HN Showcase
Back to browse
GitHub Repository

The governance layer for AI agents — monitor reasoning, audit tool calls, and secure the loop through OHTTP privacy routing.

24 starsRust

Anonymize LLM traffic to dodge API fingerprinting and rate-limiting

by clawshield·Feb 26, 2026·1 point·0 comments
Visit ProjectView on HN

AI Analysis

●MidBold Bet

OHTTP proxy for OpenClaw, but only tested on two providers and limited adoption.

Strengths
  • •Double-blind architecture (relay + gateway) genuinely hides IP from content visibility and vice versa—cryptographically sound approach.
  • •Addresses real community pain point: silent rate-limiting reports on OpenClaw specifically and distillation pressure concerns.
Weaknesses
  • •Extremely narrow applicability: OpenClaw is a niche tool, and ecosystem fragmentation means setup complexity for relay/gateway infrastructure.
  • •No evidence of actual effectiveness: claims about provider-side fingerprinting reduction are theoretical; no benchmarks or comparative rate-limit tests shown.
Category
Security
Target Audience

Heavy users of OpenClaw and LLM clients concerned about API provider fingerprinting and silent rate-limiting

Similar To

WireGuard · Tailscale

Post Description

As a heavy user of OpenClaw and various LLM clients, I’ve started noticing a disturbing trend: API providers are getting much better at "identifying" us. It’s not just about the API key anymore—it's your IP, your request timing, and your client’s specific HTTP fingerprint.

Anthropic’s recent reports on "distillation-pressure" and the community whispers about "silent" rate-limiting for specific IP ranges got me thinking: Why am I giving OpenAI/Google my home IP with every single prompt?

What I Built: I built Claw Shield. It’s a privacy layer for OpenClaw (and potentially any OpenAI-compatible client) that implements Oblivious HTTP (OHTTP).

How it works: Instead of a direct connection, Claw Shield uses a double-blind architecture:

The Client (OpenClaw Plugin) encrypts your request using HPKE.

The Relay (Cloudflare) sees your IP but cannot see your request content.

The Gateway (Your CF Worker) sees your request content but cannot see your IP.

The Model Provider sees the request coming from Cloudflare’s edge infrastructure, not you.

Why this is better than a simple VPN/Proxy:

Zero Trust: Even the Relay can't log your prompts, and the Gateway can't log your identity. You don't have to trust me or the relay provider.

Fingerprint Reduction: By standardizing the traffic through OHTTP/BHTTP, we strip away the unique signatures that providers use to identify "third-party client" traffic.

Open Source & Self-Hostable: Both the Relay and Gateway are lightweight Cloudflare Workers you can deploy in 1 click.

Status: Verified working for Gemini and OpenAI. Supporting Anthropic and others via providerTargets.

Repo: https://github.com/xinxin7/claw-shield

Similar Projects

AI/ML●●Solid

AgentForge – Multi-LLM Orchestrator in 15KB

AgentForge packs provider adapters (Claude, GPT‑4, Gemini, Perplexity), token-aware rate limiting, retry/backoff, and a MockLLMClient for tests into a tiny dependency surface — the 15KB footprint and 2 dependencies is an attention-grabber. The 3‑tier Redis cache and benchmark claims (huge latency/memory wins vs LangChain, 88% cache hit) make it a tempting low-overhead alternative, though you should validate provider feature parity and benchmarks against your workload.

Dark HorseWizardry
chunktort
103mo ago
Infrastructure●●Solid

VoidLLM – privacy-first LLM proxy (Go, self-hosted)

Zero-knowledge architecture means prompts never touch disk — unlike LiteLLM.

Solve My ProblemSlick
chrisremo85
342mo ago