brainstate

occludra/gateway

Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.

Python★ 49Apache-2.0GitHub ↗

History and source changes · Reports and owner responses · Compare

Similar

  1. SoupTeam/soup-wall

    Soup Wall: open-source security for AI agents and model traffic. Local Agent, Gateway, self-hosted Console. Apache-2.0.

    Python★ 29Apache-2.0GitHub ↗

    Why this match

    topics ai-security, llm-security, prompt-injection

  2. AGGIB/Stroq

    Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky commands to the content that dictated them. Open source, no telemetry.

    TypeScript★ 19Apache-2.0GitHub ↗

    Why this match

    topics ai-security, llm-security, prompt-injection; language differs: Python → TypeScript

  3. Tencent/AI-Infra-Guard

    A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

    Python★ 7.4kApache-2.0GitHub ↗

    Why this match

    topics ai-security, llm, llm-security

  4. superagent-ai/superagent

    Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.

    TypeScript★ 6.8kMITGitHub ↗

    Why this match

    topics llm, prompt-injection; language differs: Python → TypeScript; license differs: Apache-2.0 → MIT

  5. mattijsmoens/sovereign-shield

    Deterministic AI defense framework: immutable input filtering, n-model cryptographic hash consensus, and self-learning adaptive rules. Zero dependencies. Hardware-sealed.

    Python★ 21GitHub ↗

    Why this match

    topics ai-security, llm-security, prompt-injection

  6. NVIDIA/SkillSpector

    Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.

    Python★ 24.3kApache-2.0GitHub ↗

    Why this match

    topics ai-security, prompt-injection

  7. ConiferKit/use-conifer

    The Conifer SDK — one gateway for cloud, local, and BYOK inference, with exact per-call cost receipts. TypeScript + Python + MCP.

    TypeScript★ 49Apache-2.0GitHub ↗

    Why this match

    topics llm, openai-compatible; language differs: Python → TypeScript