Library
85,336 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
guardrails
AI repositoriesAdding guardrails to large language models.
git clone https://github.com/guardrails-ai/guardrails.git -
Guardrails
AI repositoriesNeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
git clone https://github.com/NVIDIA-NeMo/Guardrails.git -
baml
AI repositoriesThe programming language for agents
git clone https://github.com/BoundaryML/baml.git -
laya
Modelstext classification model by convaiinnovations · transformers
convaiinnovations/laya -
semantic-router
AI repositoriesAn open, programmable decision layer for models and compute.
git clone https://github.com/vllm-project/semantic-router.git -
ragbits
PromptsBuilding blocks for rapid development of GenAI applications
git clone https://github.com/deepsense-ai/ragbits.git -
gateway
AI repositoriesA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
git clone https://github.com/Portkey-AI/gateway.git -
Sponsio
SkillsDeterministic safety solutions for probabilistic AI agents
git clone https://github.com/SponsioLabs/Sponsio.git -
superagent
AI repositoriesSuperagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.
git clone https://github.com/superagent-ai/superagent.git -
spring-ai-privacy-guardrails
MCP serversPrivacy guardrails for Spring AI: request-scoped PII tokenization, least-privilege disclosure to tools, and optional Spring Security tool authorization. Supports Presidio and JVM-local OpenNLP.
git clone https://github.com/ultramancode/spring-ai-privacy-guardrails.git -
guardrail-forge
SkillsCorrect Claude once. It stays corrected. A Claude Code skill that turns corrections into tested, tamper-proof hook guardrails.
git clone https://github.com/MohammedAtya/guardrail-forge.git -
future-agi
Agents & frameworksOpen-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
git clone https://github.com/future-agi/future-agi.git -
laya-multilingual
Modelstext classification model by convaiinnovations · transformers
convaiinnovations/laya-multilingual -
failproofai
AI repositoriesObservability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement.
git clone https://github.com/FailproofAI/failproofai.git -
autoguardrails
Datasets & benchmarksAlignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface
git clone https://github.com/SantanderAI/autoguardrails.git -
hoop
AI repositoriesOpen-source enforcement at runtime that masks sensitive data and blocks destructive commands from AI agents. You change one thing: your agent's port.
git clone https://github.com/hoophq/hoop.git -
agentic_security
Agents & frameworksAgentic LLM Vulnerability Scanner / AI red teaming kit 🧪
git clone https://github.com/msoedov/agentic_security.git -
llmgateway
AI repositoriesRoute, manage, and analyze your LLM requests across multiple providers with a unified API interface.
git clone https://github.com/theopenco/llmgateway.git -
elephant-1
Modelstext classification model by baselabs · transformers
baselabs/elephant-1 -
guardrails
MCP serversAI Agent Guardrails MCP server - security layer
guardrails-mcp-server@1.0.1 -
mammoth-1
Modelstext classification model by baselabs · transformers
baselabs/mammoth-1 -
ai-guardrails
MCP serversCloudflare Workers MCP server: ai-guardrails
-
nemo-helix
Agents & frameworksNeMo Helix: Make the agents you ship faster, more accurate, and safer.
git clone https://github.com/NVIDIA-NeMo/nemo-helix.git -
javelin-guardrails-mcp-server
MCP serversAn MCP server that provides Javelin Standalone Guardrails
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.