Search

Score AWS IAM policies for risk before granting access. Deterministic + LLM-narrative scoring as an API, CLI, and GitHub Action.

Safety-critical cognitive safety library for AI agents

LangChain utilities with token tracking, RAG, and agent support

A 15-agent CLI that runs DevRel, sales, and marketing on your repo. BYO Anthropic or OpenRouter key.

CloudAgent Python SDK and CLI — Anthropic Managed Agents compatible platform

AutoGen integration for the Dakera AI memory platform

Add your description here

OpenCOAT Runtime — concern/joinpoint/pointcut/advice/weaving/copr/dcn + storage + LLM + daemon + CLI

Host-side integration for OpenCOAT Runtime — joinpoint emitter, injection consumer, and first-party framework adapters (openclaw, hermes, langgraph, autogen, crewai, custom).

Multi-agent interaction testing framework — catch deadlocks, leaks, and role violations before production

Mihver — AI agent reliability layer. Catches Claude Code skills that should have fired but didn't.

Official Python SDK for Daguito — conversational AI flows, streaming webhooks, and RAG.

Multi-Agent System for Python (MASPY) with Machine Learning proprieties

Run Petri alignment audits against real agent scaffolds (Claude Code, Codex CLI, Gemini CLI) via ACP.

Thin local CLI relay for the prove-graph backend — spawns codex / claude / deepseek subprocesses on user machines and streams stdout/stderr back over WebSocket.

AI model: SALEETAI/coding-agent-qwen-sft-v3-GGUF

AI model: SALEETAI/coding-agent-qwen-sft-v2-GGUF

AI model: Agnuxo/Agente-GPT-Qwen2.5-3B-Instruct-Spanish_8bit

AI model: Agnuxo/Agente-GPT-Qwen-2.5-3B_GGUF_16bit

AI model: Agnuxo/Agente-GPT-Qwen2.5-3B-Instruct-Spanish_English_GGUF_q6_k