Guardrails
AGENTS.md7.5k starsChanged 17 days agoLicence not identifiedView on GitHub
CONTRIBUTING.md is canonical for public contribution workflow: issues, assignment, pull requests, refactors, changelogs, validation, commits, and DCO. AI_POLICY.md is canonical for public AI-assisted contribution policy. When working inside nemoguardrails/, also…
- Installs packages
Trending
More talk lately.about the whole repository
Who's talking about NVIDIA-NeMo/Guardrails
- fern-api/fern“feat(cli): add `ref` field to git library input in docs.yml”GitHub · Jun 11, 2026 · 2 reactions
- FetchDoge/site“docs: use contact@ email and updated NeMo Guardrails link”GitHub · Oct 15, 2026 · 1 reactions
- FetchDoge/site“Update links to FetchDoge account”GitHub · Oct 15, 2026 · 1 reactions
- cgfixit/CyClaw“[security] - correct NeMo self-check input polarity”GitHub · Jul 29, 2026 · 1 reactions
- pypi/support“PEP 541 Request: nemoguardrails (TestPyPI only)”GitHub · Jul 27, 2026 · 1 reactions
The biggest 5 of 50 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 50
Talked about on GitHub (50 times).
On GitHub · 50
- Jun 11, 2026feat(cli): add `ref` field to git library input in docs.yml — fern-api/fern2 reactions · 6 comments
- Oct 15, 2026docs: use contact@ email and updated NeMo Guardrails link — FetchDoge/site1 reaction · 1 comment
- Oct 15, 2026Update links to FetchDoge account — FetchDoge/site1 reaction · 1 comment
- Jul 29, 2026[security] - correct NeMo self-check input polarity — cgfixit/CyClaw1 reaction · 1 comment
- Jul 27, 2026PEP 541 Request: nemoguardrails (TestPyPI only) — pypi/support1 reaction · 1 comment
45 more on GitHub
- Nov 12, 2026chore(deps):(deps): bump the uv group with 6 updates — daggerstuff/pixelated0 reactions · 5 comments
- Nov 10, 2026chore(deps):(deps): bump the uv group with 11 updates — daggerstuff/pixelated0 reactions · 2 comments
- Nov 9, 2026chore(deps-dev): bump nemoguardrails in /agents/langgraph/examples/guardrailed_agent — red-hat-data-services/agentic-starter-kits0 reactions · 2 comments
- Nov 9, 2026Auto update review: evidence and benchmark candidates — icecreamyoubest/awesome-agentic-ai-security0 reactions
- Nov 6, 2026chore(deps):(deps): bump the uv group with 11 updates — daggerstuff/pixelated0 reactions · 2 comments
- Nov 4, 2026chore(deps):(deps): bump the uv group with 6 updates — daggerstuff/pixelated0 reactions · 2 comments
- Nov 4, 2026Add optional NeMo trusted-host execution gate (prototype) — nicholaskouns-create/auth-kernel0 reactions · 1 comment
- Nov 2, 2026chore(deps-dev): bump nemoguardrails in /agents/langgraph/examples/guardrailed_agent — red-hat-data-services/agentic-starter-kits0 reactions · 3 comments
- Nov 2, 2026Auto update review: evidence and benchmark candidates — icecreamyoubest/awesome-agentic-ai-security0 reactions
- Nov 1, 2026Enlaces para revisar · 2026-11 — xagent7/catastro-ia0 reactions
- Nov 1, 2026chore(deps): update nemoguardrails requirement from >=0.19.0 to >=0.24.1 — NVIDIA-AI-Blueprints/Multi-Agent-Intelligent-Warehouse0 reactions · 1 comment
- Oct 28, 2026chore(deps):(deps): bump the uv group across 1 directory with 4 updates — daggerstuff/pixelated0 reactions · 2 comments
- Oct 28, 2026Python SDK + LangChain, LlamaIndex, CrewAI and OpenAI Agents SDK integrations — GuardBee/guardbee-mcp0 reactions · 1 comment
- Oct 26, 2026Auto update review: evidence and benchmark candidates — icecreamyoubest/awesome-agentic-ai-security0 reactions
- Oct 26, 2026docs(readme): replace marketing claims with verified problem statement, layer map, and license split — cordum-io/cordum0 reactions · 3 comments
- Oct 20, 2026Bump the pip-minor-patch group with 16 updates — cgfixit/CyClaw0 reactions · 1 comment
- Oct 20, 2026Bump the pip-all group across 1 directory with 55 updates — cgfixit/CyClaw0 reactions · 2 comments
- Oct 19, 2026Bump the pip-all group with 54 updates — cgfixit/CyClaw0 reactions · 1 comment
