backbay-labs/clawdstrike
Runtime security enforcement and threat hunting engine for autonomous AI fleets. Build Swarm Detection & Response (SDR) platforms with Clawdstrike.
Cryptographically signed policy enforcement at the tool boundary prevents unauthorized agent actions before execution, with Ed25519-signed receipts providing non-repudiable audit trails. Integrates with major LLM frameworks (OpenAI, Claude, LangChain) via a canonical adapter layer, and coordinates swarm-wide policies through NATS JetStream transport with kernel telemetry correlation (Tetragon, auditd) and SIEM integration. Provides 13 composable guards covering filesystem access, secrets, shell execution, prompt injection, and threat screening—fail-closed by default with operational control via a dedicated Spine C2 plane.
240 stars and 86 monthly downloads.
Stars
240
Forks
23
Language
Rust
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Monthly downloads
86
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/backbay-labs/clawdstrike"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Compare
Related agents
23blocks-OS/ai-maestro
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph...
ImKKingshuk/LockKnife
LockKnife: The Ultimate Android Security Research Tool. A unified TUI workspace and headless CLI...
conorluddy/ios-simulator-skill
An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and...
FlineDev/ContextKit
Claude Code context engineering & planning system for individual AI development workflows
mishabar410/PolicyShield
Declarative firewall for OpenClaw tool calls.