guardrails
CLAUDE.md7.5k starsChanged 8 months agoApache-2.0View on GitHub
This repo separates compatibility (what users are allowed to install) from security (what we actually ship and test against). The two live in different files and must be managed differently: - pyproject.toml — keep dependency ranges WIDE. Floors and ceilings here exist to express genuine compatibility boundaries (a real API break, a known-incompatible major), not to pin security-patched versions. Do not raise a floor just to dodge a CVE. Narrow ranges here propagate into every downstream project that installs guardrails-ai,…
We split this CLAUDE.md into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 25
Prefer fixing a transitive cap at its source: if a first-party package (e.g.
- Very specific: line 28
Only add an environment marker (e.g.
- Very specific: line 40
Run them inside the project venv (source .venv/bin/activate).
≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.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.
Files
Guardrails — contributor guidance for Claude
Dependency strategy (IMPORTANT — always follow)
This repo separates compatibility (what users are allowed to install) from security (what we actually ship and test against). The two live in different files and must be managed differently:
pyproject.toml— keep dependency ranges WIDE. Floors and ceilings here exist to express genuine compatibility boundaries (a real API break, a known-incompatible major), not to pin security-patched versions. Do not raise a floor just to dodge a CVE. Narrow ranges here propagate into every downstream project that installsguardrails-ai, causing resolver conflicts for users.poetry.lock— pin the SAFE, patched versions. Dependabot scans the lock file, so the lock is where security fixes land. Within the widepyprojectranges, the lock should resolve to the latest patched releases.
How to apply
- To fix a Dependabot/security alert: widen the
pyprojectrange only as far as needed to allow the patched version (e.g. if the fix is in a new major, raise the ceiling), then updatepoetry.lockto the patched version withpoetry update <pkg>(or a fullrm poetry.lock && poetry lockto also re-resolve non-active marker branches —poetry updatewill not re-resolve marker branches likepython_version >= "3.x"). - Prefer fixing a transitive cap at its source: if a first-party package (e.g.
guardrails-api) caps a dependency below a security fix, raise the cap in that package and release it, rather than pinning around it here. - Only add an environment marker (e.g.
; python_version < '3.15') to apyprojectdependency when a transitive constraint makes a version genuinely unresolvable for part of the supported Python range — not as a convenience.
Gates — all three must pass before any dependency change is "done"
make lint # ruff check + format --check
make type # pyright guardrails/
make test # pytest tests/Run them inside the project venv (source .venv/bin/activate). Never install into system
Python; if the venv is broken, recreate it (make refresh).
Trending
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Who's talking about guardrails-ai/guardrails
- agentic-layer/agent-runtime-operator“Introduce Guardrails”GitHub · Feb 13, 2026 · 1 reactions
- tbrandenburg/shai“GitMCP”GitHub · Nov 17, 2025 · 1 reactions
- Arize-ai/openinference“🗺 GuardrailsAI instrumentation”GitHub · Jul 1, 2024 · 1 reactions
- A Hacker News story“Guardrails AI”Hacker News · Dec 30, 2023 · 1 points
- GuardBee/guardbee-mcp“Python SDK + LangChain, LlamaIndex, CrewAI and OpenAI Agents SDK integrations”GitHub · Oct 28, 2026
The biggest 5 of 51 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 51
Talked about on GitHub and Hacker News (51 times).
On GitHub · 50
- Feb 13, 2026Introduce Guardrails — agentic-layer/agent-runtime-operator1 reaction
- Nov 17, 2025GitMCP — tbrandenburg/shai1 reaction · 5 comments
- Jul 1, 2024🗺 GuardrailsAI instrumentation — Arize-ai/openinference1 reaction · 1 comment
- Oct 28, 2026Python SDK + LangChain, LlamaIndex, CrewAI and OpenAI Agents SDK integrations — GuardBee/guardbee-mcp0 reactions
- Oct 26, 2026docs(readme): replace marketing claims with verified problem statement, layer map, and license split — cordum-io/cordum0 reactions · 3 comments
45 more on GitHub
- Oct 25, 2026Bump guardrails-ai from 0.6.8 to 0.11.0 — RudrenduPaul/hardening-llm-systems-production0 reactions
- Oct 23, 2026Freshness sweep: remove 10 unmaintained tools, fix 27 stale links — ottosulin/awesome-ai-security0 reactions
- Oct 5, 2026Result: Guardrails AI — ninadphalak/LLM-Shield-Proxy0 reactions · 1 comment
- Oct 1, 2026repo-radar: guardrails-ai/guardrails — bütçeli reask, deterministic fix ve fail-closed statü ayrımı için 7 somut öneri — ali-ulu/huqan0 reactions · 2 comments
- Sep 28, 2026[bot] Instrument Guardrails AI (30,625 weekly downloads) — braintrustdata/braintrust-sdk-python0 reactions · 1 comment
- Sep 22, 2026wiki: bulk update 2026-09-22 — wikicommit/ai-driven-dev-wiki0 reactions
