AI Agent Identity and Access Management and Inference Firewall
- agent-identity
- ai-audit
- ai-firewall
- ai-gateway
Repository Index
47,133 repositories indexed
73–96 of 100 · Most stars
Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merged into open-source projects at Microsoft, Cisco, Gen Digital, MISP and FINOS. MIT-licensed.
- agent-security
- ai-security
- llm-security
- mcp-security
Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your strongest model for the hard parts.
- model-routing
- task-routing
- ai-agents
- ai-gateway
A Java library to use the OpenAI Api in the simplest possible way.
- httpclient
- java
- openai
- simple
OpenAI-compatible async gateway for muse.ai with pluggable drivers (mock / browser-CDP / http)
C++/CUDA single-GPU inference engine for Qwen3.8 (incl. Qwen3.8-Flash-Next with offloaded experts) on the RTX 5090; grew from NInfer
Uncensored AI API and models — one key for Claude, GPT, Gemini, Grok, DeepSeek, GLM and Kimi, with uncensored and abliterated variants where available. OpenAI- and Anthropic-compatible. Pay per token.
- abliterated-models
- ai-gateway
- anthropic-compatible
- claude-api
Go AI SDK, the Go way. One unified API across 21+ providers. Streaming, structured output, MCP support, stdlib only. Go AI SDK for AI applications inspired by Vercel AI SDK.
Free AI models for every coding tool — a local OpenAI-compatible gateway for Claude Code, Codex, Cursor, Cline and OpenCode. Based on 9router (MIT).
TranslatedA relay API jailbreak project written in Rust, supporting the Responses / Chat Completions / Anthropic Messages APIs, and supporting most mainstream models such as ChatGPT/Claude/Grok/Gemini/Deepseek/Glm/Kimi
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
TranslatedMy RAG system, which can be used to import a knowledge base for knowledge Q&A, can integrate third-party MCP, and also has permission isolation, etc.
OpenRouter alternative for uncensored AI LLM access — independent RouterHub gives developers one OpenAI- and Anthropic-compatible key for 37 frontier and open-weight models, including GPT, Claude, Grok, DeepSeek and GLM, with published per-token pricing and abliterated or uncensored entries where available.
- abliterated-models
- ai-api-gateway
- ai-model-router
- ai-models
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.
Smart routing, seamless flow
Uncensored AI models from RouterHub — the website for one-key API access to Claude, GPT, Gemini, Grok, DeepSeek, GLM and Qwen, with uncensored and abliterated variants where available. OpenAI- and Anthropic-compatible. Pay per token.
- abliterated-models
- ai-api
- ai-gateway
- anthropic-compatible
Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
- action-proposals
- agentic-ai
- agents
- ai
OpenTelemetry-native tracing, token tracking, cost attribution, and prompt analytics for Go backends integrating LLMs.
Instruct LLMs to do what you want in Ruby
- ai
- gem
- ruby
- rubyml
Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
- golang
- observability
- opentelemetry
- policy-engine
You need customized prompts for your tasks! 🤏SimpleGPT is a Vim plugin designed to provide a simple yet flexible way to customize your prompts for your tasks or building chat on nearly all kinds of LLM APIs.
Improve Open Assistant with ChatGPT.
🧭 Let your coding agent off the leash — not off the rails. Guardrails, a hard budget cap & a self-fixing PR loop for Claude Code / Codex / Gemini. Eval-gated 100/100, you always merge.
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.
- agentic-ai
- ai-safety
- fastapi
- langchain