Search

The experimentation platform for agent organizations — run multi-agent orchestrations and factorial experiments entirely from text files.

A status light and a status line for Claude Code, in a cyberpunk terminal panel.

Structured thinking framework for AI agents, coding assistants, and developers to turn raw logs, events, and scattered data into decision-ready communication.

Minimal Node.js agent loop for Ollama: local LLMs that read/write/edit files, run shell commands, and call MCP tools. MCP client and server, two dependencies, fully offline.

Server with an AI agent powered by an LLM, with tools for internet search, Wikipedia, and RAG database access.

Immortal AI agents that never get dementia.

Fabio (FableWannabe): a Claude Code agent that emulates Fable's operational discipline on top of Opus, via a 6-phase reasoning pipeline and 13 skills.

LLM tool and agent-loop utilities for actor-web runtime hosts

Poison-resistant, Byzantine-fault-tolerant shared memory for Microsoft AutoGen agent teams — implements the autogen_core Memory protocol; one rogue agent can't corrupt the team's recall.

Versioned identity blocks for LLM agents -- self-evolution via a linear version chain with propose/consent/apply, rationale, and rollback

Poison-resistant, Byzantine-fault-tolerant shared memory + robust voting tools for CrewAI crews — one rogue agent can't corrupt what the crew remembers or how it votes.

LangChain tools for ReplyLayer — governed email for AI agents

Standing-wants corpus for LLM agents -- intention lifecycle, salience decay, embedding dedup, and private deliberation tools

Governed AI project doc-kit validator — check CLAUDE.md, AGENTS.md, governance.yaml and the decision log as a CI gate.

The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere

Reusable, tool-agnostic agent workflows (review, assess, advise, verify, setup) plus a CLI to install them into any repo.

Alias stub for agents-live (take your agents live). Install agents-live instead.

Skarmy's Hiring Lead — plans the earliest hires, drafts listings and exports, publishes the careers-page spec, and screens applicants (recommend-only). Prompt-runtime agent.

CI for AI agents - behavioral fingerprinting and drift detection

The game console for AI agents: behavioral research through game scenarios