Agent harnesses
OpenAPPA
archestra-ai/OpenAPPA
A 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.
Topics
Related projects
superagent6.8kAn open-source SDK for AI agent safety that blocks prompt injections, redacts PII and secrets, and scans repositories for threats. Developers embed it via TypeScript, Python, or an MCP server to guard agent deployments.
hoop842An open-source runtime control sidecar for AI agents that masks sensitive data and blocks destructive SQL or HTTP commands on the wire, with risk analysis and human review, requiring only a port change.
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.
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.
ClawVault1.1kClawVault is a security vault for OpenClaw and Claude Code that intercepts sensitive data, prompt injection, and dangerous commands through a proxy and agent hooks.
helm-d1kA DeepSeek Harness plugin that adds 49 security-analysis tools, 353 references, evidence-chain enforcement and switchable personas for authorized Android, web, native and malware work.