Agent harnesses
ClawVault
tophant-ai/ClawVault
ClawVault is a security vault for OpenClaw and Claude Code that intercepts sensitive data, prompt injection, and dangerous commands through a proxy and agent hooks.
Topics
Related projects
ClawKeeper1kHost-agnostic safety middleware for tool-using agents that blocks risky tool calls and delegates trajectory decisions to a Watcher.
ClawX7.6kA desktop client for OpenClaw agents that replaces CLI orchestration with chat, scheduling, channels and skill management.
defending-code-reference-harness7.7kA reference implementation from Anthropic that pairs Claude Code skills with an autonomous, sandboxed vulnerability-discovery pipeline covering recon, finding, verification, reporting, and patching.
nexu3.3kAn open-source desktop client that bridges your AI agent to WeChat, Feishu, Slack, and Discord in one click.
cc-safety-net2kCC Safety Net is a pre-execution guard for AI coding agents that parses commands and blocks destructive Git/filesystem operations and secret access across many coding CLIs.
OpenAPPA1.6kA deterministic guardrail layer that sits between an agent and its tools, enforcing data-flow policies before every tool call so sensitive information cannot reach unauthorized destinations.