Search

DevTorch — AI reasoning capture, audit trail, and governance for agent-assisted development

Python enterprise agent framework with AOP, IOC, and sandbox security

A provider-agnostic LLM toolkit with tool calling, skills, and parallel execution.

Qortara Governance — LangChain sidecar SDK. Deep tool-dispatch interception + Portable Trust Attestations + policy enforcement companion to LangSmith.

AI model: mradermacher/DeepSeek-R1-Clarity-AI-Agent-2-GGUF

AI model: smsk1999/qwen25-7b-slot-conf-agent-merged-v2

AI model: smsk1999/qwen25-7b-slot-conf-agent-merged

AI model: sjwjames0325/GRPO_agentic-Qwen2ForCausalLM-2B

AI model: yikeee/Open-Reward-Agent-sft-rubric-only

🦦 Crayotter: A Multimodal AI-Agent for Video-Editing, Video-Composing, and Video Production. Powered by Multimodal LLMs for autonomous Text-to-Video agentic framework. | 基于多模态大模型 (Multimodal LLMs) 的 AI 剪辑智能体，支持从文字需求到视频成品的端到端全自动生产与创作。

A hardened, containerized environment for running Claude Code as an AI agent with access to local tools via the Model Context Protocol (MCP).

A cognitive evolution framework for AI Agents based on Yogacara (Consciousness-Only) theory

Framework Claude Code : hooks d'enforcement, agents nommés (Steve, Isaac), Challenger, satellites par stack, mode nuit, permissions proactives. 11 rails / 16 règles. Zero dependency.

DeepSeek-native agent framework: Cache-First Loop, R1 Thought Harvesting, Tool-Call Repair. TypeScript + Ink TUI.

SCE Core is a cognitive AI architecture for state evolution, constraints, planning, memory, graph observability, and adaptive decision systems.

剧本分镜智能体（PenShot）：剧本→分镜→片段→prompt | 基于 LangGraph+LLM，自动解析任意格式剧本，生成 Sora/Veo/Runway 等模型可用的连贯text-to-video提示词。保持角色/剧情跨片段一致，支持 MCP/REST API/函数调用 | Python库 + A2A集成。（LLM-powered screenplay-to-video-prompt agent. Break scripts into Sora/Veo-ready shots with character consistency. LangGraph + Chroma + MCP）

Multi-agent skill discovery — search 4800+ skills from 14 sources for Claude Code, Codex, OpenCode, Cursor

Agentic Control Plane governance for LangChain / LangGraph agents. Wrap any tool with @governed; ACP decides allow/deny/redact.

Agentic Control Plane governance for CrewAI agents. Wrap any tool with @governed; ACP decides allow/deny/redact.

RawLLM – minimal orchestrator that exposes the raw power of LLMs