clawless
ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers
- 546
- TypeScript
- MIT
- 5 mo ago
ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
Govern consequential AI agent actions in Docker with deterministic policy, human approval, and signed Decision Dossiers.
Guardrails service for AI agents. Default-deny tool call evaluation with LLM safety analysis, priority-ordered decision matrix, and human-in-the-loop escalations. Session recording, behavioral analysis, MCP proxy, secret redaction, and real-time audit.
Policy-aware AI permission reviewer for OpenCode V1 and V2. Evaluates tool and command requests, allowing, denying with feedback, or escalating to the user.
eBPF Information Flow Enforcement for AI Agent safety, security and effectiveness
Passport & visa system for AI agent credentials. Detect, classify, and govern API keys, tokens, and secrets across MCP, OpenAI, Anthropic, LangChain, and more. Encrypted vault, policy engine, audit trails, delegation chains. Drop-in MCP server replaces plaintext credential storage.
Open-source deployment and governance control plane for internal AI agents — hosts each agent, scopes its tools and domains, meters token spend against budgets, and gives IT a kill switch and audit trail. TypeScript monorepo (CLI, runtime, Convex + Hono control plane).
Structured policy decisions for AI-generated shell commands and filesystem paths.
Workflow rails for agentic coding: one shared task and policy core with native OpenCode, Cursor, Codex, Pi, and CLI surfaces.
Policy-first API and policy gate for AI/CLI workflows: detect sensitive data, decide allow/transform/deny, and emit auditable receipts.
Dependency impact reports and policy gates for Rust workspaces. Snapshot, diff, reverse-BFS impact graph, transparent risk scoring, YAML policy, CycloneDX SBOM evidence, SARIF, and idempotent PR comments.
Security-focused approval reviewer for Oh My Pi (OMP) with deterministic safety gates, isolated LLM review, and auditable tool decisions.
Behavioral policy engine for AI agents. Define rules, enforce them at runtime — like a firewall for agent behavior. Built with Rust, Axum, and PostgreSQL.
Runtime authorization for AI agents. Agents get credentials and network access without ever receiving the actual credentials.
Guardian — security policy engine + monitoring + anomaly detection for OpenClaw
Frontend for RAGuard — an agent governance platform for monitoring, enforcing policies, and testing LLM-powered agents. Built with Next.js 15, shadcn/ui, and React Flow.
Infrastructure-grade identity, authorization and audit control plane for AI agents
Guarded browser task control plane with Azure-backed action planning, YAML policy evaluation, approval checkpoints, and replay timelines.
The security, governance and control plane for AI agents: identity, policy, approvals, secrets, threat detection and a tamper-evident audit log