscope-ai | 37k | Apache-2.0 | Oct 30, 2026 | Scanned, no flagged issues |
| Kestra kestra-io | 30k | Apache-2.0 | Oct 30, 2026 | Scanned, no flagged issues |
| Chroma chroma-core | 30k | Apache-2.0 | Oct 30, 2026 | Scanned, no flagged issues |