47,133 repositories indexed
25–41 of 41 · 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.
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
A Unified Framework for Efficient RSI Research
Our lightning-fast inference engine.
A Hub/research area, for jailbreaking LLM's, and breaking their safety filters.
Cross-platform desktop LLM client for OpenAI ChatGPT, DeepSeek R1, Anthropic Claude and more, with a focus on privacy and security.
MobiInfer runs 35B-A3B-class MoE models fully on-device on the Qualcomm Hexagon NPU, streaming experts from flash with lookahead scheduling (LES) and DSpark speculation.
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
🌊 Floom, "The K8s for AI", orchestrates & executes Generative AI pipelines, Empowering Developers and DevOps to focus on what matters.
PHP client for the Anthropic API: messages, streaming, tool use, thinking, web search, code execution, batches, and more.
Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
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.
Deterministic quality scorer for AI agent instruction files — 8-dimension scoring with security, multi-format (SKILL.md, CLAUDE.md, .cursorrules, AGENTS.md), anti-gaming detection, zero dependencies