An open API service providing package, version and dependency metadata of many open source software ecosystems and registries.

pypi.org "guardrails" keyword

langgraph-harness 0.1.1
Per-node HARNESS parsing, injection and enforcement for LangGraph nodes.
1 version - Latest release: about 1 hour ago - 1 maintainer
ai-permission-supervisor 0.1.0
Local guardrail for IBM Bob: intercepts every agent tool call and allows, denies, or escalates it...
1 version - Latest release: about 2 hours ago - 1 maintainer
phiproxy 0.1.0a3
Your patients' stand-in on the way to any LLM, and back: reversible PHI masking proxy (LiteLLM gu...
3 versions - Latest release: about 2 hours ago - 0 stars on GitHub - 1 maintainer
micro-jev 0.4.1 💰
Hybrid System-One Local Decision Engine (JevCompat 32/32 MUST, AnyJev L0 Prefill, StartLux Read-o...
3 versions - Latest release: about 2 hours ago - 239 downloads last month - 8 stars on GitHub - 1 maintainer
qryndel 0.3.0
A safe, schema-checked query language for SQLite: bound parameters, write guards, budgets and gua...
1 version - Latest release: about 4 hours ago - 1 maintainer
qwed 10.0.0 💰
Open-source AI verification infrastructure for deterministic verification of LLM outputs, tool ca...
29 versions - Latest release: 3 days ago - 799 downloads last month - 77 stars on GitHub - 1 maintainer
vericto 0.9.0
Official Vericto SDK for Python: database guardrails for AI agents, check SQL before it runs. Wra...
10 versions - Latest release: about 4 hours ago - 1.12 thousand downloads last month - 2 stars on GitHub - 1 maintainer
tinplate 1.1.7
Zero-dependency Python SDK for the Tinplate 42-API AI Safety, Security & Compliance Edge Gateway.
10 versions - Latest release: about 4 hours ago - 596 downloads last month - 1 maintainer
lamellar 0.2.1
Armor for small local models: rules checked by code before the answer reaches you. Fully offline.
2 versions - Latest release: about 9 hours ago - 0 stars on GitHub - 1 maintainer
brigade-cli 0.31.0
Run coding agents anywhere and keep one record of the work, with MCP servers, tools, skills, and ...
140 versions - Latest release: 3 days ago - 3.28 thousand downloads last month - 83 stars on GitHub - 1 maintainer
aijscan 0.1.0
Async jailbreak-resistance scanner for LLM endpoints
1 version - Latest release: about 4 hours ago - 0 stars on GitHub - 1 maintainer
stalwart-agents 1.1.24
Build your own AI agent, powerful but controlled: your tools and your rules, checked on your own ...
32 versions - Latest release: about 4 hours ago - 7.43 thousand downloads last month - 1 maintainer
driftgard 1.31.0
Official DriftGard Python SDK — evaluate LLM interactions against your compliance policy
45 versions - Latest release: about 5 hours ago - 369 downloads last month - 1 maintainer
sra-riskgate 1.8.1
Fail-closed checks for AI-agent stablecoin payments (USDC, USDT, USDB, USDG): OFAC SDN match, pay...
50 versions - Latest release: about 5 hours ago - 5.5 thousand downloads last month - 1 stars on GitHub - 1 maintainer
llmrivotril 0.2.1
A lightweight framework to reduce LLM hallucinations, enforce guardrails, manage stateful memory,...
9 versions - Latest release: about 5 hours ago - 490 downloads last month - 0 stars on GitHub - 1 maintainer
aapt-guard-rails 0.2.0
OWASP-mapped, CVSS-scored AI-security guardrails for LLM gateways (LiteLLM and more).
2 versions - Latest release: about 5 hours ago - 53 downloads last month - 0 stars on GitHub - 1 maintainer
nemo-helix-plugin 0.10.0
Public plugin contract for the NeMo Helix - the only package plugin authors need.
10 versions - Latest release: about 5 hours ago - 452 downloads last month - 145 stars on GitHub
nemo-helix 0.10.0
Convenience wrapper distribution for NeMo Helix Python packages
10 versions - Latest release: about 5 hours ago - 4.63 thousand downloads last month - 145 stars on GitHub
prusik 0.247.0
Agents do the work; prusik checks the receipt. The independent verification layer for AI coding a...
99 versions - Latest release: about 6 hours ago - 4.72 thousand downloads last month - 1 stars on GitHub - 1 maintainer
capt-hook 12.121.88
Stop repeating yourself to Claude.
