Library
87,246 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
destructive_command_guard
Agents & frameworksA fast Rust safety hook that blocks destructive shell, git, and filesystem commands before AI coding agents run them. 50+ security packs (databases, Kubernetes, Docker, cloud, Terraform), heredoc/inline-script scanning, CI scan mode, and explain mode; works with Claude Code, Codex, Gemini, Copilot, Cursor, and more.
git clone https://github.com/Dicklesworthstone/destructive_command_guard.git -
dev-machine-guard
Agents & frameworksScan your dev machine for AI agents, MCP servers, IDE extensions, and suspicious packages - in seconds.
git clone https://github.com/step-security/dev-machine-guard.git -
hol-guard
Agents & frameworksOpen-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
git clone https://github.com/hashgraph-online/hol-guard.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 -
project-quarry
Agents & frameworksDetection DSL and engine for AI agents
git clone https://github.com/cisco-ai-defense/project-quarry.git -
Doberman-Core
Agents & frameworksYour AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.
git clone https://github.com/DobermanCore/Doberman-Core.git -
agentic_security
Agents & frameworksAgentic LLM Vulnerability Scanner / AI red teaming kit 🧪
git clone https://github.com/msoedov/agentic_security.git -
dsh-memory
Agents & frameworks白箱AGI架构探索:元认知(自我认知循环)、持续学习(知识飞轮)、世界模型(条件空间+语义时空图)、自我改进(自举纪律)、零LLM白箱管线与可审计信任护栏。
git clone https://github.com/FuRongJun-1999/dsh-memory.git -
cc-safety-net
Agents & frameworksA pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
git clone https://github.com/kenryu42/cc-safety-net.git -
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 -
aisix
Agents & frameworksOpen-source AI gateway for LLMs & AI agents, built in Rust. One OpenAI-compatible API for OpenAI, Anthropic, Gemini, Bedrock & more — routing, guardrails, caching, rate limits, observability.
git clone https://github.com/api7/aisix.git -
harness-score
Agents & frameworksYour AI coding agent is only as reliable as the harness around it. Measure that harness in seconds with harness-score.
git clone https://github.com/paladini/harness-score.git -
teaql-agent-kit
Agents & frameworksA model-driven harness for AI coding agents: semantic modeling, app generation, progressive API Assist and evidence-based verification.
git clone https://github.com/teaql/teaql-agent-kit.git -
agentlint
Agents & frameworksLocal guardrails for AI coding agents. Check proposed file changes and shell commands, block risky patterns, and return actionable feedback. Works with Claude Code, Codex, Cursor, Gemini CLI, and more
git clone https://github.com/mauhpr/agentlint.git -
awesome-jev
Agents & frameworksA curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions.
git clone https://github.com/cobanov/awesome-jev.git -
chainloop
Agents & frameworksAgentic SDLC infrastructure. Define guardrails. Collect signals. Enforce continuously. Signed records of what your AI coding agents and CI/CD pipelines did, checked against policies as code, with the loop closed in CI/CD. AI sessions, SBOMs, VEX, SARIF and SLSA provenance, built on Sigstore and in-toto. Apache 2.0.
git clone https://github.com/chainloop-dev/chainloop.git -
Tracekit
Agents & frameworksTamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
git clone https://github.com/Cygnux-Labs/Tracekit.git -
agentos
Agents & frameworksTypeScript AI agent framework: cognitive memory, dynamic personalities, emergent behaviors and self-building designs
git clone https://github.com/framerslab/agentos.git -
audited-change-gate
Agents & frameworksAutomated Proof-of-Carrying Change Management for AIOps 2026
git clone https://github.com/ChristoAnsek/audited-change-gate.git -
cuga-agent
Agents & frameworksCUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.
git clone https://github.com/cuga-project/cuga-agent.git -
opencode-swarm
Agents & frameworksArchitect-centric agentic swarm plugin for OpenCode. Hub-and-spoke orchestration with SME consultation, code generation, and QA review.
git clone https://github.com/ZaxbyHub/opencode-swarm.git -
pilotfish
Agents & frameworksMulti-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.
git clone https://github.com/Nanako0129/pilotfish.git -
LightAgent
Agents & frameworksLightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaboration, and workflows.
git clone https://github.com/wanxingai/LightAgent.git -
scholar-loop
Agents & frameworksAn autonomous AI scientist: a multi-agent loop over literature, experiments, self-critique and write-up, with deterministic guards against reward-hacking and hallucination.
git clone https://github.com/r2m-ai/scholar-loop.git
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.