Search

A modular, extensible AI Agent framework with multi-provider support and plugin architecture

Generative AI audits for LLM, RAG, and agentic AI systems

EvalFloor: is your LLM eval improvement real? Trying k prompt variants and keeping the best scores points on noise alone -- this computes how many, so you can tell a real gain from a lucky sample.

An estate's public projection of its authority (spec 410 §4): the live-grant root and the membership root over blinded commitments, anchored on public ground; the authority presentation a verifier in another estate checks against them, learning that a gra

A general-purpose single-agent framework, currently under personal development.

The agent loop where decisions don't cost a large language model call. Zero deps, runs offline, no API key needed.

SuperX CLI - command line interface to the SuperX API for Twitter/X growth: read posts and analytics, find engaged contacts, and schedule posts and threads

Universal AI Agent Skill for iPhone Duo (dual-screen / foldable) iOS project readiness analysis and refactoring

AI agent interface for WeChat Web — send/receive messages, manage contacts, upload media, transcribe voice

Execution safety for side-effecting AI agent tools.

Preflight AI coding repositories before Codex, Copilot, Cline, Claude, Gemini, Continue, or Cursor touches them.

A benchmark for evaluating LLM agents on integrated circuit layout tasks.

Client SDK for Interagentic — federated bot identity, authentication, and payments

React hooks and headless components for Interagentic auth + payments

Next.js SDK for Interagentic auth — middleware, server auth(), route handlers, SSR provider

PostgreSQL (pgvector) StorageBackend for CrewAI unified Memory — hierarchical scopes, categories, metadata filters and native vector search

Long-term memory engine for LangGraph over any BaseStore — LLM fact extraction, consolidation, and recall ranked by semantic similarity, recency and importance (a maintained alternative to LangMem)

JevTrace tracer — 3-line integration for any agent, LangChain/LangGraph auto-tracing

Deterministic regression gate for CI: proves which tests a change broke. Zero dependencies, no LLM in the decision.

A small example package