691 versions - Latest release: about 6 hours ago - 165 thousand downloads last month - 15 stars on GitHub - 1 maintainer
adrails 0.14.4
AdRails: open-source MCP server for AI agents running ad accounts with guardrails: Google Ads, Go...
20 versions - Latest release: about 6 hours ago - 2.03 thousand downloads last month - 0 stars on GitHub - 1 maintainer
highbar 0.2.0
Evals for AI agents that behave like tests.
5 versions - Latest release: about 7 hours ago - 513 downloads last month - 0 stars on GitHub - 1 maintainer
pipecat-guardrails 0.3.1
Output guardrails for Pipecat voice agents: check what the bot is about to say, and stop it befor...
6 versions - Latest release: about 10 hours ago - 635 downloads last month - 0 stars on GitHub - 1 maintainer
benigntwin 1.0.3
Benchmark prompt-injection detectors and LLM guardrails on matched benign/attack pairs: attack re...
4 versions - Latest release: about 8 hours ago - 1 maintainer
locus-sdk 5.5.0
Oracle Generative AI Multi-Agent Reasoning Orchestrator SDK: the agent framework where the model ...
36 versions - Latest release: about 10 hours ago - 2.08 thousand downloads last month - 9 stars on GitHub - 1 maintainer
lights-out-gates 0.8.0
The gates of lights-out that need only git and Python: one line, GO or NO-GO, no container.
5 versions - Latest release: about 9 hours ago - 432 downloads last month - 10 stars on GitHub - 1 maintainer
auditail 0.9.0
Controls and evidence for AI agents that move money: spending limits, human approval, a kill swit...
11 versions - Latest release: about 9 hours ago - 997 downloads last month - 0 stars on GitHub - 1 maintainer
contract4agents 0.25.2
Typed declarative contracts for AI agent systems.
39 versions - Latest release: 5 days ago - 2.33 thousand downloads last month - 0 stars on GitHub - 1 maintainer
writ-mcp 0.2.5
Writ MCP server: point-of-action policy checks for AI agent writes (ALLOW/DENY/STEP_UP) with a ta...
10 versions - Latest release: about 9 hours ago - 751 downloads last month - 2 stars on GitHub - 1 maintainer
sentinel-proof-mcp 0.1.2
MCP server that fact-checks an LLM answer against its source passages before the user sees it: ev...
3 versions - Latest release: about 9 hours ago - 0 stars on GitHub - 1 maintainer
zn-gate 1.16.0
The local security layer for Python AI agents (LangChain, CrewAI, LlamaIndex, plain tool calling)...
30 versions - Latest release: about 9 hours ago - 9.02 thousand downloads last month - 5 stars on GitHub - 1 maintainer
sage-harness 1.3.8
Governance harness for AI coding agents — spec-SSOT closed loop for Claude Code and Codex
55 versions - Latest release: about 9 hours ago - 864 downloads last month - 0 stars on GitHub - 1 maintainer
antihallucination 0.2.1
Your numbers decide; the AI only writes. Every figure, direction and name an AI writes is checked...
2 versions - Latest release: about 10 hours ago - 1 maintainer
fusion-safety 0.1.10
Measure and guard AI agents: safety and quality evaluation with a runtime guardrail
11 versions - Latest release: about 10 hours ago - 802 downloads last month - 0 stars on GitHub - 1 maintainer
mesedi 0.9.0
Mesedi SDK: guardians for autonomous AI agents. Detect failures, halt runaways, escalate first oc...
12 versions - Latest release: about 11 hours ago - 76 downloads last month - 0 stars on GitHub - 1 maintainer
onedoor 0.11.2
A tiered guardrail/policy engine for agentic systems: default-deny, bounds, caps, approvals, dry-...
24 versions - Latest release: about 12 hours ago - 998 downloads last month - 0 stars on GitHub - 1 maintainer
laya 0.4.35
Fast, non-autoregressive System 1 decision engine with calibrated probabilities
73 versions - Latest release: about 13 hours ago - 239 thousand downloads last month - 35,523 stars on GitHub - 1 maintainer
archkeel 4.0.1
Architecture checks for coding agents
25 versions - Latest release: about 1 month ago - 1.6 thousand downloads last month - 18 stars on GitHub - 1 maintainer
squidbrake 0.14.26
Change control for AI agents. Everyday work runs on its own; anything an agent can't take back wa...
