Search

In-process MakerChecker governance. Import the pure primitives — deny-by-default authorization + separation of duties — with no server, no Postgres, and no audit chain; add the signed, offline-verifiable chain only when you want it.

Record and replay LLM agent tool calls for deterministic testing

MCP tool that leverages your agent's LLM to document what happened during your current session, in a specified user folder.

Typed, model-agnostic LLM agents in Swift — a pydantic-ai port built on Apple FoundationModels. Anthropic Claude, OpenAI, Google Gemini, and on-device, with tools, structured output, streaming, and a graph-based run engine.

Standalone task-board viewer/editor for tasks.md/planMD/spec artifacts produced by 1bcoder's deepagent_md/deepagent_spec/deepagent_task flows. No LLM calls.

Command-line tool for managing Discord servers and automating Discord via AI agents

Generate local Markdown, HTML, and JSON review cards from agent trace JSON.

agents-server — Python SDK for building AI agent services

Validate and build a synthetic agent and robotics failure gallery with reproducible review records.

Utility for simple encrypted data storage using RSA signatures via ssh-agent

AI Agent Skill for FluxSQL Workbench

Tool-agnostic role-to-model mapping for agentic coding workflows

Mailtea Python SDK — send, schedule, and manage email from your app or AI agent.

InfoLang memory integration for LlamaIndex

Autonomous SX Bet sports agent — Falcon signals, local EIP-712 execution

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.

Local AI chat with tool use, browser automation, vision, and sub-agents. Built on llama.cpp + Rust + Tauri.

AI-native programming language for building LLM agents, typed data models, and monadic pipelines — Haskell-inspired syntax, native Swift toolchain, built-in LSP and package manager.

Agent and CLI for the Jetson Arena: how a given Jetson device handles a whole model stack. Benchmarks pipelines (e.g. realtime VAD + STT + LLM + TTS on an Orin Nano Super 8GB) for latency, memory signature and quality, then publishes results plus signed-in Docker build recipes. Also maintains the arena public site.

Sentinel audit engine: deterministic heuristic rules, scoring, data model, lockfile parsing, SBOM export, and pluggable LLM adapter.