Search

Cluster manifest, orchestration, and stationary state verification for Riverbraid.

Deterministic refusal and boundary enforcement layer for Riverbraid.

Controlled DeepScientist fork that stabilizes MedAutoScience runtime and absorbs upstream improvements through audited intake.

Secure, local-first multi-agent orchestration platform with policy-driven execution and guardrails.

Foundational invariants and verification surfaces for Riverbraid.

Cryptographic integrity layer for Riverbraid seals, hashes, and signatures.

ASRP — An open-source framework for AI-agent collaborative scientific research. Encode scientific methodology into agent workflows: experiment registration, independent cross-validation, audit trails, and reproducible research pipelines.

Resources on building software with coding agents. Blog posts and case studies from teams doing it in production.

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

LangChain toolkit for RICO — let AI agents post tasks for humans in the physical world

Autonomous experiment loop runner — run 100 optimization experiments overnight. Define your goal in Markdown, bring your own LLM key, wake up to a better system.

Bridge/glue layer that composes Agently (LLM/TriggerFlow) with skills-runtime-sdk (skills/tools/WAL/events).

Omega Walls v1 safety layer for RAG/agents

AI skill for version iteration control — bumps version across all config files and forces README/docs to stay in sync. Never lets documentation fall behind the version.

The ultimate AI design skill for producing distinctive, production-grade frontend interfaces

Reusable skill for tracking what AI agents build, how long it takes, and what it costs

AI agent skills that build and run your business autonomously — from idea to revenue, 24/7. Works with Claude Code, Codex CLI, and Gemini CLI.

Spec-Driven Development toolkit for AI agents. Install production-ready skills in seconds.

Codex-style multi-agent orchestration for pi — spawn, communicate with, and coordinate sub-agents via LLM tool calls

8 minds. 1 question. Infinite consequences. Multi-agent deliberation with K-ZERO Console.