83 versions - Latest release: about 15 hours ago - 4.53 thousand downloads last month - 19 stars on GitHub - 1 maintainer
nirnay-450m 0.2.1
NIRNAY 450M: bring your own labels, get calibrated decisions locally (Banking77 87.9%)
2 versions - Latest release: about 15 hours ago - 9 stars on GitHub - 1 maintainer
autoagent-core 0.29.0
LLM agent library with tool use, dynamic tool generation, and software evolution capabilities
21 versions - Latest release: about 15 hours ago - 6.56 thousand downloads last month - 2 stars on GitHub - 1 maintainer
epistemic-guard 0.4.1
Signed tool receipts, out-of-process MCP receipt proxy, Ed25519 memory write-gating, and RAG dedu...
4 versions - Latest release: about 15 hours ago - 188 downloads last month - 1 stars on GitHub - 1 maintainer
verbatim-citation-gate 0.3.2
Catch fabricated RAG citations before they reach the user: a zero-token verbatim gate + a burden-...
1 version - Latest release: about 17 hours ago - 4 stars on GitHub - 1 maintainer
claim-check-ci 1.1.0
Every number you publish is a claim. Bind it to the artifact it came from and prove it in CI -- n...
1 version - Latest release: about 17 hours ago - 0 stars on GitHub - 1 maintainer
longguard 0.3.0
Circuit breaker middleware for LangGraph/LangChain agents — detect loops, inject Reflect & Pivot,...
12 versions - Latest release: about 20 hours ago - 829 downloads last month - 8 stars on GitHub - 1 maintainer
laya-guardrail 0.8.0
Free local guardrail for AI coding agents: every tool_call judged on-device (regex + Laya model) ...
20 versions - Latest release: about 20 hours ago - 1.29 thousand downloads last month - 35 stars on GitHub - 1 maintainer
sentinel-proof 0.1.2
Catch RAG hallucinations without an LLM judge: check every number and citation in an LLM answer a...
3 versions - Latest release: about 22 hours ago - 170 downloads last month - 0 stars on GitHub - 1 maintainer
datafog 4.12.0
Lightning-fast PII detection and anonymization library, 100x+ faster than NER-based detection (se...
178 versions - Latest release: about 23 hours ago - 35.2 thousand downloads last month - 80 stars on GitHub - 1 maintainer
fp-cloud-cli 0.0.3
Command line client for FailproofAI Cloud — sessions, events, evaluations and audits from your te...
6 versions - Latest release: about 22 hours ago - 213 downloads last month - 8,959 stars on GitHub - 1 maintainer
yana-ai 1.5.4 💰
Audits your AI coding agent setup before it can damage your repo. Scan first. Guard later.
10 versions - Latest release: about 24 hours ago - 384 downloads last month - 13 stars on GitHub - 1 maintainer
selfbrowse 0.2.1
Open-source Python browser agent for LLMs. A short numbered list of page elements instead of the ...
3 versions - Latest release: about 24 hours ago - 153 downloads last month - 1 stars on GitHub - 1 maintainer
mesedi-curl 0.1.0
Transparent curl wrapper that records direct LLM API calls to Mesedi
1 version - Latest release: 6 months ago - 20 downloads last month - 0 stars on GitHub - 1 maintainer
Top 1.8% on pypi.org
presidio-analyzer 2.2.366
Presidio Analyzer package
111 versions - Latest release: 21 days ago - 42 dependent packages - 49 dependent repositories - 5.94 million downloads last month - 11,887 stars on GitHub - 2 maintainers
Top 6.2% on pypi.org
presidio-image-redactor 0.0.62
Presidio image redactor package
26 versions - Latest release: 21 days ago - 3 dependent packages - 1 dependent repositories - 102 thousand downloads last month - 11,887 stars on GitHub - 2 maintainers
presidio-structured 0.0.10
Presidio structured package - analyzes and anonymizes structured and semi-structured data.
10 versions - Latest release: 21 days ago - 91.5 thousand downloads last month - 11,887 stars on GitHub - 1 maintainer
Top 2.2% on pypi.org
presidio-anonymizer 2.2.366
Presidio Anonymizer package - replaces analyzed text with desired values.
46 versions - Latest release: 21 days ago - 30 dependent packages - 20 dependent repositories - 3.47 million downloads last month - 11,887 stars on GitHub - 3 maintainers
presidio 2.2.366
Presidio - Data Protection and De-identification SDK
9 versions - Latest release: 21 days ago - 6.49 thousand downloads last month - 11,887 stars on GitHub - 1 maintainer
nvidia-nat-security 1.9.0
Safety and security plugin for NVIDIA NeMo Agent Toolkit (defense, guardrails, red-team)
186 versions - Latest release: 2 months ago - 2.44 thousand downloads last month - 2,702 stars on GitHub - 1 maintainer
taintwarden 0.7.0
Data-flow firewall for AI agents: blocks indirect prompt injection by tracking where every tool a...