- Sep 21, 2026wiki: bulk update 2026-09-21 — wikicommit/ai-driven-dev-wiki0 reactions
- Sep 8, 2026Weekly link audit needs attention — yzhao062/awesome-auditable-ai0 reactions
- Aug 24, 2026deps(python): bump the python-runtime group across 2 directories with 103 updates — JoeElder21/Joeyyy0 reactions · 1 comment
- Aug 5, 2026feat: add Core & Feature guardrails — JustineDevs/premortem0 reactions
- Aug 4, 2026Add support of GuardRails — The-PR-Agent/pr-agent0 reactions · 2 comments
- Aug 4, 2026License correction: Guardrails AI — repo LICENSE shows Apache-2.0 not MIT — tiberiuarva/enterpriseaitools0 reactions
- Jul 27, 2026docs: add and categorize requested AI tools in README — handsondad/future-learner0 reactions
- Jul 24, 2026Error spans are stringly-typed, duplicated, and have no defined offset basis on the streaming validate endpoint — guardrails-ai/guardrails-api0 reactions
- Jul 24, 2026Design: redesign ValidationOutcome around a tagged resolution (original / judgment / resolved value) — guardrails-ai/guardrails-ai0 reactions · 1 comment
- Jul 24, 2026OpenAI-compatible endpoint returns 200 with raw content when validation fails; should return an error carrying the guardrails payload — guardrails-ai/guardrails-api0 reactions · 1 comment
- Jul 11, 2026License correction: Guardrails AI — repo LICENSE shows Apache-2.0 not MIT — tiberiuarva/enterpriseaitools0 reactions
- Jul 7, 2026LLM Guardrails in Practice: A Decision Guide to Runtime Input/Output Filtering Tools — copilot-autogent/ai-security-blog0 reactions · 1 comment
- Jun 15, 2026Actualiza README con nuevos modelos LLM/guardrails y sección de modelos propios — erickfmm/Awesome-NLP-LLM-Spanish-Espa-ol0 reactions
- Jun 13, 2026License correction: Guardrails AI — repo LICENSE shows Apache 2.0 not MIT — tiberiuarva/enterpriseaitools0 reactions
- Jun 9, 2026chore(deps): bump guardrails-ai from 0.9.0 to 0.10.2 in /backend — rohitkumarnaidu/ScholarFormAI0 reactions · 1 comment
- Jun 7, 2026License correction: Guardrails AI — repo LICENSE shows Apache 2.0 not MIT — tiberiuarva/enterpriseaitools0 reactions
- Jun 7, 2026License correction: Guardrails AI — repo LICENSE shows Apache 2.0 not MIT — tiberiuarva/enterpriseaitools0 reactions
- Jun 7, 2026deps(deps): update guardrails-ai requirement from >=0.2.0 to >=0.10.2 in /backend — camiloavilacm/camiloavila.dev0 reactions · 3 comments
- Jun 6, 2026Daily CVE Report — 2026-06-06 (52 CVEs, 9 critical) — wj-tech/daily-cves0 reactions
- Jun 3, 2026feat(content): add guardrails-ai — JSONbored/awesome-claude0 reactions · 2 comments
- May 30, 2026License correction: Guardrails AI — repo LICENSE shows Apache 2.0 not MIT — tiberiuarva/enterpriseaitools0 reactions
- May 25, 2026License correction: Guardrails AI — tiberiuarva/enterpriseaitools0 reactions
- May 23, 2026License correction: Guardrails AI — repo LICENSE shows Apache-2.0 not MIT — tiberiuarva/enterpriseaitools0 reactions
- May 23, 2026License correction: Guardrails AI — repo LICENSE shows Apache-2.0 not MIT — tiberiuarva/enterpriseaitools0 reactions
- May 20, 2026Epic: Assimilate Guardrails AI as an Ouroboros-native agentOS capability — Ouro-labs/ouroboros-plugins0 reactions · 3 comments
- May 16, 2026License correction: Guardrails AI — repo LICENSE shows Apache License 2.0 not MIT — tiberiuarva/enterpriseaitools0 reactions
- May 12, 2026Remove guardrails-ai git source override once PyPI restores the project — Idun-Group/idun-agent-platform0 reactions
- May 12, 2026Fixed guardrails pypi bug — ProjectTech4DevAI/kaapi-guardrails0 reactions · 1 comment
- May 12, 2026Avoid CI dependency resolution failures by making `mistralai` / `guardrails-ai` optional and hardening matrix generation — mlflow/mlflow0 reactions · 8 comments
- May 9, 2026License correction: Guardrails AI — repo LICENSE shows Apache License 2.0 not MIT — tiberiuarva/enterpriseaitools0 reactions
- May 5, 2026deps(deps): update guardrails-ai requirement from >=0.2.0 to >=0.10.0 in /backend — camiloavilacm/camiloavila.dev0 reactions · 3 comments
- Apr 30, 2026Add Instructor, Guardrails AI, and Mirascope to catalog — nimit2801/Agentic-AI-For-Good0 reactions · 2 comments
- Apr 21, 2026Bump the pip group across 4 directories with 4 updates — 24601/xrx-core0 reactions
- Apr 5, 2026chore(deps): bump guardrails-ai from 0.9.3 to 0.10.0 — vectimus/sentinel0 reactions
- Mar 23, 2026chore(deps): Bump guardrails-ai from 0.8.0 to 0.9.2 — NOAA-GSL/zyra0 reactions · 1 comment
- Mar 22, 2026chore(deps): bump the patch-updates group with 3 updates — vectimus/sentinel0 reactions · 2 comments
- Mar 18, 2026Bump the pip group across 3 directories with 3 updates — 24601/xrx-core0 reactions · 1 comment
- Mar 15, 2026chore(deps): bump guardrails-ai from 0.6.6 to 0.9.1 — vectimus/sentinel0 reactions · 1 comment
- Mar 13, 2026[GR-1408]: Add integration tests for config file flows — guardrails-ai/guardrails-api0 reactions
On Hacker News · 1
- Dec 30, 2023Guardrails AI1 point
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.

