Search

The open agent control plane. Govern autonomous AI agents with pre-execution policy enforcement, approval gates, and audit trails. Works with LangChain, CrewAI, MCP, and any framework.

Provider-pool-aware multi-agent coding orchestration.

Interactive terminal CLI for building and running LLM agents. Built with LangChain, LangGraph, Prompt Toolkit, and Rich.

layer that lets you connect any agent, any tool, any api together.

SynthCode — the open-source Claude Code alternative. Battle-tested agent framework, model-agnostic, TypeScript-first, MIT licensed.

AI 助手的模組化能力框架：記憶、防禦、診斷、品質穩定 | Modular capability framework for AI assistants | Claude Code / Cursor / Any LLM

Self-improving AI coding assistant for your terminal. Powered by Kimi K2.5 (Moonshot AI) via NVIDIA NIM API. 11 built-in tools, plugin system, web search, persistent memory.

Governed audio input and output contract surface for Riverbraid.

Governed vision input and perception contract surface for Riverbraid.

Reference architecture for closed-loop AI agents — plan, execute, verify, repair.

Governed action execution surface for Riverbraid.

Riverbraid v1.5.0 | Resonant Intelligence Architecture

The identity anchor and sovereign GPG verification petal for the Riverbraid organization.

Execution bridge from verified state into system action surfaces.

The deterministic UI contract and relational interface substrate for the Riverbraid cluster.

The central directory and Merkle Root mapping for the 17-petal Riverbraid v1.5.0 substrate.

Deterministic governance predicates and allow or deny decision logic for Riverbraid.

Temporal contracts and governed time based state logic for Riverbraid.

Cluster wide verification harness for byte floor, seals, and stationary state checks.

Cognitive architecture and meaning processing layer adjacent to the Riverbraid core.