7 versions - Latest release: 1 day ago - 113 downloads last month - 1 maintainer
langchain-vericto 0.1.0
An integration package connecting Vericto (database guardrails for AI agents) and LangChain: chec...
1 version - Latest release: 1 day ago - 1 maintainer
vouchwell 0.8.2
Tamper-evident receipts for AI agent actions. Python SDK, wire-compatible with the vouchwell CLI.
5 versions - Latest release: 1 day ago - 177 downloads last month - 1 stars on GitHub - 1 maintainer
fullcourtdefense 2.2.0
Control what your AI agents do: check every tool call against your company's FullCourtDefense pol...
7 versions - Latest release: 1 day ago - 220 downloads last month - 1 maintainer
humane-proxy 0.6.0 💰
Lightweight, plug-and-play AI safety middleware that protects humans.
10 versions - Latest release: 4 months ago - 194 downloads last month - 27 stars on GitHub - 1 maintainer
ctrlrun-langchain 1.0.0
Gate a LangChain agent's tool calls with a CTRLRun policy, through wrap_tool_call.
1 version - Latest release: 2 months ago - 124 downloads last month - 28 stars on GitHub - 1 maintainer
execlave-sdk 1.10.0
Official Python SDK for the Execlave AI Governance Platform — tracing, policy enforcement, and fr...
19 versions - Latest release: 1 day ago - 107 downloads last month - 0 stars on GitHub - 1 maintainer
agentx-security-sdk 0.5.11
Runtime firewall for AI agents - watches every tool call, and once switched on blocks the catastr...
80 versions - Latest release: 1 day ago - 968 downloads last month - 1 stars on GitHub - 1 maintainer
crossfoot 0.1.0
Fail-closed numeric grounding checks for LLM output: verifies stated and derived numbers, directi...
1 version - Latest release: 1 day ago - 1 maintainer
regent-control 0.14.1
Python SDK for Regent Control — runtime policy enforcement for AI agent actions (allow / deny / e...
16 versions - Latest release: 1 day ago - 742 downloads last month - 1 maintainer
tealtiger 1.6.1
TealTiger - AI agent security platform with guardrails, cost tracking, and policy management for ...
11 versions - Latest release: 1 day ago - 98 downloads last month - 2 stars on GitHub - 1 maintainer
aegis-ai-sdk 1.2.1
Chakravyuha — AI Governance Infrastructure SDK
3 versions - Latest release: 1 day ago - 97 downloads last month - 1 maintainer
theaios-guardrails 0.3.0
Declarative YAML-based policy engine for AI agent guardrails
10 versions - Latest release: 1 day ago - 462 downloads last month - 2 stars on GitHub - 1 maintainer
doberman-core 0.21.0
Adaptive authorization layer for coding agents (open core)
14 versions - Latest release: 1 day ago - 342 downloads last month - 243 stars on GitHub - 1 maintainer
Top 5.9% on pypi.org
nemoguardrails 0.24.1
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based ...
35 versions - Latest release: 2 months ago - 2 dependent repositories - 484 thousand downloads last month - 7,500 stars on GitHub - 4 maintainers
cc-captain-hook 0.1.0
Declarative hook framework for Claude Code
1 version - Latest release: 6 months ago - 120 downloads last month - 14 stars on GitHub - 1 maintainer
agenticreq 0.1.0a3
Checks whether an agentic AI system's declared requirements are enforced in its code, with measur...
3 versions - Latest release: 1 day ago - 252 downloads last month - 0 stars on GitHub - 1 maintainer
guardflow 0.1.0
Local-first input guardrails for LLM applications.
1 version - Latest release: 1 day ago - 1 maintainer
screwtape-pay-safely 0.1.0
Check that a seller is safe to pay before your AI agent pays. Drop-in for LangChain, LangGraph, C...
1 version - Latest release: 1 day ago - 1 maintainer
ferrogw 1.6.1 💰
Ferro Labs AI Gateway — one binary in front of 30 LLM providers
16 versions - Latest release: 2 days ago - 1.38 thousand downloads last month - 271 stars on GitHub - 1 maintainer
ckg-nvidia-guardrails 0.1.0
NeMo Guardrails as a traversable knowledge graph — 50 nodes, MCP-native, free
1 version - Latest release: 4 months ago - 1 maintainer
dutygate 0.2.0
DutyGate: a chatbot-agnostic gate that flags legal and compliance triggers in inbound messages be...
2 versions - Latest release: about 2 months ago - 48 downloads last month - 4 stars on GitHub - 1 maintainer
grapharc 0.1.7
A graph engineering toolkit on LangGraph: typed state contracts, per-node write permissions, enfo...