- Oct 19, 2026Auto update review: evidence and benchmark candidates — icecreamyoubest/awesome-agentic-ai-security0 reactions
- Oct 18, 2026Bump the pip-all group with 62 updates — cgfixit/CyClaw0 reactions · 1 comment
- Oct 12, 2026Auto update review: evidence and benchmark candidates — icecreamyoubest/awesome-agentic-ai-security0 reactions
- Oct 8, 2026chore(deps): update nemoguardrails requirement from ==0.11.* to ==0.17.* — Hoodkitz/us-expat-tax0 reactions
- Oct 7, 2026feat(server): execute buffered guarded operations — sjmaple/cr-Guardrails0 reactions
- Oct 7, 2026feat(server): declare private transparent proxy contracts — sjmaple/cr-Guardrails0 reactions
- Oct 7, 2026feat: add tool_safety_check LLM-judged per-tool rail — sjmaple/cr-Guardrails0 reactions
- Oct 7, 2026fix(library): Presidio detection blocks the async event loop — sjmaple/cr-Guardrails0 reactions
- Oct 5, 2026Auto update review: evidence and benchmark candidates — icecreamyoubest/awesome-agentic-ai-security0 reactions
- Sep 28, 2026Auto update review: evidence and benchmark candidates — icecreamyoubest/awesome-agentic-ai-security0 reactions
- Sep 27, 2026deps(pip): update nemoguardrails requirement from >=0.10 to >=0.24.1 — keyuraghao/aisrf0 reactions · 1 comment
- Sep 26, 2026Protecting against LLM Vulnerabilities — nicholaskouns-create/E47-Kartekeya0 reactions · 7 comments
- Sep 24, 2026Bump nemoguardrails from 0.9.1.1 to 0.24.1 — dsp-testing/poetry-unknown-metadata-test-v20 reactions
- Sep 24, 2026wiki: bulk update 2026-09-24 — wikicommit/ai-driven-dev-wiki0 reactions
- Sep 22, 2026Bump the pip-all group with 9 updates — cgfixit/CyClaw0 reactions · 1 comment
- Sep 21, 2026chore(deps): update nemoguardrails requirement from >=0.19.0 to >=0.24.1 — tentechle/Multi-Agent-Intelligent-Warehouse0 reactions · 1 comment
- Sep 21, 2026Auto update review: evidence and benchmark candidates — icecreamyoubest/awesome-agentic-ai-securitysays it tested it0 reactions
- Sep 14, 2026[bot] Instrument NVIDIA NeMo Guardrails (149,615 weekly downloads) — braintrustdata/braintrust-sdk-python0 reactions
- Sep 7, 2026deps(deps): bump nemoguardrails from 0.22.0 to 0.24.0 in the python-minor-patch group — niluferbagevi-gif/Sidar0 reactions · 2 comments
- Sep 5, 2026feat(plugin): conduct-nemo-guard — runnable support-bot example + Guard Activity source tag — sseshachala/conductai0 reactions · 4 comments
- Sep 5, 2026epic(guard): NeMo Guardrails integration — plugin, register, import (three tracks) — sseshachala/conductai0 reactions
- Aug 24, 2026Auto update review: evidence and benchmark candidates — icecreamyoubest/awesome-agentic-ai-securitysays it tested it0 reactions
- Aug 17, 2026Auto update review: evidence and benchmark candidates — icecreamyoubest/awesome-agentic-ai-securitysays it tested it0 reactions
- Aug 12, 2026Discussion(nemo-guardrails): Evaluate moving NeMo plugins to `/v1/checks` endpoint for redaction support — opendatahub-io/ai-gateway-payload-processing0 reactions · 3 comments
- Aug 10, 2026Auto update review: evidence and benchmark candidates — icecreamyoubest/awesome-agentic-ai-securitysays it tested it0 reactions
- Aug 3, 2026Auto update review: evidence and benchmark candidates — icecreamyoubest/awesome-agentic-ai-securitysays it tested it0 reactions
- Jul 11, 2026Link Checker Report — NipunaRanasinghe/awesome-ai-agents0 reactions
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository7 other files it gives its agents.
- docs/AGENTS.mdAGENTS.md
- nemoguardrails/AGENTS.mdAGENTS.md
- add-library-railSkill
- guardrails-developer-create-guardrailsSkill
- guardrails-developer-guideSkill
- recorded-testsSkill
- review-library-railSkill
The file
Show its rules and text
We split this AGENTS.md into the rules it gives an agent
26 rules. About 0 are common, 11 are distinctive, and 15 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
Distinctive · estimate
This author's own choices. Worth a look.
15
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