8 versions - Latest release: 3 months ago - 45 downloads last month - 88 stars on GitHub - 1 maintainer
dashclaw 5.39.0 💰
Govern Python agent callbacks with policy checks, remote approvals, execution claims, and outcome...
133 versions - Latest release: 8 days ago - 713 downloads last month - 318 stars on GitHub - 1 maintainer
failproofai-sdk 0.0.1b6
Emit agent telemetry to FailproofAI Cloud — zero-dependency, stdlib only
6 versions - Latest release: about 1 month ago - 2.01 thousand downloads last month - 8,959 stars on GitHub - 1 maintainer
emilia-crewai 0.3.5
Guard CrewAI tools with EMILIA Protocol — require an offline-verifiable authorization receipt (EP...
5 versions - Latest release: 2 months ago - 95 downloads last month - 550 stars on GitHub - 1 maintainer
forge-guardrails 0.10.1
A reliability layer for self-hosted LLM tool-calling. Guardrails, context management, and backend...
25 versions - Latest release: 15 days ago - 573 downloads last month - 2,270 stars on GitHub - 1 maintainer
ac-jobs-mcp 0.1.1
MCP server for AC Jobs - an admission gate that keeps AI agents on-goal.
2 versions - Latest release: 2 months ago - 1 maintainer
swarm-agents 3.0.0
Lightweight framework for LLM agents with tools, hooks, guardrails, and provider routing
33 versions - Latest release: 2 days ago - 1.5 thousand downloads last month - 1 maintainer
recusal-pydantic-ai 0.1.1
Recusal gate for Pydantic AI: judge every tool call in before_tool_execute, refuse before it runs...
2 versions - Latest release: 2 days ago - 6 stars on GitHub - 1 maintainer
recusal-google-adk 0.1.1
Recusal gate for Google ADK: judge every tool call in a before-tool callback or a runner plugin, ...
2 versions - Latest release: 2 days ago - 6 stars on GitHub - 1 maintainer
recusal-crewai 0.1.1
Recusal gate for CrewAI: judge every tool call in CrewAI's own tool-call hooks, block a refusal b...
2 versions - Latest release: 2 days ago - 6 stars on GitHub - 1 maintainer
ejentum 1.8.0
Deterministic Reasoning-Augmented Retrieval (RAR) Cognitive Infrastructure SDK
2 versions - Latest release: 2 days ago - 38 downloads last month - 1 maintainer
recusal 0.14.1
Lightweight, extensible governance for AI agent tool calls, Claude-native and framework-neutral: ...
46 versions - Latest release: 2 days ago - 1.76 thousand downloads last month - 6 stars on GitHub - 1 maintainer
agent-evidence-guard 0.1.1
Deterministic validation of AI-agent completion claims against evidence and authority requirements.
1 version - Latest release: 3 months ago - 119 downloads last month - 0 stars on GitHub - 1 maintainer
norcaster 0.1.1
Norcaster Python SDK: ask Norcaster for a decision (allow, hide or block) before your app calls a...
3 versions - Latest release: 2 days ago - 23 downloads last month - 1 maintainer
recusal-openai-agents-mcp 0.1.1
Recusal gate for MCP tools on an OpenAI Agents SDK agent: judge each local MCP server call and ea...
2 versions - Latest release: 2 days ago - 6 stars on GitHub - 1 maintainer
recusal-openai-agents 0.1.1
Recusal gate for the OpenAI Agents SDK: judge every function tool call in a tool input guardrail,...
2 versions - Latest release: 2 days ago - 6 stars on GitHub - 1 maintainer
recusal-langchain 0.1.1
Recusal gate for LangChain create_agent: the recusal-langgraph ToolNode gate as tool-call middlew...
2 versions - Latest release: 2 days ago - 6 stars on GitHub - 1 maintainer
recusal-openai 0.1.1
Recusal gate for the OpenAI API: judge every function call of a Responses or Chat Completions loo...
2 versions - Latest release: 2 days ago - 6 stars on GitHub - 1 maintainer
recusal-langgraph 0.1.1
Recusal gate for LangGraph: judge every ToolNode call at execution time, refuse before it runs, a...
2 versions - Latest release: 2 days ago - 6 stars on GitHub - 1 maintainer
aegis-guardrails 4.5.0
Project rules for AI coding agents (Claude Code, Codex CLI, Antigravity): MCP server, AGENTS.md b...
13 versions - Latest release: 14 days ago - 0 downloads last month - 4 stars on GitHub - 1 maintainer